2022-04-18 23:48:18,587 - mmseg - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: A100-SXM-80GB CUDA_HOME: /mnt/lustre/share/cuda-11.3 NVCC: Build cuda_11.3.r11.3/compiler.29920130_0 GCC: gcc (GCC) 5.4.0 PyTorch: 1.9.0+cu111 PyTorch compiling details: PyTorch built with: - GCC 7.3 - C++ Version: 201402 - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.1.2 (Git Hash 98be7e8afa711dc9b66c8ff3504129cb82013cdb) - OpenMP 201511 (a.k.a. OpenMP 4.5) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.1 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86 - CuDNN 8.0.5 - Magma 2.5.2 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.9.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, TorchVision: 0.10.0+cu111 OpenCV: 4.5.5 MMCV: 1.4.2 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 11.1 MMSegmentation: 0.20.2+ ------------------------------------------------------------ 2022-04-18 23:48:18,588 - mmseg - INFO - Distributed training: True 2022-04-18 23:48:18,936 - mmseg - INFO - Config: norm_cfg = dict(type='SyncBN', requires_grad=True) model = dict( type='EncoderDecoder', pretrained='pretrained/beit_large_patch16_224_pt22k_ft22k.pth', backbone=dict( type='BEiTDenseAdaptor', patch_size=16, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4, qkv_bias=True, use_abs_pos_emb=False, use_rel_pos_bias=True, img_size=640, init_values=1e-06, drop_path_rate=0.3, conv_inplane=64, n_points=4, deform_num_heads=16, interact_with_ffn=True, interact_ffn_ratio=0.25, interact_deform_ratio=0.5, extract_with_ffn=True, extract_ffn_ratio=0.25, extract_deform_ratio=0.5, num_extract_block=2, add_vit_feature=True, interact_indexes=[[0, 5], [6, 11], [12, 17], [18, 23]]), decode_head=dict( type='UPerHead', in_channels=[1024, 1024, 1024, 1024], in_index=[0, 1, 2, 3], pool_scales=(1, 2, 3, 6), channels=1024, dropout_ratio=0.1, num_classes=171, norm_cfg=dict(type='SyncBN', requires_grad=True), align_corners=False, loss_decode=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)), auxiliary_head=dict( type='FCNHead', in_channels=1024, in_index=2, channels=256, num_convs=1, concat_input=False, dropout_ratio=0.1, num_classes=171, norm_cfg=dict(type='SyncBN', requires_grad=True), align_corners=False, loss_decode=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)), train_cfg=dict(), test_cfg=dict(mode='slide', crop_size=(640, 640), stride=(426, 426))) dataset_type = 'COCOStuffDataset' data_root = 'data/coco_stuff164k' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) crop_size = (640, 640) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=(640, 640), cat_max_ratio=0.75), dict(type='RandomFlip', prob=0.5), dict(type='PhotoMetricDistortion'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size=(640, 640), pad_val=0, seg_pad_val=255), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(2560, 640), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='ResizeToMultiple', size_divisor=32), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=2, workers_per_gpu=4, train=dict( type='COCOStuffDataset', data_root='data/coco_stuff164k', img_dir='images/train2017', ann_dir='annotations/train2017', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations'), dict(type='Resize', img_scale=(2560, 640), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=(640, 640), cat_max_ratio=0.75), dict(type='RandomFlip', prob=0.5), dict(type='PhotoMetricDistortion'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size=(640, 640), pad_val=0, seg_pad_val=255), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']) ]), val=dict( type='COCOStuffDataset', data_root='data/coco_stuff164k', img_dir='images/val2017', ann_dir='annotations/val2017', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(2560, 640), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='ResizeToMultiple', size_divisor=32), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='COCOStuffDataset', data_root='data/coco_stuff164k', img_dir='images/val2017', ann_dir='annotations/val2017', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(2560, 640), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='ResizeToMultiple', size_divisor=32), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) log_config = dict( interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] cudnn_benchmark = True optimizer = dict( type='AdamW', lr=2e-05, betas=(0.9, 0.999), weight_decay=0.05, constructor='LayerDecayOptimizerConstructor', paramwise_cfg=dict(num_layers=24, layer_decay_rate=0.9)) optimizer_config = dict() lr_config = dict( policy='poly', warmup='linear', warmup_iters=1500, warmup_ratio=1e-06, power=1.0, min_lr=0.0, by_epoch=False) runner = dict(type='IterBasedRunner', max_iters=80000) checkpoint_config = dict(by_epoch=False, interval=1000, max_keep_ckpts=2) evaluation = dict(interval=8000, metric='mIoU', pre_eval=True) work_dir = './work_dirs/upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4' gpu_ids = range(0, 8) auto_resume = False 2022-04-18 23:48:27,623 - mmseg - INFO - Set random seed to 1914568349, deterministic: False 2022-04-18 23:48:50,747 - mmseg - WARNING - The model and loaded state dict do not match exactly unexpected key in source state_dict: fc_norm.weight, fc_norm.bias, head.weight, head.bias missing keys in source state_dict: blocks.0.attn.relative_position_index, blocks.1.attn.relative_position_index, blocks.2.attn.relative_position_index, blocks.3.attn.relative_position_index, blocks.4.attn.relative_position_index, blocks.5.attn.relative_position_index, blocks.6.attn.relative_position_index, blocks.7.attn.relative_position_index, blocks.8.attn.relative_position_index, blocks.9.attn.relative_position_index, blocks.10.attn.relative_position_index, blocks.11.attn.relative_position_index, blocks.12.attn.relative_position_index, blocks.13.attn.relative_position_index, blocks.14.attn.relative_position_index, blocks.15.attn.relative_position_index, blocks.16.attn.relative_position_index, blocks.17.attn.relative_position_index, blocks.18.attn.relative_position_index, blocks.19.attn.relative_position_index, blocks.20.attn.relative_position_index, blocks.21.attn.relative_position_index, blocks.22.attn.relative_position_index, blocks.23.attn.relative_position_index 2022-04-18 23:48:52,520 - mmseg - INFO - initialize UPerHead with init_cfg {'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} 2022-04-18 23:48:53,017 - mmseg - INFO - initialize FCNHead with init_cfg {'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} Name of parameter - Initialization information backbone.cls_token - torch.Size([1, 1, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.level_embed - torch.Size([3, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.patch_embed.proj.weight - torch.Size([1024, 3, 16, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.patch_embed.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.gamma_1 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.gamma_2 - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.q_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.v_bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.relative_position_bias_table - torch.Size([6244, 16]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.qkv.weight - torch.Size([3072, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.proj.weight - torch.Size([1024, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc1.weight - torch.Size([4096, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc1.bias - torch.Size([4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc2.weight - torch.Size([1024, 4096]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.0.weight - torch.Size([64, 3, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.1.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.1.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.3.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.4.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.4.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.6.weight - torch.Size([64, 64, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.7.weight - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.stem.7.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv2.0.weight - torch.Size([128, 64, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv2.1.weight - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv2.1.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv3.0.weight - torch.Size([256, 128, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv3.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv3.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv4.0.weight - torch.Size([256, 256, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv4.1.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.conv4.1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc1.weight - torch.Size([1024, 64, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc2.weight - torch.Size([1024, 128, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc3.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc3.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc4.weight - torch.Size([1024, 256, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.conv_branch.fc4.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.attention_weights.weight - torch.Size([64, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.extract.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.gamma - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.sampling_offsets.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.attention_weights.weight - torch.Size([192, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.attention_weights.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.insert.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn.fc1.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn.fc1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn.dwconv.dwconv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn.fc2.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.0.ffn_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.attention_weights.weight - torch.Size([64, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.extract.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.gamma - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.sampling_offsets.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.attention_weights.weight - torch.Size([192, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.attention_weights.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.insert.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn.fc1.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn.fc1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn.dwconv.dwconv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn.fc2.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.1.ffn_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.attention_weights.weight - torch.Size([64, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.extract.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.gamma - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.sampling_offsets.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.attention_weights.weight - torch.Size([192, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.attention_weights.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.insert.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn.fc1.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn.fc1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn.dwconv.dwconv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn.fc2.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.2.ffn_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.attention_weights.weight - torch.Size([64, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.extract.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.gamma - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.sampling_offsets.weight - torch.Size([384, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.sampling_offsets.bias - torch.Size([384]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.attention_weights.weight - torch.Size([192, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.attention_weights.bias - torch.Size([192]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.insert.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn.fc1.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn.fc1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn.dwconv.dwconv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn.fc2.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.interact_blocks.3.ffn_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.attention_weights.weight - torch.Size([64, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.extract.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn.fc1.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn.fc1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn.dwconv.dwconv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn.fc2.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.0.ffn_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.query_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.query_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.feat_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.feat_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.sampling_offsets.weight - torch.Size([128, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.sampling_offsets.bias - torch.Size([128]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.attention_weights.weight - torch.Size([64, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.attention_weights.bias - torch.Size([64]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.value_proj.weight - torch.Size([512, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.value_proj.bias - torch.Size([512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.output_proj.weight - torch.Size([1024, 512]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.extract.attn.output_proj.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn.fc1.weight - torch.Size([256, 1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn.fc1.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn.dwconv.dwconv.weight - torch.Size([256, 1, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn.dwconv.dwconv.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn.fc2.weight - torch.Size([1024, 256]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn.fc2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn_norm.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.extract_blocks.1.ffn_norm.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.up.weight - torch.Size([1024, 1024, 2, 2]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.up.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm1.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm1.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm2.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm2.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm3.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm3.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm4.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.norm4.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.conv_seg.weight - torch.Size([171, 1024, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 decode_head.conv_seg.bias - torch.Size([171]): NormalInit: mean=0, std=0.01, bias=0 decode_head.psp_modules.0.1.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.0.1.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.0.1.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.1.1.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.1.1.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.1.1.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.2.1.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.2.1.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.2.1.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.3.1.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.3.1.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.psp_modules.3.1.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.bottleneck.conv.weight - torch.Size([1024, 5120, 3, 3]): Initialized by user-defined `init_weights` in ConvModule decode_head.bottleneck.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.bottleneck.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.0.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.0.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.0.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.1.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.1.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.1.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.2.conv.weight - torch.Size([1024, 1024, 1, 1]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.2.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.lateral_convs.2.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.0.conv.weight - torch.Size([1024, 1024, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.0.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.0.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.1.conv.weight - torch.Size([1024, 1024, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.1.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.1.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.2.conv.weight - torch.Size([1024, 1024, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.2.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_convs.2.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_bottleneck.conv.weight - torch.Size([1024, 4096, 3, 3]): Initialized by user-defined `init_weights` in ConvModule decode_head.fpn_bottleneck.bn.weight - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.fpn_bottleneck.bn.bias - torch.Size([1024]): The value is the same before and after calling `init_weights` of EncoderDecoder auxiliary_head.conv_seg.weight - torch.Size([171, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 auxiliary_head.conv_seg.bias - torch.Size([171]): NormalInit: mean=0, std=0.01, bias=0 auxiliary_head.convs.0.conv.weight - torch.Size([256, 1024, 3, 3]): The value is the same before and after calling `init_weights` of EncoderDecoder auxiliary_head.convs.0.bn.weight - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder auxiliary_head.convs.0.bn.bias - torch.Size([256]): The value is the same before and after calling `init_weights` of EncoderDecoder 2022-04-18 23:48:53,024 - mmseg - INFO - EncoderDecoder( (backbone): BEiTDenseAdaptor( (patch_embed): PatchEmbed( (proj): Conv2d(3, 1024, kernel_size=(16, 16), stride=(16, 16)) ) (pos_drop): Dropout(p=0.0, inplace=False) (blocks): ModuleList( (0): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): Identity() (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (1): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.013043479062616825) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (2): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.02608695812523365) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (3): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.03913043811917305) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (4): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.0521739162504673) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (5): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.06521739810705185) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (6): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.0782608762383461) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (7): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.09130435436964035) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (8): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.1043478325009346) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (9): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.11739131063222885) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (10): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.1304347962141037) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (11): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.14347827434539795) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (12): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.1565217524766922) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (13): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.16956523060798645) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (14): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.1826087087392807) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (15): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.19565218687057495) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (16): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.2086956650018692) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (17): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.22173914313316345) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (18): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.2347826212644577) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (19): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.24782609939575195) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (20): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.260869562625885) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (21): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.27391305565834045) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (22): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.2869565188884735) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) (23): Block( (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=1024, out_features=3072, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=1024, out_features=1024, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) ) (drop_path): DropPath(p=0.30000001192092896) (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=1024, out_features=4096, bias=True) (act): GELU() (fc2): Linear(in_features=4096, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) ) ) (conv_branch): ConvBranch( (stem): Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): SyncBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): SyncBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (5): ReLU(inplace=True) (6): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (7): SyncBatchNorm(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (8): ReLU(inplace=True) (9): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False) ) (conv2): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): SyncBatchNorm(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv3): Sequential( (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (conv4): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace=True) ) (fc1): Conv2d(64, 1024, kernel_size=(1, 1), stride=(1, 1)) (fc2): Conv2d(128, 1024, kernel_size=(1, 1), stride=(1, 1)) (fc3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1)) (fc4): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1)) ) (interact_blocks): Sequential( (0): InteractBlock( (extract): ExtractLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) (attention_weights): Linear(in_features=1024, out_features=64, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (insert): InsertLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) (attention_weights): Linear(in_features=1024, out_features=192, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (ffn): ConvFFN( (fc1): Linear(in_features=1024, out_features=256, bias=True) (dwconv): DWConv( (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) ) (act): GELU() (fc2): Linear(in_features=256, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (drop_path): DropPath() ) (1): InteractBlock( (extract): ExtractLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) (attention_weights): Linear(in_features=1024, out_features=64, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (insert): InsertLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) (attention_weights): Linear(in_features=1024, out_features=192, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (ffn): ConvFFN( (fc1): Linear(in_features=1024, out_features=256, bias=True) (dwconv): DWConv( (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) ) (act): GELU() (fc2): Linear(in_features=256, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (drop_path): DropPath() ) (2): InteractBlock( (extract): ExtractLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) (attention_weights): Linear(in_features=1024, out_features=64, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (insert): InsertLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) (attention_weights): Linear(in_features=1024, out_features=192, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (ffn): ConvFFN( (fc1): Linear(in_features=1024, out_features=256, bias=True) (dwconv): DWConv( (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) ) (act): GELU() (fc2): Linear(in_features=256, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (drop_path): DropPath() ) (3): InteractBlock( (extract): ExtractLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) (attention_weights): Linear(in_features=1024, out_features=64, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (insert): InsertLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=384, bias=True) (attention_weights): Linear(in_features=1024, out_features=192, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (ffn): ConvFFN( (fc1): Linear(in_features=1024, out_features=256, bias=True) (dwconv): DWConv( (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) ) (act): GELU() (fc2): Linear(in_features=256, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (drop_path): DropPath() ) ) (extract_blocks): Sequential( (0): ExtractBlock( (extract): ExtractLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) (attention_weights): Linear(in_features=1024, out_features=64, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (ffn): ConvFFN( (fc1): Linear(in_features=1024, out_features=256, bias=True) (dwconv): DWConv( (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) ) (act): GELU() (fc2): Linear(in_features=256, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (drop_path): Identity() ) (1): ExtractBlock( (extract): ExtractLayer( (query_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (feat_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (attn): MSDeformAttn( (sampling_offsets): Linear(in_features=1024, out_features=128, bias=True) (attention_weights): Linear(in_features=1024, out_features=64, bias=True) (value_proj): Linear(in_features=1024, out_features=512, bias=True) (output_proj): Linear(in_features=512, out_features=1024, bias=True) ) ) (ffn): ConvFFN( (fc1): Linear(in_features=1024, out_features=256, bias=True) (dwconv): DWConv( (dwconv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256) ) (act): GELU() (fc2): Linear(in_features=256, out_features=1024, bias=True) (drop): Dropout(p=0.0, inplace=False) ) (ffn_norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) (drop_path): Identity() ) ) (up): ConvTranspose2d(1024, 1024, kernel_size=(2, 2), stride=(2, 2)) (norm1): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (norm2): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (norm3): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (norm4): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) (decode_head): UPerHead( input_transform=multiple_select, ignore_index=255, align_corners=False (loss_decode): CrossEntropyLoss() (conv_seg): Conv2d(1024, 171, kernel_size=(1, 1), stride=(1, 1)) (dropout): Dropout2d(p=0.1, inplace=False) (psp_modules): PPM( (0): Sequential( (0): AdaptiveAvgPool2d(output_size=1) (1): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) ) (1): Sequential( (0): AdaptiveAvgPool2d(output_size=2) (1): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) ) (2): Sequential( (0): AdaptiveAvgPool2d(output_size=3) (1): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) ) (3): Sequential( (0): AdaptiveAvgPool2d(output_size=6) (1): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) ) ) (bottleneck): ConvModule( (conv): Conv2d(5120, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) (lateral_convs): ModuleList( (0): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU() ) (1): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU() ) (2): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU() ) ) (fpn_convs): ModuleList( (0): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU() ) (1): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU() ) (2): ConvModule( (conv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU() ) ) (fpn_bottleneck): ConvModule( (conv): Conv2d(4096, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): SyncBatchNorm(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) ) init_cfg={'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} (auxiliary_head): FCNHead( input_transform=None, ignore_index=255, align_corners=False (loss_decode): CrossEntropyLoss() (conv_seg): Conv2d(256, 171, kernel_size=(1, 1), stride=(1, 1)) (dropout): Dropout2d(p=0.1, inplace=False) (convs): Sequential( (0): ConvModule( (conv): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn): SyncBatchNorm(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (activate): ReLU(inplace=True) ) ) ) init_cfg={'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} ) 2022-04-18 23:48:55,226 - mmseg - INFO - Loaded 118287 images 2022-04-18 23:48:56,511 - mmseg - INFO - Loaded 5000 images 2022-04-18 23:48:56,512 - mmseg - INFO - Start running, host: chenzhe.vendor@SH-IDC1-10-140-1-130, work_dir: /mnt/lustre/chenzhe.vendor/workspace/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4 2022-04-18 23:48:56,512 - mmseg - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) PolyLrUpdaterHook (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) PolyLrUpdaterHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_train_iter: (VERY_HIGH ) PolyLrUpdaterHook (LOW ) IterTimerHook (LOW ) DistEvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (NORMAL ) CheckpointHook (LOW ) IterTimerHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- after_train_epoch: (NORMAL ) CheckpointHook (LOW ) DistEvalHook (VERY_LOW ) TextLoggerHook -------------------- before_val_epoch: (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (VERY_LOW ) TextLoggerHook -------------------- after_run: (VERY_LOW ) TextLoggerHook -------------------- 2022-04-18 23:48:56,512 - mmseg - INFO - workflow: [('train', 1)], max: 80000 iters 2022-04-18 23:48:56,512 - mmseg - INFO - Checkpoints will be saved to /mnt/lustre/chenzhe.vendor/workspace/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4 by HardDiskBackend. 2022-04-18 23:51:20,496 - mmseg - INFO - Iter [50/80000] lr: 4.688e-08, eta: 1 day, 21:50:21, time: 2.064, data_time: 0.009, memory: 73037, decode.loss_ce: 4.4214, decode.acc_seg: 0.3252, aux.loss_ce: 1.7565, aux.acc_seg: 0.4596, loss: 6.1779 2022-04-18 23:52:07,652 - mmseg - INFO - Iter [100/80000] lr: 9.465e-08, eta: 1 day, 9:22:05, time: 0.943, data_time: 0.005, memory: 73037, decode.loss_ce: 4.3960, decode.acc_seg: 0.7162, aux.loss_ce: 1.7596, aux.acc_seg: 0.3966, loss: 6.1556 2022-04-18 23:52:54,932 - mmseg - INFO - Iter [150/80000] lr: 1.424e-07, eta: 1 day, 5:13:32, time: 0.946, data_time: 0.006, memory: 73037, decode.loss_ce: 4.3327, decode.acc_seg: 2.5601, aux.loss_ce: 1.7543, aux.acc_seg: 0.4664, loss: 6.0869 2022-04-18 23:53:41,885 - mmseg - INFO - Iter [200/80000] lr: 1.900e-07, eta: 1 day, 3:06:32, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 4.2525, decode.acc_seg: 5.8576, aux.loss_ce: 1.7428, aux.acc_seg: 0.6503, loss: 5.9953 2022-04-18 23:54:29,300 - mmseg - INFO - Iter [250/80000] lr: 2.376e-07, eta: 1 day, 1:52:31, time: 0.948, data_time: 0.005, memory: 73037, decode.loss_ce: 4.1686, decode.acc_seg: 9.7644, aux.loss_ce: 1.7366, aux.acc_seg: 0.6460, loss: 5.9052 2022-04-18 23:55:16,317 - mmseg - INFO - Iter [300/80000] lr: 2.851e-07, eta: 1 day, 1:01:06, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 4.0990, decode.acc_seg: 13.6518, aux.loss_ce: 1.7473, aux.acc_seg: 1.2569, loss: 5.8463 2022-04-18 23:56:03,344 - mmseg - INFO - Iter [350/80000] lr: 3.326e-07, eta: 1 day, 0:24:14, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 3.9152, decode.acc_seg: 16.6536, aux.loss_ce: 1.7188, aux.acc_seg: 2.4385, loss: 5.6340 2022-04-18 23:56:50,193 - mmseg - INFO - Iter [400/80000] lr: 3.800e-07, eta: 23:55:47, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 3.8030, decode.acc_seg: 18.5755, aux.loss_ce: 1.7320, aux.acc_seg: 4.4092, loss: 5.5351 2022-04-18 23:57:37,030 - mmseg - INFO - Iter [450/80000] lr: 4.274e-07, eta: 23:33:27, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 3.6142, decode.acc_seg: 19.7928, aux.loss_ce: 1.6984, aux.acc_seg: 6.6143, loss: 5.3126 2022-04-18 23:58:23,783 - mmseg - INFO - Iter [500/80000] lr: 4.747e-07, eta: 23:15:12, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 3.4737, decode.acc_seg: 21.4406, aux.loss_ce: 1.6910, aux.acc_seg: 9.5811, loss: 5.1646 2022-04-18 23:59:10,450 - mmseg - INFO - Iter [550/80000] lr: 5.219e-07, eta: 22:59:55, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 3.3323, decode.acc_seg: 22.3092, aux.loss_ce: 1.6556, aux.acc_seg: 12.7909, loss: 4.9879 2022-04-18 23:59:56,893 - mmseg - INFO - Iter [600/80000] lr: 5.691e-07, eta: 22:46:26, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 3.2882, decode.acc_seg: 23.6250, aux.loss_ce: 1.6777, aux.acc_seg: 15.5323, loss: 4.9659 2022-04-19 00:00:45,086 - mmseg - INFO - Iter [650/80000] lr: 6.162e-07, eta: 22:38:41, time: 0.965, data_time: 0.007, memory: 73037, decode.loss_ce: 3.1778, decode.acc_seg: 23.8273, aux.loss_ce: 1.6538, aux.acc_seg: 17.4911, loss: 4.8316 2022-04-19 00:01:31,819 - mmseg - INFO - Iter [700/80000] lr: 6.632e-07, eta: 22:29:05, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 3.1494, decode.acc_seg: 24.1818, aux.loss_ce: 1.6522, aux.acc_seg: 17.9764, loss: 4.8016 2022-04-19 00:02:19,390 - mmseg - INFO - Iter [750/80000] lr: 7.102e-07, eta: 22:21:47, time: 0.948, data_time: 0.005, memory: 73037, decode.loss_ce: 3.0221, decode.acc_seg: 26.5494, aux.loss_ce: 1.6314, aux.acc_seg: 20.8848, loss: 4.6536 2022-04-19 00:03:06,887 - mmseg - INFO - Iter [800/80000] lr: 7.572e-07, eta: 22:15:49, time: 0.954, data_time: 0.009, memory: 73037, decode.loss_ce: 3.0226, decode.acc_seg: 25.5410, aux.loss_ce: 1.6112, aux.acc_seg: 20.0907, loss: 4.6338 2022-04-19 00:03:53,870 - mmseg - INFO - Iter [850/80000] lr: 8.040e-07, eta: 22:09:22, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 2.8466, decode.acc_seg: 28.4069, aux.loss_ce: 1.5798, aux.acc_seg: 22.0222, loss: 4.4264 2022-04-19 00:04:40,501 - mmseg - INFO - Iter [900/80000] lr: 8.509e-07, eta: 22:03:01, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 2.7918, decode.acc_seg: 27.8333, aux.loss_ce: 1.5506, aux.acc_seg: 21.7117, loss: 4.3424 2022-04-19 00:05:27,451 - mmseg - INFO - Iter [950/80000] lr: 8.976e-07, eta: 21:57:42, time: 0.939, data_time: 0.005, memory: 73037, decode.loss_ce: 2.7405, decode.acc_seg: 28.7171, aux.loss_ce: 1.5363, aux.acc_seg: 22.0277, loss: 4.2768 2022-04-19 00:06:14,721 - mmseg - INFO - Saving checkpoint at 1000 iterations 2022-04-19 00:06:34,059 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 00:06:34,119 - mmseg - INFO - Iter [1000/80000] lr: 9.443e-07, eta: 22:18:17, time: 1.325, data_time: 0.006, memory: 73037, decode.loss_ce: 2.7210, decode.acc_seg: 29.3568, aux.loss_ce: 1.5078, aux.acc_seg: 23.2804, loss: 4.2288 2022-04-19 00:07:21,765 - mmseg - INFO - Iter [1050/80000] lr: 9.909e-07, eta: 22:13:57, time: 0.961, data_time: 0.014, memory: 73037, decode.loss_ce: 2.6256, decode.acc_seg: 31.1976, aux.loss_ce: 1.4979, aux.acc_seg: 23.5811, loss: 4.1235 2022-04-19 00:08:08,645 - mmseg - INFO - Iter [1100/80000] lr: 1.038e-06, eta: 22:08:32, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 2.5573, decode.acc_seg: 31.3277, aux.loss_ce: 1.4581, aux.acc_seg: 24.5158, loss: 4.0154 2022-04-19 00:08:55,725 - mmseg - INFO - Iter [1150/80000] lr: 1.084e-06, eta: 22:03:47, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 2.4524, decode.acc_seg: 34.1894, aux.loss_ce: 1.4230, aux.acc_seg: 26.6814, loss: 3.8754 2022-04-19 00:09:42,906 - mmseg - INFO - Iter [1200/80000] lr: 1.130e-06, eta: 21:59:27, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 2.4536, decode.acc_seg: 33.5426, aux.loss_ce: 1.4141, aux.acc_seg: 25.2853, loss: 3.8677 2022-04-19 00:10:29,830 - mmseg - INFO - Iter [1250/80000] lr: 1.177e-06, eta: 21:55:09, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 2.3642, decode.acc_seg: 34.7041, aux.loss_ce: 1.3809, aux.acc_seg: 26.1971, loss: 3.7451 2022-04-19 00:11:16,579 - mmseg - INFO - Iter [1300/80000] lr: 1.223e-06, eta: 21:50:56, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 2.2025, decode.acc_seg: 38.5063, aux.loss_ce: 1.3506, aux.acc_seg: 28.1396, loss: 3.5531 2022-04-19 00:12:03,690 - mmseg - INFO - Iter [1350/80000] lr: 1.269e-06, eta: 21:47:18, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 2.2567, decode.acc_seg: 38.4583, aux.loss_ce: 1.3521, aux.acc_seg: 29.6904, loss: 3.6088 2022-04-19 00:12:50,644 - mmseg - INFO - Iter [1400/80000] lr: 1.316e-06, eta: 21:43:46, time: 0.939, data_time: 0.007, memory: 73037, decode.loss_ce: 2.1585, decode.acc_seg: 37.1691, aux.loss_ce: 1.3003, aux.acc_seg: 27.4748, loss: 3.4588 2022-04-19 00:13:37,530 - mmseg - INFO - Iter [1450/80000] lr: 1.362e-06, eta: 21:40:20, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 2.0933, decode.acc_seg: 40.0902, aux.loss_ce: 1.2931, aux.acc_seg: 29.4212, loss: 3.3864 2022-04-19 00:14:24,631 - mmseg - INFO - Iter [1500/80000] lr: 1.408e-06, eta: 21:37:16, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 2.1431, decode.acc_seg: 36.5194, aux.loss_ce: 1.2862, aux.acc_seg: 25.4362, loss: 3.4292 2022-04-19 00:15:11,922 - mmseg - INFO - Iter [1550/80000] lr: 1.408e-06, eta: 21:34:30, time: 0.945, data_time: 0.005, memory: 73037, decode.loss_ce: 1.9806, decode.acc_seg: 41.1002, aux.loss_ce: 1.2393, aux.acc_seg: 29.5204, loss: 3.2199 2022-04-19 00:15:58,958 - mmseg - INFO - Iter [1600/80000] lr: 1.407e-06, eta: 21:31:41, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 1.9662, decode.acc_seg: 40.9366, aux.loss_ce: 1.2308, aux.acc_seg: 29.8659, loss: 3.1971 2022-04-19 00:16:45,930 - mmseg - INFO - Iter [1650/80000] lr: 1.406e-06, eta: 21:28:54, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 1.8958, decode.acc_seg: 42.9587, aux.loss_ce: 1.2129, aux.acc_seg: 31.1114, loss: 3.1087 2022-04-19 00:17:32,841 - mmseg - INFO - Iter [1700/80000] lr: 1.405e-06, eta: 21:26:12, time: 0.938, data_time: 0.007, memory: 73037, decode.loss_ce: 1.8199, decode.acc_seg: 44.2188, aux.loss_ce: 1.1786, aux.acc_seg: 31.8667, loss: 2.9985 2022-04-19 00:18:19,645 - mmseg - INFO - Iter [1750/80000] lr: 1.404e-06, eta: 21:23:33, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 1.8246, decode.acc_seg: 43.4342, aux.loss_ce: 1.1734, aux.acc_seg: 30.9376, loss: 2.9981 2022-04-19 00:19:06,743 - mmseg - INFO - Iter [1800/80000] lr: 1.404e-06, eta: 21:21:12, time: 0.942, data_time: 0.007, memory: 73037, decode.loss_ce: 1.7904, decode.acc_seg: 44.0846, aux.loss_ce: 1.1676, aux.acc_seg: 29.6937, loss: 2.9580 2022-04-19 00:19:53,455 - mmseg - INFO - Iter [1850/80000] lr: 1.403e-06, eta: 21:18:39, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 1.7775, decode.acc_seg: 44.2583, aux.loss_ce: 1.1530, aux.acc_seg: 29.9338, loss: 2.9305 2022-04-19 00:20:40,569 - mmseg - INFO - Iter [1900/80000] lr: 1.402e-06, eta: 21:16:29, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 1.6701, decode.acc_seg: 47.1559, aux.loss_ce: 1.1201, aux.acc_seg: 33.1228, loss: 2.7902 2022-04-19 00:21:27,428 - mmseg - INFO - Iter [1950/80000] lr: 1.401e-06, eta: 21:14:13, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 1.7084, decode.acc_seg: 46.2773, aux.loss_ce: 1.1489, aux.acc_seg: 30.1088, loss: 2.8573 2022-04-19 00:22:14,563 - mmseg - INFO - Saving checkpoint at 2000 iterations 2022-04-19 00:22:27,078 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 00:22:27,083 - mmseg - INFO - Iter [2000/80000] lr: 1.400e-06, eta: 21:20:19, time: 1.192, data_time: 0.006, memory: 73037, decode.loss_ce: 1.6595, decode.acc_seg: 47.8006, aux.loss_ce: 1.1220, aux.acc_seg: 32.0932, loss: 2.7815 2022-04-19 00:23:14,249 - mmseg - INFO - Iter [2050/80000] lr: 1.399e-06, eta: 21:18:13, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 1.6012, decode.acc_seg: 49.0358, aux.loss_ce: 1.0966, aux.acc_seg: 32.9361, loss: 2.6978 2022-04-19 00:24:01,396 - mmseg - INFO - Iter [2100/80000] lr: 1.398e-06, eta: 21:16:07, time: 0.943, data_time: 0.005, memory: 73037, decode.loss_ce: 1.5418, decode.acc_seg: 47.9321, aux.loss_ce: 1.0490, aux.acc_seg: 33.3262, loss: 2.5908 2022-04-19 00:24:48,253 - mmseg - INFO - Iter [2150/80000] lr: 1.397e-06, eta: 21:13:55, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 1.5074, decode.acc_seg: 48.7935, aux.loss_ce: 1.0672, aux.acc_seg: 31.5216, loss: 2.5746 2022-04-19 00:25:35,129 - mmseg - INFO - Iter [2200/80000] lr: 1.396e-06, eta: 21:11:47, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 1.4870, decode.acc_seg: 50.2087, aux.loss_ce: 1.0400, aux.acc_seg: 35.0851, loss: 2.5270 2022-04-19 00:26:21,893 - mmseg - INFO - Iter [2250/80000] lr: 1.395e-06, eta: 21:09:40, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 1.5261, decode.acc_seg: 48.2178, aux.loss_ce: 1.0450, aux.acc_seg: 31.4608, loss: 2.5711 2022-04-19 00:27:08,651 - mmseg - INFO - Iter [2300/80000] lr: 1.395e-06, eta: 21:07:36, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 1.4199, decode.acc_seg: 52.5007, aux.loss_ce: 1.0256, aux.acc_seg: 35.0567, loss: 2.4456 2022-04-19 00:27:55,569 - mmseg - INFO - Iter [2350/80000] lr: 1.394e-06, eta: 21:05:40, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 1.4927, decode.acc_seg: 49.3114, aux.loss_ce: 1.0418, aux.acc_seg: 33.8630, loss: 2.5346 2022-04-19 00:28:42,764 - mmseg - INFO - Iter [2400/80000] lr: 1.393e-06, eta: 21:03:56, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 1.4557, decode.acc_seg: 51.9982, aux.loss_ce: 1.0263, aux.acc_seg: 36.1751, loss: 2.4820 2022-04-19 00:29:29,733 - mmseg - INFO - Iter [2450/80000] lr: 1.392e-06, eta: 21:02:07, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 1.3756, decode.acc_seg: 51.8223, aux.loss_ce: 0.9869, aux.acc_seg: 35.7816, loss: 2.3624 2022-04-19 00:30:16,515 - mmseg - INFO - Iter [2500/80000] lr: 1.391e-06, eta: 21:00:15, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 1.3713, decode.acc_seg: 49.8838, aux.loss_ce: 0.9717, aux.acc_seg: 33.7673, loss: 2.3430 2022-04-19 00:31:03,530 - mmseg - INFO - Iter [2550/80000] lr: 1.390e-06, eta: 20:58:32, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 1.4141, decode.acc_seg: 52.1116, aux.loss_ce: 1.0171, aux.acc_seg: 33.9892, loss: 2.4312 2022-04-19 00:31:51,054 - mmseg - INFO - Iter [2600/80000] lr: 1.389e-06, eta: 20:57:07, time: 0.951, data_time: 0.007, memory: 73037, decode.loss_ce: 1.3326, decode.acc_seg: 53.2699, aux.loss_ce: 0.9693, aux.acc_seg: 35.6359, loss: 2.3019 2022-04-19 00:32:37,842 - mmseg - INFO - Iter [2650/80000] lr: 1.388e-06, eta: 20:55:22, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 1.2769, decode.acc_seg: 54.3657, aux.loss_ce: 0.9473, aux.acc_seg: 36.6019, loss: 2.2242 2022-04-19 00:33:24,873 - mmseg - INFO - Iter [2700/80000] lr: 1.387e-06, eta: 20:53:45, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 1.3153, decode.acc_seg: 54.1041, aux.loss_ce: 0.9445, aux.acc_seg: 38.0847, loss: 2.2598 2022-04-19 00:34:11,828 - mmseg - INFO - Iter [2750/80000] lr: 1.386e-06, eta: 20:52:09, time: 0.939, data_time: 0.005, memory: 73037, decode.loss_ce: 1.3067, decode.acc_seg: 53.5802, aux.loss_ce: 0.9376, aux.acc_seg: 37.7554, loss: 2.2443 2022-04-19 00:34:58,614 - mmseg - INFO - Iter [2800/80000] lr: 1.386e-06, eta: 20:50:30, time: 0.936, data_time: 0.008, memory: 73037, decode.loss_ce: 1.2909, decode.acc_seg: 53.1584, aux.loss_ce: 0.9374, aux.acc_seg: 37.3929, loss: 2.2283 2022-04-19 00:35:45,315 - mmseg - INFO - Iter [2850/80000] lr: 1.385e-06, eta: 20:48:50, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 1.2261, decode.acc_seg: 55.2583, aux.loss_ce: 0.8939, aux.acc_seg: 38.4495, loss: 2.1201 2022-04-19 00:36:32,234 - mmseg - INFO - Iter [2900/80000] lr: 1.384e-06, eta: 20:47:18, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 1.2535, decode.acc_seg: 54.0636, aux.loss_ce: 0.9048, aux.acc_seg: 39.0850, loss: 2.1583 2022-04-19 00:37:18,908 - mmseg - INFO - Iter [2950/80000] lr: 1.383e-06, eta: 20:45:40, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 1.2796, decode.acc_seg: 53.2290, aux.loss_ce: 0.9177, aux.acc_seg: 36.3707, loss: 2.1973 2022-04-19 00:38:06,195 - mmseg - INFO - Saving checkpoint at 3000 iterations 2022-04-19 00:38:19,407 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 00:38:19,408 - mmseg - INFO - Iter [3000/80000] lr: 1.382e-06, eta: 20:49:59, time: 1.210, data_time: 0.006, memory: 73037, decode.loss_ce: 1.2173, decode.acc_seg: 54.6787, aux.loss_ce: 0.8949, aux.acc_seg: 38.0447, loss: 2.1123 2022-04-19 00:39:06,828 - mmseg - INFO - Iter [3050/80000] lr: 1.381e-06, eta: 20:48:39, time: 0.949, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1626, decode.acc_seg: 56.7664, aux.loss_ce: 0.8779, aux.acc_seg: 40.3036, loss: 2.0405 2022-04-19 00:39:53,712 - mmseg - INFO - Iter [3100/80000] lr: 1.380e-06, eta: 20:47:06, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 1.2074, decode.acc_seg: 55.1526, aux.loss_ce: 0.8868, aux.acc_seg: 38.3278, loss: 2.0943 2022-04-19 00:40:40,639 - mmseg - INFO - Iter [3150/80000] lr: 1.379e-06, eta: 20:45:35, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 1.2502, decode.acc_seg: 54.9087, aux.loss_ce: 0.9024, aux.acc_seg: 38.7455, loss: 2.1526 2022-04-19 00:41:27,276 - mmseg - INFO - Iter [3200/80000] lr: 1.378e-06, eta: 20:43:59, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1861, decode.acc_seg: 56.5891, aux.loss_ce: 0.8612, aux.acc_seg: 41.3798, loss: 2.0473 2022-04-19 00:42:14,091 - mmseg - INFO - Iter [3250/80000] lr: 1.377e-06, eta: 20:42:28, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1483, decode.acc_seg: 55.0972, aux.loss_ce: 0.8461, aux.acc_seg: 39.0918, loss: 1.9944 2022-04-19 00:43:00,862 - mmseg - INFO - Iter [3300/80000] lr: 1.377e-06, eta: 20:40:58, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1718, decode.acc_seg: 55.9755, aux.loss_ce: 0.8554, aux.acc_seg: 39.8239, loss: 2.0272 2022-04-19 00:43:47,999 - mmseg - INFO - Iter [3350/80000] lr: 1.376e-06, eta: 20:39:37, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1545, decode.acc_seg: 55.8254, aux.loss_ce: 0.8331, aux.acc_seg: 40.6257, loss: 1.9876 2022-04-19 00:44:35,257 - mmseg - INFO - Iter [3400/80000] lr: 1.375e-06, eta: 20:38:20, time: 0.945, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1310, decode.acc_seg: 55.4634, aux.loss_ce: 0.8273, aux.acc_seg: 39.4298, loss: 1.9583 2022-04-19 00:45:22,472 - mmseg - INFO - Iter [3450/80000] lr: 1.374e-06, eta: 20:37:03, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1475, decode.acc_seg: 56.5757, aux.loss_ce: 0.8266, aux.acc_seg: 42.0935, loss: 1.9742 2022-04-19 00:46:09,901 - mmseg - INFO - Iter [3500/80000] lr: 1.373e-06, eta: 20:35:52, time: 0.949, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1064, decode.acc_seg: 55.2599, aux.loss_ce: 0.7919, aux.acc_seg: 41.8506, loss: 1.8984 2022-04-19 00:46:56,894 - mmseg - INFO - Iter [3550/80000] lr: 1.372e-06, eta: 20:34:31, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1108, decode.acc_seg: 57.0281, aux.loss_ce: 0.7919, aux.acc_seg: 42.4925, loss: 1.9027 2022-04-19 00:47:43,920 - mmseg - INFO - Iter [3600/80000] lr: 1.371e-06, eta: 20:33:13, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1077, decode.acc_seg: 57.2035, aux.loss_ce: 0.7992, aux.acc_seg: 42.4608, loss: 1.9069 2022-04-19 00:48:31,420 - mmseg - INFO - Iter [3650/80000] lr: 1.370e-06, eta: 20:32:05, time: 0.950, data_time: 0.007, memory: 73037, decode.loss_ce: 1.1227, decode.acc_seg: 57.4922, aux.loss_ce: 0.8184, aux.acc_seg: 41.4673, loss: 1.9411 2022-04-19 00:49:18,360 - mmseg - INFO - Iter [3700/80000] lr: 1.369e-06, eta: 20:30:46, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1583, decode.acc_seg: 55.8352, aux.loss_ce: 0.8110, aux.acc_seg: 41.8122, loss: 1.9693 2022-04-19 00:50:05,364 - mmseg - INFO - Iter [3750/80000] lr: 1.369e-06, eta: 20:29:30, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1487, decode.acc_seg: 56.7586, aux.loss_ce: 0.8101, aux.acc_seg: 42.3652, loss: 1.9588 2022-04-19 00:50:52,297 - mmseg - INFO - Iter [3800/80000] lr: 1.368e-06, eta: 20:28:11, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0920, decode.acc_seg: 57.3144, aux.loss_ce: 0.7724, aux.acc_seg: 43.6599, loss: 1.8644 2022-04-19 00:51:39,109 - mmseg - INFO - Iter [3850/80000] lr: 1.367e-06, eta: 20:26:54, time: 0.937, data_time: 0.007, memory: 73037, decode.loss_ce: 1.0531, decode.acc_seg: 57.2720, aux.loss_ce: 0.7604, aux.acc_seg: 43.1858, loss: 1.8135 2022-04-19 00:52:25,899 - mmseg - INFO - Iter [3900/80000] lr: 1.366e-06, eta: 20:25:35, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0600, decode.acc_seg: 57.0927, aux.loss_ce: 0.7520, aux.acc_seg: 43.6611, loss: 1.8120 2022-04-19 00:53:12,886 - mmseg - INFO - Iter [3950/80000] lr: 1.365e-06, eta: 20:24:21, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0788, decode.acc_seg: 57.2420, aux.loss_ce: 0.7457, aux.acc_seg: 44.8198, loss: 1.8245 2022-04-19 00:53:59,713 - mmseg - INFO - Saving checkpoint at 4000 iterations 2022-04-19 00:54:12,466 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 00:54:12,466 - mmseg - INFO - Iter [4000/80000] lr: 1.364e-06, eta: 20:27:07, time: 1.192, data_time: 0.007, memory: 73037, decode.loss_ce: 1.0605, decode.acc_seg: 56.5081, aux.loss_ce: 0.7407, aux.acc_seg: 45.0724, loss: 1.8012 2022-04-19 00:54:59,380 - mmseg - INFO - Iter [4050/80000] lr: 1.363e-06, eta: 20:25:50, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0528, decode.acc_seg: 57.9449, aux.loss_ce: 0.7555, aux.acc_seg: 45.7679, loss: 1.8083 2022-04-19 00:55:46,219 - mmseg - INFO - Iter [4100/80000] lr: 1.362e-06, eta: 20:24:32, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0332, decode.acc_seg: 56.3614, aux.loss_ce: 0.7188, aux.acc_seg: 44.5540, loss: 1.7520 2022-04-19 00:56:32,811 - mmseg - INFO - Iter [4150/80000] lr: 1.361e-06, eta: 20:23:11, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0325, decode.acc_seg: 58.1989, aux.loss_ce: 0.7132, aux.acc_seg: 47.4589, loss: 1.7457 2022-04-19 00:57:19,980 - mmseg - INFO - Iter [4200/80000] lr: 1.360e-06, eta: 20:22:00, time: 0.942, data_time: 0.005, memory: 73037, decode.loss_ce: 1.1002, decode.acc_seg: 56.8253, aux.loss_ce: 0.7500, aux.acc_seg: 45.4080, loss: 1.8503 2022-04-19 00:58:06,936 - mmseg - INFO - Iter [4250/80000] lr: 1.360e-06, eta: 20:20:47, time: 0.940, data_time: 0.007, memory: 73037, decode.loss_ce: 1.0791, decode.acc_seg: 56.2508, aux.loss_ce: 0.7385, aux.acc_seg: 45.2661, loss: 1.8176 2022-04-19 00:58:53,704 - mmseg - INFO - Iter [4300/80000] lr: 1.359e-06, eta: 20:19:31, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0589, decode.acc_seg: 56.9056, aux.loss_ce: 0.7284, aux.acc_seg: 45.2213, loss: 1.7872 2022-04-19 00:59:40,741 - mmseg - INFO - Iter [4350/80000] lr: 1.358e-06, eta: 20:18:20, time: 0.941, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0204, decode.acc_seg: 57.6806, aux.loss_ce: 0.6984, aux.acc_seg: 47.0516, loss: 1.7188 2022-04-19 01:00:27,817 - mmseg - INFO - Iter [4400/80000] lr: 1.357e-06, eta: 20:17:11, time: 0.941, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9463, decode.acc_seg: 58.3525, aux.loss_ce: 0.6849, aux.acc_seg: 46.6977, loss: 1.6312 2022-04-19 01:01:15,062 - mmseg - INFO - Iter [4450/80000] lr: 1.356e-06, eta: 20:16:04, time: 0.945, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0590, decode.acc_seg: 58.4126, aux.loss_ce: 0.7251, aux.acc_seg: 46.7132, loss: 1.7840 2022-04-19 01:02:01,999 - mmseg - INFO - Iter [4500/80000] lr: 1.355e-06, eta: 20:14:53, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 1.1010, decode.acc_seg: 57.3533, aux.loss_ce: 0.7224, aux.acc_seg: 47.5210, loss: 1.8234 2022-04-19 01:02:48,890 - mmseg - INFO - Iter [4550/80000] lr: 1.354e-06, eta: 20:13:42, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9708, decode.acc_seg: 57.5185, aux.loss_ce: 0.6655, aux.acc_seg: 46.7746, loss: 1.6363 2022-04-19 01:03:36,354 - mmseg - INFO - Iter [4600/80000] lr: 1.353e-06, eta: 20:12:41, time: 0.950, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0476, decode.acc_seg: 56.6585, aux.loss_ce: 0.6937, aux.acc_seg: 46.5194, loss: 1.7412 2022-04-19 01:04:23,183 - mmseg - INFO - Iter [4650/80000] lr: 1.352e-06, eta: 20:11:30, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0183, decode.acc_seg: 58.0026, aux.loss_ce: 0.6888, aux.acc_seg: 48.1053, loss: 1.7072 2022-04-19 01:05:09,792 - mmseg - INFO - Iter [4700/80000] lr: 1.351e-06, eta: 20:10:15, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0291, decode.acc_seg: 57.7589, aux.loss_ce: 0.6876, aux.acc_seg: 47.1019, loss: 1.7167 2022-04-19 01:05:56,809 - mmseg - INFO - Iter [4750/80000] lr: 1.351e-06, eta: 20:09:08, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0165, decode.acc_seg: 57.1951, aux.loss_ce: 0.6774, aux.acc_seg: 46.6957, loss: 1.6939 2022-04-19 01:06:43,521 - mmseg - INFO - Iter [4800/80000] lr: 1.350e-06, eta: 20:07:56, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9629, decode.acc_seg: 57.2160, aux.loss_ce: 0.6486, aux.acc_seg: 48.6897, loss: 1.6116 2022-04-19 01:07:30,549 - mmseg - INFO - Iter [4850/80000] lr: 1.349e-06, eta: 20:06:50, time: 0.942, data_time: 0.007, memory: 73037, decode.loss_ce: 0.9799, decode.acc_seg: 58.7945, aux.loss_ce: 0.6707, aux.acc_seg: 47.7713, loss: 1.6506 2022-04-19 01:08:17,474 - mmseg - INFO - Iter [4900/80000] lr: 1.348e-06, eta: 20:05:43, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9689, decode.acc_seg: 61.1218, aux.loss_ce: 0.6452, aux.acc_seg: 51.9007, loss: 1.6141 2022-04-19 01:09:04,597 - mmseg - INFO - Iter [4950/80000] lr: 1.347e-06, eta: 20:04:39, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9667, decode.acc_seg: 57.5392, aux.loss_ce: 0.6228, aux.acc_seg: 49.4244, loss: 1.5895 2022-04-19 01:09:51,700 - mmseg - INFO - Saving checkpoint at 5000 iterations 2022-04-19 01:10:04,098 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 01:10:04,137 - mmseg - INFO - Iter [5000/80000] lr: 1.346e-06, eta: 20:06:41, time: 1.190, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0009, decode.acc_seg: 59.5394, aux.loss_ce: 0.6617, aux.acc_seg: 48.5260, loss: 1.6626 2022-04-19 01:10:51,265 - mmseg - INFO - Iter [5050/80000] lr: 1.345e-06, eta: 20:05:36, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9688, decode.acc_seg: 57.9023, aux.loss_ce: 0.6387, aux.acc_seg: 49.0877, loss: 1.6075 2022-04-19 01:11:38,368 - mmseg - INFO - Iter [5100/80000] lr: 1.344e-06, eta: 20:04:31, time: 0.942, data_time: 0.009, memory: 73037, decode.loss_ce: 1.0365, decode.acc_seg: 55.9930, aux.loss_ce: 0.6649, aux.acc_seg: 47.2609, loss: 1.7014 2022-04-19 01:12:25,126 - mmseg - INFO - Iter [5150/80000] lr: 1.343e-06, eta: 20:03:21, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 1.0095, decode.acc_seg: 57.4923, aux.loss_ce: 0.6549, aux.acc_seg: 49.1490, loss: 1.6644 2022-04-19 01:13:11,901 - mmseg - INFO - Iter [5200/80000] lr: 1.342e-06, eta: 20:02:12, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9837, decode.acc_seg: 57.6360, aux.loss_ce: 0.6340, aux.acc_seg: 48.8599, loss: 1.6178 2022-04-19 01:13:58,523 - mmseg - INFO - Iter [5250/80000] lr: 1.342e-06, eta: 20:01:00, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9780, decode.acc_seg: 59.0994, aux.loss_ce: 0.6398, aux.acc_seg: 50.2184, loss: 1.6178 2022-04-19 01:14:45,165 - mmseg - INFO - Iter [5300/80000] lr: 1.341e-06, eta: 19:59:51, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0328, decode.acc_seg: 57.4189, aux.loss_ce: 0.6501, aux.acc_seg: 48.2246, loss: 1.6829 2022-04-19 01:15:31,936 - mmseg - INFO - Iter [5350/80000] lr: 1.340e-06, eta: 19:58:43, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9836, decode.acc_seg: 59.1843, aux.loss_ce: 0.6274, aux.acc_seg: 50.4331, loss: 1.6109 2022-04-19 01:16:18,796 - mmseg - INFO - Iter [5400/80000] lr: 1.339e-06, eta: 19:57:37, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9820, decode.acc_seg: 57.5439, aux.loss_ce: 0.6301, aux.acc_seg: 50.0682, loss: 1.6121 2022-04-19 01:17:05,760 - mmseg - INFO - Iter [5450/80000] lr: 1.338e-06, eta: 19:56:32, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9734, decode.acc_seg: 57.9641, aux.loss_ce: 0.6181, aux.acc_seg: 49.9579, loss: 1.5916 2022-04-19 01:17:52,857 - mmseg - INFO - Iter [5500/80000] lr: 1.337e-06, eta: 19:55:30, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9587, decode.acc_seg: 59.8352, aux.loss_ce: 0.6057, aux.acc_seg: 52.0278, loss: 1.5644 2022-04-19 01:18:39,832 - mmseg - INFO - Iter [5550/80000] lr: 1.336e-06, eta: 19:54:26, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9964, decode.acc_seg: 57.8386, aux.loss_ce: 0.6187, aux.acc_seg: 49.7678, loss: 1.6151 2022-04-19 01:19:27,085 - mmseg - INFO - Iter [5600/80000] lr: 1.335e-06, eta: 19:53:26, time: 0.945, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9014, decode.acc_seg: 59.5163, aux.loss_ce: 0.5911, aux.acc_seg: 50.8491, loss: 1.4925 2022-04-19 01:20:14,131 - mmseg - INFO - Iter [5650/80000] lr: 1.334e-06, eta: 19:52:24, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9944, decode.acc_seg: 59.8614, aux.loss_ce: 0.6032, aux.acc_seg: 52.9284, loss: 1.5976 2022-04-19 01:21:01,182 - mmseg - INFO - Iter [5700/80000] lr: 1.334e-06, eta: 19:51:22, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 1.0189, decode.acc_seg: 57.1729, aux.loss_ce: 0.6215, aux.acc_seg: 49.4235, loss: 1.6404 2022-04-19 01:21:47,890 - mmseg - INFO - Iter [5750/80000] lr: 1.333e-06, eta: 19:50:16, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9798, decode.acc_seg: 57.8759, aux.loss_ce: 0.6039, aux.acc_seg: 50.0205, loss: 1.5837 2022-04-19 01:22:34,510 - mmseg - INFO - Iter [5800/80000] lr: 1.332e-06, eta: 19:49:09, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9059, decode.acc_seg: 60.6551, aux.loss_ce: 0.5954, aux.acc_seg: 51.8949, loss: 1.5014 2022-04-19 01:23:21,527 - mmseg - INFO - Iter [5850/80000] lr: 1.331e-06, eta: 19:48:07, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9552, decode.acc_seg: 59.8388, aux.loss_ce: 0.5973, aux.acc_seg: 52.1236, loss: 1.5525 2022-04-19 01:24:08,621 - mmseg - INFO - Iter [5900/80000] lr: 1.330e-06, eta: 19:47:07, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9714, decode.acc_seg: 59.4698, aux.loss_ce: 0.5937, aux.acc_seg: 51.8683, loss: 1.5651 2022-04-19 01:24:55,874 - mmseg - INFO - Iter [5950/80000] lr: 1.329e-06, eta: 19:46:09, time: 0.945, data_time: 0.007, memory: 73037, decode.loss_ce: 0.9219, decode.acc_seg: 59.9812, aux.loss_ce: 0.5660, aux.acc_seg: 53.1815, loss: 1.4880 2022-04-19 01:25:42,470 - mmseg - INFO - Saving checkpoint at 6000 iterations 2022-04-19 01:25:54,539 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 01:25:54,540 - mmseg - INFO - Iter [6000/80000] lr: 1.328e-06, eta: 19:47:31, time: 1.173, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9799, decode.acc_seg: 58.4250, aux.loss_ce: 0.5934, aux.acc_seg: 51.5196, loss: 1.5733 2022-04-19 01:26:41,631 - mmseg - INFO - Iter [6050/80000] lr: 1.327e-06, eta: 19:46:31, time: 0.942, data_time: 0.007, memory: 73037, decode.loss_ce: 0.9094, decode.acc_seg: 59.6909, aux.loss_ce: 0.5599, aux.acc_seg: 52.4740, loss: 1.4693 2022-04-19 01:27:28,486 - mmseg - INFO - Iter [6100/80000] lr: 1.326e-06, eta: 19:45:27, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9544, decode.acc_seg: 60.8908, aux.loss_ce: 0.5947, aux.acc_seg: 52.9578, loss: 1.5491 2022-04-19 01:28:15,188 - mmseg - INFO - Iter [6150/80000] lr: 1.325e-06, eta: 19:44:22, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9675, decode.acc_seg: 58.5586, aux.loss_ce: 0.5913, aux.acc_seg: 50.6698, loss: 1.5588 2022-04-19 01:29:02,033 - mmseg - INFO - Iter [6200/80000] lr: 1.325e-06, eta: 19:43:19, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9882, decode.acc_seg: 57.6986, aux.loss_ce: 0.5859, aux.acc_seg: 51.6382, loss: 1.5741 2022-04-19 01:29:49,141 - mmseg - INFO - Iter [6250/80000] lr: 1.324e-06, eta: 19:42:19, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9852, decode.acc_seg: 58.2213, aux.loss_ce: 0.5844, aux.acc_seg: 51.6367, loss: 1.5696 2022-04-19 01:30:36,173 - mmseg - INFO - Iter [6300/80000] lr: 1.323e-06, eta: 19:41:18, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9863, decode.acc_seg: 58.4505, aux.loss_ce: 0.5851, aux.acc_seg: 51.3669, loss: 1.5714 2022-04-19 01:31:23,232 - mmseg - INFO - Iter [6350/80000] lr: 1.322e-06, eta: 19:40:18, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8925, decode.acc_seg: 59.7469, aux.loss_ce: 0.5418, aux.acc_seg: 53.6671, loss: 1.4343 2022-04-19 01:32:10,045 - mmseg - INFO - Iter [6400/80000] lr: 1.321e-06, eta: 19:39:16, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9428, decode.acc_seg: 59.2052, aux.loss_ce: 0.5616, aux.acc_seg: 52.3725, loss: 1.5044 2022-04-19 01:32:56,747 - mmseg - INFO - Iter [6450/80000] lr: 1.320e-06, eta: 19:38:11, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9379, decode.acc_seg: 58.9052, aux.loss_ce: 0.5542, aux.acc_seg: 52.7404, loss: 1.4920 2022-04-19 01:33:43,518 - mmseg - INFO - Iter [6500/80000] lr: 1.319e-06, eta: 19:37:09, time: 0.937, data_time: 0.007, memory: 73037, decode.loss_ce: 0.9682, decode.acc_seg: 58.2682, aux.loss_ce: 0.5713, aux.acc_seg: 51.5817, loss: 1.5395 2022-04-19 01:34:30,715 - mmseg - INFO - Iter [6550/80000] lr: 1.318e-06, eta: 19:36:11, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9473, decode.acc_seg: 58.3126, aux.loss_ce: 0.5661, aux.acc_seg: 51.0059, loss: 1.5135 2022-04-19 01:35:17,577 - mmseg - INFO - Iter [6600/80000] lr: 1.317e-06, eta: 19:35:11, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9339, decode.acc_seg: 59.2472, aux.loss_ce: 0.5563, aux.acc_seg: 52.9897, loss: 1.4902 2022-04-19 01:36:04,323 - mmseg - INFO - Iter [6650/80000] lr: 1.316e-06, eta: 19:34:08, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9280, decode.acc_seg: 59.1672, aux.loss_ce: 0.5508, aux.acc_seg: 52.7218, loss: 1.4788 2022-04-19 01:36:51,293 - mmseg - INFO - Iter [6700/80000] lr: 1.316e-06, eta: 19:33:09, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8997, decode.acc_seg: 61.7895, aux.loss_ce: 0.5430, aux.acc_seg: 55.1479, loss: 1.4426 2022-04-19 01:37:37,880 - mmseg - INFO - Iter [6750/80000] lr: 1.315e-06, eta: 19:32:05, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9088, decode.acc_seg: 59.0602, aux.loss_ce: 0.5417, aux.acc_seg: 52.7581, loss: 1.4505 2022-04-19 01:38:24,649 - mmseg - INFO - Iter [6800/80000] lr: 1.314e-06, eta: 19:31:04, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8724, decode.acc_seg: 58.9985, aux.loss_ce: 0.5220, aux.acc_seg: 52.2729, loss: 1.3944 2022-04-19 01:39:11,843 - mmseg - INFO - Iter [6850/80000] lr: 1.313e-06, eta: 19:30:07, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9319, decode.acc_seg: 61.2279, aux.loss_ce: 0.5491, aux.acc_seg: 54.9383, loss: 1.4809 2022-04-19 01:39:58,437 - mmseg - INFO - Iter [6900/80000] lr: 1.312e-06, eta: 19:29:05, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.9194, decode.acc_seg: 60.2832, aux.loss_ce: 0.5371, aux.acc_seg: 54.1223, loss: 1.4564 2022-04-19 01:40:45,276 - mmseg - INFO - Iter [6950/80000] lr: 1.311e-06, eta: 19:28:05, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8950, decode.acc_seg: 60.0855, aux.loss_ce: 0.5184, aux.acc_seg: 54.6540, loss: 1.4135 2022-04-19 01:41:32,330 - mmseg - INFO - Saving checkpoint at 7000 iterations 2022-04-19 01:41:44,244 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 01:41:44,244 - mmseg - INFO - Iter [7000/80000] lr: 1.310e-06, eta: 19:29:11, time: 1.179, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9269, decode.acc_seg: 60.2543, aux.loss_ce: 0.5322, aux.acc_seg: 54.3448, loss: 1.4591 2022-04-19 01:42:31,457 - mmseg - INFO - Iter [7050/80000] lr: 1.309e-06, eta: 19:28:15, time: 0.945, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8873, decode.acc_seg: 60.2101, aux.loss_ce: 0.5176, aux.acc_seg: 53.2970, loss: 1.4049 2022-04-19 01:43:18,661 - mmseg - INFO - Iter [7100/80000] lr: 1.308e-06, eta: 19:27:18, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9537, decode.acc_seg: 58.6304, aux.loss_ce: 0.5426, aux.acc_seg: 52.9971, loss: 1.4963 2022-04-19 01:44:05,295 - mmseg - INFO - Iter [7150/80000] lr: 1.307e-06, eta: 19:26:16, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8929, decode.acc_seg: 58.8172, aux.loss_ce: 0.5158, aux.acc_seg: 52.8499, loss: 1.4087 2022-04-19 01:44:52,415 - mmseg - INFO - Iter [7200/80000] lr: 1.307e-06, eta: 19:25:19, time: 0.942, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9682, decode.acc_seg: 57.6796, aux.loss_ce: 0.5429, aux.acc_seg: 53.0702, loss: 1.5111 2022-04-19 01:45:38,850 - mmseg - INFO - Iter [7250/80000] lr: 1.306e-06, eta: 19:24:15, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9334, decode.acc_seg: 59.3397, aux.loss_ce: 0.5335, aux.acc_seg: 53.5216, loss: 1.4669 2022-04-19 01:46:25,474 - mmseg - INFO - Iter [7300/80000] lr: 1.305e-06, eta: 19:23:13, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9037, decode.acc_seg: 60.3643, aux.loss_ce: 0.5170, aux.acc_seg: 54.6600, loss: 1.4207 2022-04-19 01:47:12,169 - mmseg - INFO - Iter [7350/80000] lr: 1.304e-06, eta: 19:22:12, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9695, decode.acc_seg: 58.5569, aux.loss_ce: 0.5347, aux.acc_seg: 53.5418, loss: 1.5042 2022-04-19 01:48:01,847 - mmseg - INFO - Iter [7400/80000] lr: 1.303e-06, eta: 19:21:40, time: 0.993, data_time: 0.056, memory: 73037, decode.loss_ce: 0.9302, decode.acc_seg: 58.4068, aux.loss_ce: 0.5266, aux.acc_seg: 52.7853, loss: 1.4568 2022-04-19 01:48:49,340 - mmseg - INFO - Iter [7450/80000] lr: 1.302e-06, eta: 19:20:47, time: 0.950, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8898, decode.acc_seg: 60.2286, aux.loss_ce: 0.5332, aux.acc_seg: 52.8894, loss: 1.4230 2022-04-19 01:49:36,104 - mmseg - INFO - Iter [7500/80000] lr: 1.301e-06, eta: 19:19:47, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9003, decode.acc_seg: 61.1701, aux.loss_ce: 0.5167, aux.acc_seg: 55.5782, loss: 1.4170 2022-04-19 01:50:23,289 - mmseg - INFO - Iter [7550/80000] lr: 1.300e-06, eta: 19:18:52, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8984, decode.acc_seg: 60.4428, aux.loss_ce: 0.5021, aux.acc_seg: 55.4968, loss: 1.4005 2022-04-19 01:51:09,801 - mmseg - INFO - Iter [7600/80000] lr: 1.299e-06, eta: 19:17:50, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8591, decode.acc_seg: 60.4808, aux.loss_ce: 0.4978, aux.acc_seg: 54.8789, loss: 1.3569 2022-04-19 01:51:56,905 - mmseg - INFO - Iter [7650/80000] lr: 1.299e-06, eta: 19:16:54, time: 0.942, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8741, decode.acc_seg: 58.8350, aux.loss_ce: 0.4887, aux.acc_seg: 54.1498, loss: 1.3628 2022-04-19 01:52:43,914 - mmseg - INFO - Iter [7700/80000] lr: 1.298e-06, eta: 19:15:56, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8794, decode.acc_seg: 61.1455, aux.loss_ce: 0.5032, aux.acc_seg: 56.3612, loss: 1.3826 2022-04-19 01:53:31,356 - mmseg - INFO - Iter [7750/80000] lr: 1.297e-06, eta: 19:15:04, time: 0.950, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9120, decode.acc_seg: 60.5522, aux.loss_ce: 0.5103, aux.acc_seg: 55.2579, loss: 1.4223 2022-04-19 01:54:18,110 - mmseg - INFO - Iter [7800/80000] lr: 1.296e-06, eta: 19:14:05, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8997, decode.acc_seg: 59.4298, aux.loss_ce: 0.5045, aux.acc_seg: 53.8670, loss: 1.4042 2022-04-19 01:55:04,940 - mmseg - INFO - Iter [7850/80000] lr: 1.295e-06, eta: 19:13:06, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8494, decode.acc_seg: 60.5701, aux.loss_ce: 0.4837, aux.acc_seg: 55.2356, loss: 1.3331 2022-04-19 01:55:51,720 - mmseg - INFO - Iter [7900/80000] lr: 1.294e-06, eta: 19:12:08, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9087, decode.acc_seg: 58.3878, aux.loss_ce: 0.5103, aux.acc_seg: 53.1597, loss: 1.4190 2022-04-19 01:56:38,428 - mmseg - INFO - Iter [7950/80000] lr: 1.293e-06, eta: 19:11:09, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9010, decode.acc_seg: 60.1144, aux.loss_ce: 0.4941, aux.acc_seg: 55.5089, loss: 1.3952 2022-04-19 01:57:25,337 - mmseg - INFO - Saving checkpoint at 8000 iterations 2022-04-19 01:57:38,481 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 01:57:38,482 - mmseg - INFO - Iter [8000/80000] lr: 1.292e-06, eta: 19:12:09, time: 1.201, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8735, decode.acc_seg: 60.3973, aux.loss_ce: 0.4942, aux.acc_seg: 55.3754, loss: 1.3677 2022-04-19 02:02:16,750 - mmseg - INFO - per class results: 2022-04-19 02:02:16,759 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 84.82 | 95.1 | | bicycle | 67.36 | 83.8 | | car | 63.23 | 80.28 | | motorcycle | 81.52 | 94.5 | | airplane | 82.5 | 94.18 | | bus | 80.8 | 92.83 | | train | 80.59 | 93.3 | | truck | 62.81 | 81.78 | | boat | 64.22 | 81.91 | | traffic light | 56.9 | 80.21 | | fire hydrant | 80.42 | 96.15 | | stop sign | 72.7 | 97.97 | | parking meter | 71.42 | 86.08 | | bench | 52.72 | 70.29 | | bird | 79.74 | 88.76 | | cat | 83.3 | 90.27 | | dog | 77.99 | 86.74 | | horse | 83.3 | 93.38 | | sheep | 85.96 | 96.57 | | cow | 86.56 | 92.4 | | elephant | 90.74 | 97.88 | | bear | 90.68 | 96.92 | | zebra | 89.81 | 97.21 | | giraffe | 83.2 | 94.92 | | backpack | 32.55 | 50.71 | | umbrella | 80.64 | 91.36 | | handbag | 27.33 | 32.39 | | tie | 0.12 | 0.12 | | suitcase | 76.47 | 94.31 | | frisbee | 62.65 | 87.66 | | skis | 29.33 | 40.49 | | snowboard | 51.34 | 63.73 | | sports ball | 22.69 | 22.77 | | kite | 65.96 | 81.19 | | baseball bat | 34.63 | 39.33 | | baseball glove | 65.9 | 70.76 | | skateboard | 69.27 | 87.49 | | surfboard | 75.7 | 85.85 | | tennis racket | 79.29 | 87.27 | | bottle | 46.39 | 60.57 | | wine glass | 52.56 | 70.33 | | cup | 51.78 | 72.56 | | fork | 29.16 | 39.55 | | knife | 26.31 | 38.93 | | spoon | 1.49 | 1.5 | | bowl | 43.93 | 60.61 | | banana | 67.93 | 90.57 | | apple | 47.55 | 79.7 | | sandwich | 50.36 | 72.07 | | orange | 68.27 | 82.51 | | broccoli | 37.57 | 43.09 | | carrot | 55.09 | 67.64 | | hot dog | 54.15 | 68.21 | | pizza | 77.19 | 92.69 | | donut | 74.94 | 92.19 | | cake | 63.26 | 84.76 | | chair | 46.68 | 69.21 | | couch | 58.9 | 79.75 | | potted plant | 27.52 | 38.16 | | bed | 64.9 | 81.08 | | dining table | 43.94 | 79.23 | | toilet | 79.84 | 92.06 | | tv | 69.12 | 84.14 | | laptop | 70.36 | 93.16 | | mouse | 52.28 | 56.37 | | remote | 47.96 | 70.83 | | keyboard | 57.81 | 68.51 | | cell phone | 74.76 | 87.2 | | microwave | 64.46 | 93.55 | | oven | 51.38 | 84.49 | | toaster | 0.0 | 0.0 | | sink | 59.73 | 81.07 | | refrigerator | 71.39 | 91.59 | | book | 47.15 | 63.47 | | clock | 66.05 | 88.89 | | vase | 56.28 | 89.1 | | scissors | 65.19 | 92.18 | | teddy bear | 76.9 | 90.72 | | hair drier | 0.0 | 0.0 | | toothbrush | 46.22 | 59.6 | | banner | 26.16 | 68.36 | | blanket | 1.15 | 1.25 | | branch | 19.89 | 21.34 | | bridge | 33.03 | 58.23 | | building-other | 53.62 | 69.23 | | bush | 32.37 | 47.33 | | cabinet | 55.02 | 74.18 | | cage | 19.51 | 28.37 | | cardboard | 42.51 | 54.32 | | carpet | 50.15 | 79.69 | | ceiling-other | 64.25 | 81.25 | | ceiling-tile | 0.0 | 0.0 | | cloth | 0.0 | 0.0 | | clothes | 11.77 | 12.91 | | clouds | 51.09 | 71.52 | | counter | 28.52 | 45.1 | | cupboard | 0.0 | 0.0 | | curtain | 64.43 | 78.56 | | desk-stuff | 43.93 | 65.6 | | dirt | 41.8 | 67.88 | | door-stuff | 41.04 | 72.92 | | fence | 32.77 | 61.59 | | floor-marble | 0.05 | 0.05 | | floor-other | 20.58 | 26.72 | | floor-stone | 0.0 | 0.0 | | floor-tile | 61.03 | 79.21 | | floor-wood | 58.1 | 83.83 | | flower | 45.65 | 72.91 | | fog | 10.43 | 11.47 | | food-other | 22.72 | 26.73 | | fruit | 25.54 | 31.62 | | furniture-other | 13.74 | 17.0 | | grass | 69.48 | 81.34 | | gravel | 22.57 | 33.43 | | ground-other | 1.29 | 1.42 | | hill | 8.81 | 10.17 | | house | 28.14 | 38.58 | | leaves | 28.38 | 33.28 | | light | 35.78 | 51.49 | | mat | 0.0 | 0.0 | | metal | 26.24 | 32.95 | | mirror-stuff | 43.62 | 59.5 | | moss | 0.0 | 0.0 | | mountain | 51.48 | 81.29 | | mud | 0.71 | 0.9 | | napkin | 0.16 | 0.16 | | net | 44.63 | 66.39 | | paper | 28.47 | 36.32 | | pavement | 47.05 | 65.99 | | pillow | 0.0 | 0.0 | | plant-other | 16.1 | 23.0 | | plastic | 13.6 | 15.91 | | platform | 24.37 | 35.04 | | playingfield | 69.44 | 89.82 | | railing | 2.5 | 2.65 | | railroad | 55.3 | 85.37 | | river | 46.31 | 75.51 | | road | 62.96 | 84.14 | | rock | 45.89 | 65.57 | | roof | 21.84 | 28.15 | | rug | 23.37 | 26.82 | | salad | 0.0 | 0.0 | | sand | 62.53 | 71.08 | | sea | 84.0 | 90.76 | | shelf | 27.63 | 33.74 | | sky-other | 70.61 | 83.82 | | skyscraper | 34.95 | 41.59 | | snow | 87.47 | 90.17 | | solid-other | 0.0 | 0.0 | | stairs | 24.84 | 57.0 | | stone | 15.39 | 26.26 | | straw | 27.71 | 32.63 | | structural-other | 0.0 | 0.0 | | table | 16.33 | 19.97 | | tent | 10.16 | 14.68 | | textile-other | 12.62 | 18.75 | | towel | 30.29 | 40.94 | | tree | 72.34 | 89.25 | | vegetable | 37.1 | 43.4 | | wall-brick | 47.47 | 57.53 | | wall-concrete | 60.31 | 81.52 | | wall-other | 17.63 | 22.21 | | wall-panel | 3.49 | 3.84 | | wall-stone | 30.5 | 38.61 | | wall-tile | 63.29 | 86.73 | | wall-wood | 36.75 | 55.04 | | water-other | 21.46 | 28.56 | | waterdrops | 0.0 | 0.0 | | window-blind | 50.49 | 62.46 | | window-other | 44.99 | 72.86 | | wood | 22.92 | 30.33 | +------------------+-------+-------+ 2022-04-19 02:02:16,760 - mmseg - INFO - Summary: 2022-04-19 02:02:16,760 - mmseg - INFO - +------+-------+-------+ | aAcc | mIoU | mAcc | +------+-------+-------+ | 71.2 | 44.31 | 57.19 | +------+-------+-------+ 2022-04-19 02:02:16,776 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 02:02:16,776 - mmseg - INFO - Iter(val) [625] aAcc: 0.7120, mIoU: 0.4431, mAcc: 0.5719, IoU.person: 0.8482, IoU.bicycle: 0.6736, IoU.car: 0.6323, IoU.motorcycle: 0.8152, IoU.airplane: 0.8250, IoU.bus: 0.8080, IoU.train: 0.8059, IoU.truck: 0.6281, IoU.boat: 0.6422, IoU.traffic light: 0.5690, IoU.fire hydrant: 0.8042, IoU.stop sign: 0.7270, IoU.parking meter: 0.7142, IoU.bench: 0.5272, IoU.bird: 0.7974, IoU.cat: 0.8330, IoU.dog: 0.7799, IoU.horse: 0.8330, IoU.sheep: 0.8596, IoU.cow: 0.8656, IoU.elephant: 0.9074, IoU.bear: 0.9068, IoU.zebra: 0.8981, IoU.giraffe: 0.8320, IoU.backpack: 0.3255, IoU.umbrella: 0.8064, IoU.handbag: 0.2733, IoU.tie: 0.0012, IoU.suitcase: 0.7647, IoU.frisbee: 0.6265, IoU.skis: 0.2933, IoU.snowboard: 0.5134, IoU.sports ball: 0.2269, IoU.kite: 0.6596, IoU.baseball bat: 0.3463, IoU.baseball glove: 0.6590, IoU.skateboard: 0.6927, IoU.surfboard: 0.7570, IoU.tennis racket: 0.7929, IoU.bottle: 0.4639, IoU.wine glass: 0.5256, IoU.cup: 0.5178, IoU.fork: 0.2916, IoU.knife: 0.2631, IoU.spoon: 0.0149, IoU.bowl: 0.4393, IoU.banana: 0.6793, IoU.apple: 0.4755, IoU.sandwich: 0.5036, IoU.orange: 0.6827, IoU.broccoli: 0.3757, IoU.carrot: 0.5509, IoU.hot dog: 0.5415, IoU.pizza: 0.7719, IoU.donut: 0.7494, IoU.cake: 0.6326, IoU.chair: 0.4668, IoU.couch: 0.5890, IoU.potted plant: 0.2752, IoU.bed: 0.6490, IoU.dining table: 0.4394, IoU.toilet: 0.7984, IoU.tv: 0.6912, IoU.laptop: 0.7036, IoU.mouse: 0.5228, IoU.remote: 0.4796, IoU.keyboard: 0.5781, IoU.cell phone: 0.7476, IoU.microwave: 0.6446, IoU.oven: 0.5138, IoU.toaster: 0.0000, IoU.sink: 0.5973, IoU.refrigerator: 0.7139, IoU.book: 0.4715, IoU.clock: 0.6605, IoU.vase: 0.5628, IoU.scissors: 0.6519, IoU.teddy bear: 0.7690, IoU.hair drier: 0.0000, IoU.toothbrush: 0.4622, IoU.banner: 0.2616, IoU.blanket: 0.0115, IoU.branch: 0.1989, IoU.bridge: 0.3303, IoU.building-other: 0.5362, IoU.bush: 0.3237, IoU.cabinet: 0.5502, IoU.cage: 0.1951, IoU.cardboard: 0.4251, IoU.carpet: 0.5015, IoU.ceiling-other: 0.6425, IoU.ceiling-tile: 0.0000, IoU.cloth: 0.0000, IoU.clothes: 0.1177, IoU.clouds: 0.5109, IoU.counter: 0.2852, IoU.cupboard: 0.0000, IoU.curtain: 0.6443, IoU.desk-stuff: 0.4393, IoU.dirt: 0.4180, IoU.door-stuff: 0.4104, IoU.fence: 0.3277, IoU.floor-marble: 0.0005, IoU.floor-other: 0.2058, IoU.floor-stone: 0.0000, IoU.floor-tile: 0.6103, IoU.floor-wood: 0.5810, IoU.flower: 0.4565, IoU.fog: 0.1043, IoU.food-other: 0.2272, IoU.fruit: 0.2554, IoU.furniture-other: 0.1374, IoU.grass: 0.6948, IoU.gravel: 0.2257, IoU.ground-other: 0.0129, IoU.hill: 0.0881, IoU.house: 0.2814, IoU.leaves: 0.2838, IoU.light: 0.3578, IoU.mat: 0.0000, IoU.metal: 0.2624, IoU.mirror-stuff: 0.4362, IoU.moss: 0.0000, IoU.mountain: 0.5148, IoU.mud: 0.0071, IoU.napkin: 0.0016, IoU.net: 0.4463, IoU.paper: 0.2847, IoU.pavement: 0.4705, IoU.pillow: 0.0000, IoU.plant-other: 0.1610, IoU.plastic: 0.1360, IoU.platform: 0.2437, IoU.playingfield: 0.6944, IoU.railing: 0.0250, IoU.railroad: 0.5530, IoU.river: 0.4631, IoU.road: 0.6296, IoU.rock: 0.4589, IoU.roof: 0.2184, IoU.rug: 0.2337, IoU.salad: 0.0000, IoU.sand: 0.6253, IoU.sea: 0.8400, IoU.shelf: 0.2763, IoU.sky-other: 0.7061, IoU.skyscraper: 0.3495, IoU.snow: 0.8747, IoU.solid-other: 0.0000, IoU.stairs: 0.2484, IoU.stone: 0.1539, IoU.straw: 0.2771, IoU.structural-other: 0.0000, IoU.table: 0.1633, IoU.tent: 0.1016, IoU.textile-other: 0.1262, IoU.towel: 0.3029, IoU.tree: 0.7234, IoU.vegetable: 0.3710, IoU.wall-brick: 0.4747, IoU.wall-concrete: 0.6031, IoU.wall-other: 0.1763, IoU.wall-panel: 0.0349, IoU.wall-stone: 0.3050, IoU.wall-tile: 0.6329, IoU.wall-wood: 0.3675, IoU.water-other: 0.2146, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5049, IoU.window-other: 0.4499, IoU.wood: 0.2292, Acc.person: 0.9510, Acc.bicycle: 0.8380, Acc.car: 0.8028, Acc.motorcycle: 0.9450, Acc.airplane: 0.9418, Acc.bus: 0.9283, Acc.train: 0.9330, Acc.truck: 0.8178, Acc.boat: 0.8191, Acc.traffic light: 0.8021, Acc.fire hydrant: 0.9615, Acc.stop sign: 0.9797, Acc.parking meter: 0.8608, Acc.bench: 0.7029, Acc.bird: 0.8876, Acc.cat: 0.9027, Acc.dog: 0.8674, Acc.horse: 0.9338, Acc.sheep: 0.9657, Acc.cow: 0.9240, Acc.elephant: 0.9788, Acc.bear: 0.9692, Acc.zebra: 0.9721, Acc.giraffe: 0.9492, Acc.backpack: 0.5071, Acc.umbrella: 0.9136, Acc.handbag: 0.3239, Acc.tie: 0.0012, Acc.suitcase: 0.9431, Acc.frisbee: 0.8766, Acc.skis: 0.4049, Acc.snowboard: 0.6373, Acc.sports ball: 0.2277, Acc.kite: 0.8119, Acc.baseball bat: 0.3933, Acc.baseball glove: 0.7076, Acc.skateboard: 0.8749, Acc.surfboard: 0.8585, Acc.tennis racket: 0.8727, Acc.bottle: 0.6057, Acc.wine glass: 0.7033, Acc.cup: 0.7256, Acc.fork: 0.3955, Acc.knife: 0.3893, Acc.spoon: 0.0150, Acc.bowl: 0.6061, Acc.banana: 0.9057, Acc.apple: 0.7970, Acc.sandwich: 0.7207, Acc.orange: 0.8251, Acc.broccoli: 0.4309, Acc.carrot: 0.6764, Acc.hot dog: 0.6821, Acc.pizza: 0.9269, Acc.donut: 0.9219, Acc.cake: 0.8476, Acc.chair: 0.6921, Acc.couch: 0.7975, Acc.potted plant: 0.3816, Acc.bed: 0.8108, Acc.dining table: 0.7923, Acc.toilet: 0.9206, Acc.tv: 0.8414, Acc.laptop: 0.9316, Acc.mouse: 0.5637, Acc.remote: 0.7083, Acc.keyboard: 0.6851, Acc.cell phone: 0.8720, Acc.microwave: 0.9355, Acc.oven: 0.8449, Acc.toaster: 0.0000, Acc.sink: 0.8107, Acc.refrigerator: 0.9159, Acc.book: 0.6347, Acc.clock: 0.8889, Acc.vase: 0.8910, Acc.scissors: 0.9218, Acc.teddy bear: 0.9072, Acc.hair drier: 0.0000, Acc.toothbrush: 0.5960, Acc.banner: 0.6836, Acc.blanket: 0.0125, Acc.branch: 0.2134, Acc.bridge: 0.5823, Acc.building-other: 0.6923, Acc.bush: 0.4733, Acc.cabinet: 0.7418, Acc.cage: 0.2837, Acc.cardboard: 0.5432, Acc.carpet: 0.7969, Acc.ceiling-other: 0.8125, Acc.ceiling-tile: 0.0000, Acc.cloth: 0.0000, Acc.clothes: 0.1291, Acc.clouds: 0.7152, Acc.counter: 0.4510, Acc.cupboard: 0.0000, Acc.curtain: 0.7856, Acc.desk-stuff: 0.6560, Acc.dirt: 0.6788, Acc.door-stuff: 0.7292, Acc.fence: 0.6159, Acc.floor-marble: 0.0005, Acc.floor-other: 0.2672, Acc.floor-stone: 0.0000, Acc.floor-tile: 0.7921, Acc.floor-wood: 0.8383, Acc.flower: 0.7291, Acc.fog: 0.1147, Acc.food-other: 0.2673, Acc.fruit: 0.3162, Acc.furniture-other: 0.1700, Acc.grass: 0.8134, Acc.gravel: 0.3343, Acc.ground-other: 0.0142, Acc.hill: 0.1017, Acc.house: 0.3858, Acc.leaves: 0.3328, Acc.light: 0.5149, Acc.mat: 0.0000, Acc.metal: 0.3295, Acc.mirror-stuff: 0.5950, Acc.moss: 0.0000, Acc.mountain: 0.8129, Acc.mud: 0.0090, Acc.napkin: 0.0016, Acc.net: 0.6639, Acc.paper: 0.3632, Acc.pavement: 0.6599, Acc.pillow: 0.0000, Acc.plant-other: 0.2300, Acc.plastic: 0.1591, Acc.platform: 0.3504, Acc.playingfield: 0.8982, Acc.railing: 0.0265, Acc.railroad: 0.8537, Acc.river: 0.7551, Acc.road: 0.8414, Acc.rock: 0.6557, Acc.roof: 0.2815, Acc.rug: 0.2682, Acc.salad: 0.0000, Acc.sand: 0.7108, Acc.sea: 0.9076, Acc.shelf: 0.3374, Acc.sky-other: 0.8382, Acc.skyscraper: 0.4159, Acc.snow: 0.9017, Acc.solid-other: 0.0000, Acc.stairs: 0.5700, Acc.stone: 0.2626, Acc.straw: 0.3263, Acc.structural-other: 0.0000, Acc.table: 0.1997, Acc.tent: 0.1468, Acc.textile-other: 0.1875, Acc.towel: 0.4094, Acc.tree: 0.8925, Acc.vegetable: 0.4340, Acc.wall-brick: 0.5753, Acc.wall-concrete: 0.8152, Acc.wall-other: 0.2221, Acc.wall-panel: 0.0384, Acc.wall-stone: 0.3861, Acc.wall-tile: 0.8673, Acc.wall-wood: 0.5504, Acc.water-other: 0.2856, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6246, Acc.window-other: 0.7286, Acc.wood: 0.3033 2022-04-19 02:03:03,705 - mmseg - INFO - Iter [8050/80000] lr: 1.291e-06, eta: 19:52:39, time: 6.505, data_time: 5.572, memory: 73037, decode.loss_ce: 0.8883, decode.acc_seg: 59.6962, aux.loss_ce: 0.4887, aux.acc_seg: 55.2782, loss: 1.3770 2022-04-19 02:03:50,744 - mmseg - INFO - Iter [8100/80000] lr: 1.290e-06, eta: 19:51:25, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9212, decode.acc_seg: 59.2333, aux.loss_ce: 0.4982, aux.acc_seg: 54.4575, loss: 1.4194 2022-04-19 02:04:37,149 - mmseg - INFO - Iter [8150/80000] lr: 1.290e-06, eta: 19:50:07, time: 0.930, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8515, decode.acc_seg: 62.2373, aux.loss_ce: 0.4767, aux.acc_seg: 57.9335, loss: 1.3282 2022-04-19 02:05:23,739 - mmseg - INFO - Iter [8200/80000] lr: 1.289e-06, eta: 19:48:50, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8603, decode.acc_seg: 60.8816, aux.loss_ce: 0.4767, aux.acc_seg: 55.9030, loss: 1.3370 2022-04-19 02:06:10,183 - mmseg - INFO - Iter [8250/80000] lr: 1.288e-06, eta: 19:47:32, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9162, decode.acc_seg: 60.0168, aux.loss_ce: 0.5075, aux.acc_seg: 55.4441, loss: 1.4237 2022-04-19 02:06:56,853 - mmseg - INFO - Iter [8300/80000] lr: 1.287e-06, eta: 19:46:17, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8950, decode.acc_seg: 60.3813, aux.loss_ce: 0.4824, aux.acc_seg: 56.1302, loss: 1.3774 2022-04-19 02:07:43,380 - mmseg - INFO - Iter [8350/80000] lr: 1.286e-06, eta: 19:45:01, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8461, decode.acc_seg: 61.1853, aux.loss_ce: 0.4654, aux.acc_seg: 56.9933, loss: 1.3115 2022-04-19 02:08:29,939 - mmseg - INFO - Iter [8400/80000] lr: 1.285e-06, eta: 19:43:45, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8085, decode.acc_seg: 61.6977, aux.loss_ce: 0.4519, aux.acc_seg: 56.6816, loss: 1.2603 2022-04-19 02:09:16,575 - mmseg - INFO - Iter [8450/80000] lr: 1.284e-06, eta: 19:42:30, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8632, decode.acc_seg: 60.0152, aux.loss_ce: 0.4776, aux.acc_seg: 55.4794, loss: 1.3409 2022-04-19 02:10:03,274 - mmseg - INFO - Iter [8500/80000] lr: 1.283e-06, eta: 19:41:16, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8393, decode.acc_seg: 59.7230, aux.loss_ce: 0.4491, aux.acc_seg: 56.0379, loss: 1.2884 2022-04-19 02:10:49,842 - mmseg - INFO - Iter [8550/80000] lr: 1.282e-06, eta: 19:40:02, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8279, decode.acc_seg: 61.2002, aux.loss_ce: 0.4508, aux.acc_seg: 57.5153, loss: 1.2787 2022-04-19 02:11:36,718 - mmseg - INFO - Iter [8600/80000] lr: 1.281e-06, eta: 19:38:50, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8800, decode.acc_seg: 61.0783, aux.loss_ce: 0.4712, aux.acc_seg: 57.6430, loss: 1.3512 2022-04-19 02:12:23,242 - mmseg - INFO - Iter [8650/80000] lr: 1.281e-06, eta: 19:37:36, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8945, decode.acc_seg: 60.5760, aux.loss_ce: 0.4807, aux.acc_seg: 55.3334, loss: 1.3752 2022-04-19 02:13:09,626 - mmseg - INFO - Iter [8700/80000] lr: 1.280e-06, eta: 19:36:21, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8800, decode.acc_seg: 60.0029, aux.loss_ce: 0.4719, aux.acc_seg: 56.0592, loss: 1.3519 2022-04-19 02:13:56,315 - mmseg - INFO - Iter [8750/80000] lr: 1.279e-06, eta: 19:35:08, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8827, decode.acc_seg: 59.8088, aux.loss_ce: 0.4702, aux.acc_seg: 55.4113, loss: 1.3529 2022-04-19 02:14:42,822 - mmseg - INFO - Iter [8800/80000] lr: 1.278e-06, eta: 19:33:55, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8291, decode.acc_seg: 60.7003, aux.loss_ce: 0.4452, aux.acc_seg: 56.5540, loss: 1.2743 2022-04-19 02:15:29,489 - mmseg - INFO - Iter [8850/80000] lr: 1.277e-06, eta: 19:32:43, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8967, decode.acc_seg: 60.1932, aux.loss_ce: 0.4789, aux.acc_seg: 56.0971, loss: 1.3757 2022-04-19 02:16:16,164 - mmseg - INFO - Iter [8900/80000] lr: 1.276e-06, eta: 19:31:30, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8598, decode.acc_seg: 59.7205, aux.loss_ce: 0.4592, aux.acc_seg: 55.7205, loss: 1.3190 2022-04-19 02:17:02,897 - mmseg - INFO - Iter [8950/80000] lr: 1.275e-06, eta: 19:30:20, time: 0.937, data_time: 0.008, memory: 73037, decode.loss_ce: 0.9115, decode.acc_seg: 60.6186, aux.loss_ce: 0.4806, aux.acc_seg: 55.9222, loss: 1.3921 2022-04-19 02:17:49,626 - mmseg - INFO - Saving checkpoint at 9000 iterations 2022-04-19 02:18:08,619 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 02:18:08,635 - mmseg - INFO - Iter [9000/80000] lr: 1.274e-06, eta: 19:31:38, time: 1.312, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8772, decode.acc_seg: 59.0256, aux.loss_ce: 0.4664, aux.acc_seg: 55.0359, loss: 1.3436 2022-04-19 02:18:56,122 - mmseg - INFO - Iter [9050/80000] lr: 1.273e-06, eta: 19:30:34, time: 0.953, data_time: 0.010, memory: 73037, decode.loss_ce: 0.8762, decode.acc_seg: 59.4976, aux.loss_ce: 0.4689, aux.acc_seg: 55.0050, loss: 1.3451 2022-04-19 02:19:42,486 - mmseg - INFO - Iter [9100/80000] lr: 1.272e-06, eta: 19:29:20, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8894, decode.acc_seg: 58.5694, aux.loss_ce: 0.4679, aux.acc_seg: 54.7579, loss: 1.3572 2022-04-19 02:20:29,068 - mmseg - INFO - Iter [9150/80000] lr: 1.272e-06, eta: 19:28:08, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8591, decode.acc_seg: 61.1095, aux.loss_ce: 0.4661, aux.acc_seg: 56.3818, loss: 1.3253 2022-04-19 02:21:15,812 - mmseg - INFO - Iter [9200/80000] lr: 1.271e-06, eta: 19:26:58, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8924, decode.acc_seg: 60.7111, aux.loss_ce: 0.4738, aux.acc_seg: 56.4308, loss: 1.3661 2022-04-19 02:22:02,615 - mmseg - INFO - Iter [9250/80000] lr: 1.270e-06, eta: 19:25:48, time: 0.936, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8580, decode.acc_seg: 60.3373, aux.loss_ce: 0.4537, aux.acc_seg: 56.3193, loss: 1.3116 2022-04-19 02:22:49,229 - mmseg - INFO - Iter [9300/80000] lr: 1.269e-06, eta: 19:24:37, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8592, decode.acc_seg: 60.5764, aux.loss_ce: 0.4527, aux.acc_seg: 56.5861, loss: 1.3119 2022-04-19 02:23:35,695 - mmseg - INFO - Iter [9350/80000] lr: 1.268e-06, eta: 19:23:26, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8588, decode.acc_seg: 60.8097, aux.loss_ce: 0.4371, aux.acc_seg: 57.5673, loss: 1.2960 2022-04-19 02:24:22,428 - mmseg - INFO - Iter [9400/80000] lr: 1.267e-06, eta: 19:22:16, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8561, decode.acc_seg: 59.3385, aux.loss_ce: 0.4559, aux.acc_seg: 55.1219, loss: 1.3120 2022-04-19 02:25:08,977 - mmseg - INFO - Iter [9450/80000] lr: 1.266e-06, eta: 19:21:06, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8280, decode.acc_seg: 59.8619, aux.loss_ce: 0.4407, aux.acc_seg: 56.1085, loss: 1.2687 2022-04-19 02:25:55,341 - mmseg - INFO - Iter [9500/80000] lr: 1.265e-06, eta: 19:19:54, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8470, decode.acc_seg: 61.3195, aux.loss_ce: 0.4476, aux.acc_seg: 57.4350, loss: 1.2946 2022-04-19 02:26:41,985 - mmseg - INFO - Iter [9550/80000] lr: 1.264e-06, eta: 19:18:45, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8676, decode.acc_seg: 58.8943, aux.loss_ce: 0.4556, aux.acc_seg: 55.1765, loss: 1.3232 2022-04-19 02:27:28,838 - mmseg - INFO - Iter [9600/80000] lr: 1.264e-06, eta: 19:17:37, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8887, decode.acc_seg: 59.6490, aux.loss_ce: 0.4665, aux.acc_seg: 55.6730, loss: 1.3552 2022-04-19 02:28:15,314 - mmseg - INFO - Iter [9650/80000] lr: 1.263e-06, eta: 19:16:27, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8327, decode.acc_seg: 62.0604, aux.loss_ce: 0.4397, aux.acc_seg: 58.1938, loss: 1.2723 2022-04-19 02:29:01,814 - mmseg - INFO - Iter [9700/80000] lr: 1.262e-06, eta: 19:15:17, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8294, decode.acc_seg: 61.9240, aux.loss_ce: 0.4350, aux.acc_seg: 57.9249, loss: 1.2644 2022-04-19 02:29:48,655 - mmseg - INFO - Iter [9750/80000] lr: 1.261e-06, eta: 19:14:10, time: 0.937, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8915, decode.acc_seg: 59.5979, aux.loss_ce: 0.4532, aux.acc_seg: 56.5765, loss: 1.3448 2022-04-19 02:30:35,359 - mmseg - INFO - Iter [9800/80000] lr: 1.260e-06, eta: 19:13:02, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.9031, decode.acc_seg: 59.7195, aux.loss_ce: 0.4621, aux.acc_seg: 56.1064, loss: 1.3652 2022-04-19 02:31:21,913 - mmseg - INFO - Iter [9850/80000] lr: 1.259e-06, eta: 19:11:54, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8312, decode.acc_seg: 60.2299, aux.loss_ce: 0.4321, aux.acc_seg: 55.9601, loss: 1.2633 2022-04-19 02:32:08,321 - mmseg - INFO - Iter [9900/80000] lr: 1.258e-06, eta: 19:10:44, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8530, decode.acc_seg: 60.8572, aux.loss_ce: 0.4451, aux.acc_seg: 57.4057, loss: 1.2981 2022-04-19 02:32:54,961 - mmseg - INFO - Iter [9950/80000] lr: 1.257e-06, eta: 19:09:37, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8286, decode.acc_seg: 63.1099, aux.loss_ce: 0.4305, aux.acc_seg: 59.3599, loss: 1.2591 2022-04-19 02:33:41,601 - mmseg - INFO - Saving checkpoint at 10000 iterations 2022-04-19 02:33:57,641 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 02:33:57,651 - mmseg - INFO - Iter [10000/80000] lr: 1.256e-06, eta: 19:10:20, time: 1.251, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8642, decode.acc_seg: 60.7312, aux.loss_ce: 0.4450, aux.acc_seg: 57.2972, loss: 1.3092 2022-04-19 02:34:44,821 - mmseg - INFO - Iter [10050/80000] lr: 1.255e-06, eta: 19:09:17, time: 0.947, data_time: 0.009, memory: 73037, decode.loss_ce: 0.8800, decode.acc_seg: 59.6406, aux.loss_ce: 0.4516, aux.acc_seg: 56.1529, loss: 1.3316 2022-04-19 02:35:31,612 - mmseg - INFO - Iter [10100/80000] lr: 1.255e-06, eta: 19:08:11, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8457, decode.acc_seg: 61.3573, aux.loss_ce: 0.4328, aux.acc_seg: 58.0168, loss: 1.2785 2022-04-19 02:36:18,369 - mmseg - INFO - Iter [10150/80000] lr: 1.254e-06, eta: 19:07:04, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8633, decode.acc_seg: 60.9368, aux.loss_ce: 0.4380, aux.acc_seg: 57.6699, loss: 1.3013 2022-04-19 02:37:05,404 - mmseg - INFO - Iter [10200/80000] lr: 1.253e-06, eta: 19:05:59, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8724, decode.acc_seg: 60.3892, aux.loss_ce: 0.4381, aux.acc_seg: 57.6559, loss: 1.3106 2022-04-19 02:37:52,287 - mmseg - INFO - Iter [10250/80000] lr: 1.252e-06, eta: 19:04:54, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.9027, decode.acc_seg: 59.7934, aux.loss_ce: 0.4533, aux.acc_seg: 56.5829, loss: 1.3560 2022-04-19 02:38:38,901 - mmseg - INFO - Iter [10300/80000] lr: 1.251e-06, eta: 19:03:46, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8728, decode.acc_seg: 59.9761, aux.loss_ce: 0.4459, aux.acc_seg: 56.4997, loss: 1.3187 2022-04-19 02:39:25,320 - mmseg - INFO - Iter [10350/80000] lr: 1.250e-06, eta: 19:02:39, time: 0.930, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8787, decode.acc_seg: 60.7575, aux.loss_ce: 0.4465, aux.acc_seg: 56.6002, loss: 1.3252 2022-04-19 02:40:11,944 - mmseg - INFO - Iter [10400/80000] lr: 1.249e-06, eta: 19:01:32, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8627, decode.acc_seg: 59.0188, aux.loss_ce: 0.4339, aux.acc_seg: 56.2561, loss: 1.2966 2022-04-19 02:40:58,678 - mmseg - INFO - Iter [10450/80000] lr: 1.248e-06, eta: 19:00:27, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8482, decode.acc_seg: 61.0398, aux.loss_ce: 0.4293, aux.acc_seg: 57.3553, loss: 1.2775 2022-04-19 02:41:45,544 - mmseg - INFO - Iter [10500/80000] lr: 1.247e-06, eta: 18:59:22, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8943, decode.acc_seg: 60.4014, aux.loss_ce: 0.4460, aux.acc_seg: 57.0016, loss: 1.3404 2022-04-19 02:42:32,223 - mmseg - INFO - Iter [10550/80000] lr: 1.246e-06, eta: 18:58:16, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8492, decode.acc_seg: 60.8284, aux.loss_ce: 0.4311, aux.acc_seg: 57.9896, loss: 1.2803 2022-04-19 02:43:18,818 - mmseg - INFO - Iter [10600/80000] lr: 1.246e-06, eta: 18:57:10, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8549, decode.acc_seg: 61.3693, aux.loss_ce: 0.4360, aux.acc_seg: 57.7635, loss: 1.2909 2022-04-19 02:44:05,355 - mmseg - INFO - Iter [10650/80000] lr: 1.245e-06, eta: 18:56:04, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8705, decode.acc_seg: 61.0100, aux.loss_ce: 0.4385, aux.acc_seg: 58.0945, loss: 1.3090 2022-04-19 02:44:51,856 - mmseg - INFO - Iter [10700/80000] lr: 1.244e-06, eta: 18:54:58, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8938, decode.acc_seg: 59.6404, aux.loss_ce: 0.4427, aux.acc_seg: 57.1284, loss: 1.3365 2022-04-19 02:45:38,607 - mmseg - INFO - Iter [10750/80000] lr: 1.243e-06, eta: 18:53:53, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8109, decode.acc_seg: 61.3521, aux.loss_ce: 0.4131, aux.acc_seg: 57.6829, loss: 1.2240 2022-04-19 02:46:25,163 - mmseg - INFO - Iter [10800/80000] lr: 1.242e-06, eta: 18:52:48, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8201, decode.acc_seg: 62.5307, aux.loss_ce: 0.4136, aux.acc_seg: 59.3978, loss: 1.2337 2022-04-19 02:47:11,916 - mmseg - INFO - Iter [10850/80000] lr: 1.241e-06, eta: 18:51:44, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8448, decode.acc_seg: 60.7731, aux.loss_ce: 0.4185, aux.acc_seg: 57.9722, loss: 1.2633 2022-04-19 02:47:58,628 - mmseg - INFO - Iter [10900/80000] lr: 1.240e-06, eta: 18:50:40, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8565, decode.acc_seg: 61.2985, aux.loss_ce: 0.4298, aux.acc_seg: 57.7981, loss: 1.2864 2022-04-19 02:48:45,222 - mmseg - INFO - Iter [10950/80000] lr: 1.239e-06, eta: 18:49:35, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8502, decode.acc_seg: 61.5313, aux.loss_ce: 0.4213, aux.acc_seg: 58.9926, loss: 1.2716 2022-04-19 02:49:31,848 - mmseg - INFO - Saving checkpoint at 11000 iterations 2022-04-19 02:49:46,803 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 02:49:46,804 - mmseg - INFO - Iter [11000/80000] lr: 1.238e-06, eta: 18:50:04, time: 1.231, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8437, decode.acc_seg: 60.8666, aux.loss_ce: 0.4213, aux.acc_seg: 58.0540, loss: 1.2649 2022-04-19 02:50:33,608 - mmseg - INFO - Iter [11050/80000] lr: 1.237e-06, eta: 18:49:00, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8263, decode.acc_seg: 61.1081, aux.loss_ce: 0.4147, aux.acc_seg: 58.5799, loss: 1.2410 2022-04-19 02:51:20,142 - mmseg - INFO - Iter [11100/80000] lr: 1.237e-06, eta: 18:47:55, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8440, decode.acc_seg: 61.1688, aux.loss_ce: 0.4292, aux.acc_seg: 57.4058, loss: 1.2732 2022-04-19 02:52:06,687 - mmseg - INFO - Iter [11150/80000] lr: 1.236e-06, eta: 18:46:50, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8467, decode.acc_seg: 60.8334, aux.loss_ce: 0.4202, aux.acc_seg: 58.1539, loss: 1.2669 2022-04-19 02:52:53,268 - mmseg - INFO - Iter [11200/80000] lr: 1.235e-06, eta: 18:45:46, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8338, decode.acc_seg: 61.8627, aux.loss_ce: 0.4146, aux.acc_seg: 59.2196, loss: 1.2484 2022-04-19 02:53:39,809 - mmseg - INFO - Iter [11250/80000] lr: 1.234e-06, eta: 18:44:40, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8238, decode.acc_seg: 59.7867, aux.loss_ce: 0.4085, aux.acc_seg: 57.1235, loss: 1.2323 2022-04-19 02:54:26,434 - mmseg - INFO - Iter [11300/80000] lr: 1.233e-06, eta: 18:43:37, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8790, decode.acc_seg: 59.0464, aux.loss_ce: 0.4318, aux.acc_seg: 56.4965, loss: 1.3108 2022-04-19 02:55:13,215 - mmseg - INFO - Iter [11350/80000] lr: 1.232e-06, eta: 18:42:34, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8280, decode.acc_seg: 60.9246, aux.loss_ce: 0.4148, aux.acc_seg: 58.2937, loss: 1.2428 2022-04-19 02:55:59,798 - mmseg - INFO - Iter [11400/80000] lr: 1.231e-06, eta: 18:41:30, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8248, decode.acc_seg: 61.4515, aux.loss_ce: 0.3974, aux.acc_seg: 59.2612, loss: 1.2222 2022-04-19 02:56:46,355 - mmseg - INFO - Iter [11450/80000] lr: 1.230e-06, eta: 18:40:26, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8633, decode.acc_seg: 60.7760, aux.loss_ce: 0.4241, aux.acc_seg: 57.9461, loss: 1.2874 2022-04-19 02:57:32,961 - mmseg - INFO - Iter [11500/80000] lr: 1.229e-06, eta: 18:39:23, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8192, decode.acc_seg: 60.4397, aux.loss_ce: 0.4055, aux.acc_seg: 57.7666, loss: 1.2247 2022-04-19 02:58:19,749 - mmseg - INFO - Iter [11550/80000] lr: 1.229e-06, eta: 18:38:20, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8285, decode.acc_seg: 61.9346, aux.loss_ce: 0.4115, aux.acc_seg: 59.1574, loss: 1.2400 2022-04-19 02:59:06,333 - mmseg - INFO - Iter [11600/80000] lr: 1.228e-06, eta: 18:37:17, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8369, decode.acc_seg: 61.0736, aux.loss_ce: 0.4138, aux.acc_seg: 57.9240, loss: 1.2507 2022-04-19 02:59:53,242 - mmseg - INFO - Iter [11650/80000] lr: 1.227e-06, eta: 18:36:16, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8447, decode.acc_seg: 59.7174, aux.loss_ce: 0.4114, aux.acc_seg: 56.7235, loss: 1.2561 2022-04-19 03:00:39,690 - mmseg - INFO - Iter [11700/80000] lr: 1.226e-06, eta: 18:35:12, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8230, decode.acc_seg: 60.6312, aux.loss_ce: 0.4093, aux.acc_seg: 56.9900, loss: 1.2323 2022-04-19 03:01:26,559 - mmseg - INFO - Iter [11750/80000] lr: 1.225e-06, eta: 18:34:11, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8498, decode.acc_seg: 62.3063, aux.loss_ce: 0.4178, aux.acc_seg: 60.1469, loss: 1.2676 2022-04-19 03:02:13,319 - mmseg - INFO - Iter [11800/80000] lr: 1.224e-06, eta: 18:33:09, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8430, decode.acc_seg: 63.0366, aux.loss_ce: 0.4115, aux.acc_seg: 60.6321, loss: 1.2545 2022-04-19 03:03:00,027 - mmseg - INFO - Iter [11850/80000] lr: 1.223e-06, eta: 18:32:07, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7910, decode.acc_seg: 62.6306, aux.loss_ce: 0.3867, aux.acc_seg: 60.1430, loss: 1.1777 2022-04-19 03:03:46,851 - mmseg - INFO - Iter [11900/80000] lr: 1.222e-06, eta: 18:31:06, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8056, decode.acc_seg: 60.0492, aux.loss_ce: 0.4006, aux.acc_seg: 57.5524, loss: 1.2062 2022-04-19 03:04:33,451 - mmseg - INFO - Iter [11950/80000] lr: 1.221e-06, eta: 18:30:03, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8506, decode.acc_seg: 60.6706, aux.loss_ce: 0.4142, aux.acc_seg: 57.6241, loss: 1.2648 2022-04-19 03:05:20,157 - mmseg - INFO - Saving checkpoint at 12000 iterations 2022-04-19 03:05:32,475 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 03:05:32,480 - mmseg - INFO - Iter [12000/80000] lr: 1.220e-06, eta: 18:30:12, time: 1.180, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8570, decode.acc_seg: 59.7791, aux.loss_ce: 0.4113, aux.acc_seg: 57.4996, loss: 1.2683 2022-04-19 03:06:19,440 - mmseg - INFO - Iter [12050/80000] lr: 1.220e-06, eta: 18:29:11, time: 0.940, data_time: 0.009, memory: 73037, decode.loss_ce: 0.8488, decode.acc_seg: 60.1201, aux.loss_ce: 0.4071, aux.acc_seg: 58.3308, loss: 1.2559 2022-04-19 03:07:06,114 - mmseg - INFO - Iter [12100/80000] lr: 1.219e-06, eta: 18:28:09, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7870, decode.acc_seg: 60.9006, aux.loss_ce: 0.3834, aux.acc_seg: 58.8727, loss: 1.1704 2022-04-19 03:07:52,755 - mmseg - INFO - Iter [12150/80000] lr: 1.218e-06, eta: 18:27:08, time: 0.935, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8302, decode.acc_seg: 58.7577, aux.loss_ce: 0.4022, aux.acc_seg: 56.5395, loss: 1.2324 2022-04-19 03:08:39,828 - mmseg - INFO - Iter [12200/80000] lr: 1.217e-06, eta: 18:26:08, time: 0.941, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8265, decode.acc_seg: 62.2394, aux.loss_ce: 0.4070, aux.acc_seg: 59.3985, loss: 1.2334 2022-04-19 03:09:26,364 - mmseg - INFO - Iter [12250/80000] lr: 1.216e-06, eta: 18:25:06, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8209, decode.acc_seg: 61.9054, aux.loss_ce: 0.3935, aux.acc_seg: 59.9250, loss: 1.2144 2022-04-19 03:10:12,765 - mmseg - INFO - Iter [12300/80000] lr: 1.215e-06, eta: 18:24:03, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8336, decode.acc_seg: 61.0780, aux.loss_ce: 0.4061, aux.acc_seg: 58.7804, loss: 1.2397 2022-04-19 03:10:59,753 - mmseg - INFO - Iter [12350/80000] lr: 1.214e-06, eta: 18:23:03, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8003, decode.acc_seg: 61.3920, aux.loss_ce: 0.3943, aux.acc_seg: 59.1820, loss: 1.1946 2022-04-19 03:11:46,493 - mmseg - INFO - Iter [12400/80000] lr: 1.213e-06, eta: 18:22:03, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8282, decode.acc_seg: 60.6420, aux.loss_ce: 0.4037, aux.acc_seg: 58.3420, loss: 1.2319 2022-04-19 03:12:33,186 - mmseg - INFO - Iter [12450/80000] lr: 1.212e-06, eta: 18:21:02, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8434, decode.acc_seg: 61.6486, aux.loss_ce: 0.4131, aux.acc_seg: 58.5710, loss: 1.2565 2022-04-19 03:13:20,355 - mmseg - INFO - Iter [12500/80000] lr: 1.211e-06, eta: 18:20:04, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8110, decode.acc_seg: 60.4540, aux.loss_ce: 0.3946, aux.acc_seg: 58.4672, loss: 1.2056 2022-04-19 03:14:07,072 - mmseg - INFO - Iter [12550/80000] lr: 1.211e-06, eta: 18:19:03, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7986, decode.acc_seg: 61.6575, aux.loss_ce: 0.3831, aux.acc_seg: 59.5254, loss: 1.1817 2022-04-19 03:14:53,530 - mmseg - INFO - Iter [12600/80000] lr: 1.210e-06, eta: 18:18:01, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8635, decode.acc_seg: 59.7761, aux.loss_ce: 0.4154, aux.acc_seg: 57.9376, loss: 1.2789 2022-04-19 03:15:40,300 - mmseg - INFO - Iter [12650/80000] lr: 1.209e-06, eta: 18:17:01, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8185, decode.acc_seg: 62.6732, aux.loss_ce: 0.3911, aux.acc_seg: 60.4513, loss: 1.2095 2022-04-19 03:16:26,840 - mmseg - INFO - Iter [12700/80000] lr: 1.208e-06, eta: 18:16:00, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8348, decode.acc_seg: 62.1506, aux.loss_ce: 0.3976, aux.acc_seg: 59.9257, loss: 1.2324 2022-04-19 03:17:13,786 - mmseg - INFO - Iter [12750/80000] lr: 1.207e-06, eta: 18:15:01, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8469, decode.acc_seg: 61.1219, aux.loss_ce: 0.4023, aux.acc_seg: 59.0831, loss: 1.2492 2022-04-19 03:18:00,529 - mmseg - INFO - Iter [12800/80000] lr: 1.206e-06, eta: 18:14:01, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8145, decode.acc_seg: 61.0265, aux.loss_ce: 0.3903, aux.acc_seg: 58.9667, loss: 1.2047 2022-04-19 03:18:47,507 - mmseg - INFO - Iter [12850/80000] lr: 1.205e-06, eta: 18:13:02, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8373, decode.acc_seg: 60.8134, aux.loss_ce: 0.4020, aux.acc_seg: 58.3711, loss: 1.2393 2022-04-19 03:19:34,131 - mmseg - INFO - Iter [12900/80000] lr: 1.204e-06, eta: 18:12:02, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8154, decode.acc_seg: 61.0421, aux.loss_ce: 0.3872, aux.acc_seg: 59.5885, loss: 1.2026 2022-04-19 03:20:21,108 - mmseg - INFO - Iter [12950/80000] lr: 1.203e-06, eta: 18:11:04, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7758, decode.acc_seg: 61.7209, aux.loss_ce: 0.3769, aux.acc_seg: 59.3530, loss: 1.1527 2022-04-19 03:21:07,451 - mmseg - INFO - Saving checkpoint at 13000 iterations 2022-04-19 03:21:24,162 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 03:21:24,165 - mmseg - INFO - Iter [13000/80000] lr: 1.202e-06, eta: 18:11:28, time: 1.259, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8086, decode.acc_seg: 60.7601, aux.loss_ce: 0.3873, aux.acc_seg: 58.3032, loss: 1.1959 2022-04-19 03:22:11,450 - mmseg - INFO - Iter [13050/80000] lr: 1.202e-06, eta: 18:10:31, time: 0.948, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8332, decode.acc_seg: 61.5124, aux.loss_ce: 0.3982, aux.acc_seg: 59.6211, loss: 1.2314 2022-04-19 03:22:58,445 - mmseg - INFO - Iter [13100/80000] lr: 1.201e-06, eta: 18:09:32, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8035, decode.acc_seg: 61.2247, aux.loss_ce: 0.3847, aux.acc_seg: 59.0249, loss: 1.1881 2022-04-19 03:23:45,360 - mmseg - INFO - Iter [13150/80000] lr: 1.200e-06, eta: 18:08:34, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8231, decode.acc_seg: 60.7405, aux.loss_ce: 0.3909, aux.acc_seg: 58.8038, loss: 1.2140 2022-04-19 03:24:32,294 - mmseg - INFO - Iter [13200/80000] lr: 1.199e-06, eta: 18:07:36, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7877, decode.acc_seg: 60.7410, aux.loss_ce: 0.3814, aux.acc_seg: 58.3254, loss: 1.1691 2022-04-19 03:25:18,850 - mmseg - INFO - Iter [13250/80000] lr: 1.198e-06, eta: 18:06:35, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7742, decode.acc_seg: 60.2635, aux.loss_ce: 0.3691, aux.acc_seg: 58.1621, loss: 1.1433 2022-04-19 03:26:05,611 - mmseg - INFO - Iter [13300/80000] lr: 1.197e-06, eta: 18:05:36, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7786, decode.acc_seg: 61.6882, aux.loss_ce: 0.3797, aux.acc_seg: 59.6354, loss: 1.1583 2022-04-19 03:26:52,255 - mmseg - INFO - Iter [13350/80000] lr: 1.196e-06, eta: 18:04:36, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7933, decode.acc_seg: 61.2205, aux.loss_ce: 0.3767, aux.acc_seg: 59.3134, loss: 1.1699 2022-04-19 03:27:39,228 - mmseg - INFO - Iter [13400/80000] lr: 1.195e-06, eta: 18:03:38, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8207, decode.acc_seg: 61.0574, aux.loss_ce: 0.3940, aux.acc_seg: 59.2117, loss: 1.2147 2022-04-19 03:28:25,681 - mmseg - INFO - Iter [13450/80000] lr: 1.194e-06, eta: 18:02:38, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8151, decode.acc_seg: 61.3249, aux.loss_ce: 0.3874, aux.acc_seg: 59.7954, loss: 1.2025 2022-04-19 03:29:12,272 - mmseg - INFO - Iter [13500/80000] lr: 1.194e-06, eta: 18:01:38, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8310, decode.acc_seg: 60.8811, aux.loss_ce: 0.3964, aux.acc_seg: 59.1580, loss: 1.2274 2022-04-19 03:29:58,736 - mmseg - INFO - Iter [13550/80000] lr: 1.193e-06, eta: 18:00:38, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8181, decode.acc_seg: 61.3165, aux.loss_ce: 0.3834, aux.acc_seg: 59.4528, loss: 1.2015 2022-04-19 03:30:45,446 - mmseg - INFO - Iter [13600/80000] lr: 1.192e-06, eta: 17:59:39, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8295, decode.acc_seg: 61.0503, aux.loss_ce: 0.3925, aux.acc_seg: 58.3074, loss: 1.2220 2022-04-19 03:31:31,958 - mmseg - INFO - Iter [13650/80000] lr: 1.191e-06, eta: 17:58:39, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8772, decode.acc_seg: 59.9567, aux.loss_ce: 0.4140, aux.acc_seg: 57.5243, loss: 1.2911 2022-04-19 03:32:18,680 - mmseg - INFO - Iter [13700/80000] lr: 1.190e-06, eta: 17:57:40, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7804, decode.acc_seg: 63.1182, aux.loss_ce: 0.3761, aux.acc_seg: 60.9194, loss: 1.1565 2022-04-19 03:33:05,248 - mmseg - INFO - Iter [13750/80000] lr: 1.189e-06, eta: 17:56:41, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8565, decode.acc_seg: 60.6071, aux.loss_ce: 0.3969, aux.acc_seg: 58.8492, loss: 1.2534 2022-04-19 03:33:52,020 - mmseg - INFO - Iter [13800/80000] lr: 1.188e-06, eta: 17:55:43, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7782, decode.acc_seg: 63.0823, aux.loss_ce: 0.3682, aux.acc_seg: 61.4527, loss: 1.1464 2022-04-19 03:34:39,012 - mmseg - INFO - Iter [13850/80000] lr: 1.187e-06, eta: 17:54:46, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8127, decode.acc_seg: 60.9764, aux.loss_ce: 0.3821, aux.acc_seg: 59.3168, loss: 1.1949 2022-04-19 03:35:25,723 - mmseg - INFO - Iter [13900/80000] lr: 1.186e-06, eta: 17:53:47, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7968, decode.acc_seg: 60.4565, aux.loss_ce: 0.3727, aux.acc_seg: 58.8973, loss: 1.1694 2022-04-19 03:36:12,438 - mmseg - INFO - Iter [13950/80000] lr: 1.185e-06, eta: 17:52:49, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8013, decode.acc_seg: 60.2072, aux.loss_ce: 0.3753, aux.acc_seg: 58.6392, loss: 1.1765 2022-04-19 03:36:58,899 - mmseg - INFO - Saving checkpoint at 14000 iterations 2022-04-19 03:37:12,254 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 03:37:12,255 - mmseg - INFO - Iter [14000/80000] lr: 1.185e-06, eta: 17:52:52, time: 1.196, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8359, decode.acc_seg: 60.4427, aux.loss_ce: 0.3951, aux.acc_seg: 58.6650, loss: 1.2310 2022-04-19 03:37:59,055 - mmseg - INFO - Iter [14050/80000] lr: 1.184e-06, eta: 17:51:54, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8285, decode.acc_seg: 61.4110, aux.loss_ce: 0.3853, aux.acc_seg: 59.5794, loss: 1.2138 2022-04-19 03:38:45,884 - mmseg - INFO - Iter [14100/80000] lr: 1.183e-06, eta: 17:50:57, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7917, decode.acc_seg: 61.9597, aux.loss_ce: 0.3792, aux.acc_seg: 59.8101, loss: 1.1709 2022-04-19 03:39:32,683 - mmseg - INFO - Iter [14150/80000] lr: 1.182e-06, eta: 17:49:59, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8305, decode.acc_seg: 61.5650, aux.loss_ce: 0.3918, aux.acc_seg: 59.7001, loss: 1.2223 2022-04-19 03:40:19,399 - mmseg - INFO - Iter [14200/80000] lr: 1.181e-06, eta: 17:49:01, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8109, decode.acc_seg: 61.1405, aux.loss_ce: 0.3835, aux.acc_seg: 59.0736, loss: 1.1944 2022-04-19 03:41:05,977 - mmseg - INFO - Iter [14250/80000] lr: 1.180e-06, eta: 17:48:02, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8212, decode.acc_seg: 61.0772, aux.loss_ce: 0.3837, aux.acc_seg: 59.3983, loss: 1.2050 2022-04-19 03:41:52,931 - mmseg - INFO - Iter [14300/80000] lr: 1.179e-06, eta: 17:47:05, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8003, decode.acc_seg: 60.7530, aux.loss_ce: 0.3782, aux.acc_seg: 58.8931, loss: 1.1785 2022-04-19 03:42:39,502 - mmseg - INFO - Iter [14350/80000] lr: 1.178e-06, eta: 17:46:06, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8108, decode.acc_seg: 59.7213, aux.loss_ce: 0.3800, aux.acc_seg: 58.0882, loss: 1.1907 2022-04-19 03:43:26,181 - mmseg - INFO - Iter [14400/80000] lr: 1.177e-06, eta: 17:45:08, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7862, decode.acc_seg: 60.6602, aux.loss_ce: 0.3672, aux.acc_seg: 58.7496, loss: 1.1534 2022-04-19 03:44:12,998 - mmseg - INFO - Iter [14450/80000] lr: 1.176e-06, eta: 17:44:11, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8194, decode.acc_seg: 62.5138, aux.loss_ce: 0.3819, aux.acc_seg: 60.8480, loss: 1.2013 2022-04-19 03:44:59,943 - mmseg - INFO - Iter [14500/80000] lr: 1.176e-06, eta: 17:43:14, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.8466, decode.acc_seg: 60.2282, aux.loss_ce: 0.3957, aux.acc_seg: 57.9577, loss: 1.2423 2022-04-19 03:45:46,865 - mmseg - INFO - Iter [14550/80000] lr: 1.175e-06, eta: 17:42:18, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8497, decode.acc_seg: 59.7208, aux.loss_ce: 0.3998, aux.acc_seg: 58.2375, loss: 1.2495 2022-04-19 03:46:33,824 - mmseg - INFO - Iter [14600/80000] lr: 1.174e-06, eta: 17:41:21, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7918, decode.acc_seg: 61.0553, aux.loss_ce: 0.3702, aux.acc_seg: 59.2958, loss: 1.1620 2022-04-19 03:47:20,694 - mmseg - INFO - Iter [14650/80000] lr: 1.173e-06, eta: 17:40:24, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8268, decode.acc_seg: 62.0595, aux.loss_ce: 0.3831, aux.acc_seg: 60.4569, loss: 1.2099 2022-04-19 03:48:07,331 - mmseg - INFO - Iter [14700/80000] lr: 1.172e-06, eta: 17:39:27, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7934, decode.acc_seg: 60.8487, aux.loss_ce: 0.3781, aux.acc_seg: 58.8074, loss: 1.1714 2022-04-19 03:48:53,996 - mmseg - INFO - Iter [14750/80000] lr: 1.171e-06, eta: 17:38:29, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8077, decode.acc_seg: 60.9654, aux.loss_ce: 0.3770, aux.acc_seg: 58.8848, loss: 1.1846 2022-04-19 03:49:43,588 - mmseg - INFO - Iter [14800/80000] lr: 1.170e-06, eta: 17:37:45, time: 0.992, data_time: 0.061, memory: 73037, decode.loss_ce: 0.7970, decode.acc_seg: 61.9908, aux.loss_ce: 0.3693, aux.acc_seg: 60.9996, loss: 1.1663 2022-04-19 03:50:30,267 - mmseg - INFO - Iter [14850/80000] lr: 1.169e-06, eta: 17:36:47, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8055, decode.acc_seg: 61.9206, aux.loss_ce: 0.3799, aux.acc_seg: 60.4058, loss: 1.1854 2022-04-19 03:51:16,931 - mmseg - INFO - Iter [14900/80000] lr: 1.168e-06, eta: 17:35:50, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7490, decode.acc_seg: 62.0270, aux.loss_ce: 0.3520, aux.acc_seg: 60.7337, loss: 1.1010 2022-04-19 03:52:03,606 - mmseg - INFO - Iter [14950/80000] lr: 1.167e-06, eta: 17:34:52, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8019, decode.acc_seg: 61.4018, aux.loss_ce: 0.3766, aux.acc_seg: 59.5384, loss: 1.1784 2022-04-19 03:52:50,130 - mmseg - INFO - Saving checkpoint at 15000 iterations 2022-04-19 03:53:03,653 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 03:53:03,653 - mmseg - INFO - Iter [15000/80000] lr: 1.167e-06, eta: 17:34:53, time: 1.201, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7734, decode.acc_seg: 62.4321, aux.loss_ce: 0.3681, aux.acc_seg: 60.4305, loss: 1.1414 2022-04-19 03:53:50,434 - mmseg - INFO - Iter [15050/80000] lr: 1.166e-06, eta: 17:33:56, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7694, decode.acc_seg: 63.1593, aux.loss_ce: 0.3712, aux.acc_seg: 61.0391, loss: 1.1407 2022-04-19 03:54:37,291 - mmseg - INFO - Iter [15100/80000] lr: 1.165e-06, eta: 17:32:59, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7489, decode.acc_seg: 62.7343, aux.loss_ce: 0.3527, aux.acc_seg: 61.2825, loss: 1.1017 2022-04-19 03:55:24,117 - mmseg - INFO - Iter [15150/80000] lr: 1.164e-06, eta: 17:32:03, time: 0.938, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8181, decode.acc_seg: 60.6095, aux.loss_ce: 0.3861, aux.acc_seg: 58.6242, loss: 1.2042 2022-04-19 03:56:11,288 - mmseg - INFO - Iter [15200/80000] lr: 1.163e-06, eta: 17:31:08, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7705, decode.acc_seg: 62.6462, aux.loss_ce: 0.3674, aux.acc_seg: 61.0588, loss: 1.1379 2022-04-19 03:56:58,675 - mmseg - INFO - Iter [15250/80000] lr: 1.162e-06, eta: 17:30:14, time: 0.949, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8166, decode.acc_seg: 62.0110, aux.loss_ce: 0.3840, aux.acc_seg: 60.2193, loss: 1.2006 2022-04-19 03:57:45,541 - mmseg - INFO - Iter [15300/80000] lr: 1.161e-06, eta: 17:29:18, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7436, decode.acc_seg: 62.5214, aux.loss_ce: 0.3576, aux.acc_seg: 61.0057, loss: 1.1012 2022-04-19 03:58:32,002 - mmseg - INFO - Iter [15350/80000] lr: 1.160e-06, eta: 17:28:20, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7936, decode.acc_seg: 62.6248, aux.loss_ce: 0.3754, aux.acc_seg: 60.9414, loss: 1.1690 2022-04-19 03:59:18,798 - mmseg - INFO - Iter [15400/80000] lr: 1.159e-06, eta: 17:27:23, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7896, decode.acc_seg: 62.6333, aux.loss_ce: 0.3689, aux.acc_seg: 60.6386, loss: 1.1585 2022-04-19 04:00:05,701 - mmseg - INFO - Iter [15450/80000] lr: 1.159e-06, eta: 17:26:28, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7743, decode.acc_seg: 63.1800, aux.loss_ce: 0.3687, aux.acc_seg: 61.3876, loss: 1.1429 2022-04-19 04:00:52,304 - mmseg - INFO - Iter [15500/80000] lr: 1.158e-06, eta: 17:25:30, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8179, decode.acc_seg: 61.1982, aux.loss_ce: 0.3855, aux.acc_seg: 59.3803, loss: 1.2034 2022-04-19 04:01:39,184 - mmseg - INFO - Iter [15550/80000] lr: 1.157e-06, eta: 17:24:35, time: 0.939, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7643, decode.acc_seg: 61.7364, aux.loss_ce: 0.3628, aux.acc_seg: 59.8392, loss: 1.1270 2022-04-19 04:02:26,139 - mmseg - INFO - Iter [15600/80000] lr: 1.156e-06, eta: 17:23:39, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7847, decode.acc_seg: 60.7550, aux.loss_ce: 0.3716, aux.acc_seg: 58.8688, loss: 1.1563 2022-04-19 04:03:13,260 - mmseg - INFO - Iter [15650/80000] lr: 1.155e-06, eta: 17:22:44, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7798, decode.acc_seg: 61.9118, aux.loss_ce: 0.3679, aux.acc_seg: 59.6638, loss: 1.1477 2022-04-19 04:04:00,234 - mmseg - INFO - Iter [15700/80000] lr: 1.154e-06, eta: 17:21:49, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7440, decode.acc_seg: 62.1934, aux.loss_ce: 0.3517, aux.acc_seg: 60.4852, loss: 1.0957 2022-04-19 04:04:46,947 - mmseg - INFO - Iter [15750/80000] lr: 1.153e-06, eta: 17:20:53, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7859, decode.acc_seg: 61.1248, aux.loss_ce: 0.3624, aux.acc_seg: 60.0605, loss: 1.1484 2022-04-19 04:05:34,239 - mmseg - INFO - Iter [15800/80000] lr: 1.152e-06, eta: 17:19:59, time: 0.946, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7667, decode.acc_seg: 62.5861, aux.loss_ce: 0.3588, aux.acc_seg: 60.8294, loss: 1.1254 2022-04-19 04:06:21,445 - mmseg - INFO - Iter [15850/80000] lr: 1.151e-06, eta: 17:19:04, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7985, decode.acc_seg: 60.7151, aux.loss_ce: 0.3828, aux.acc_seg: 58.0560, loss: 1.1813 2022-04-19 04:07:08,419 - mmseg - INFO - Iter [15900/80000] lr: 1.150e-06, eta: 17:18:09, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8013, decode.acc_seg: 60.2443, aux.loss_ce: 0.3704, aux.acc_seg: 58.4895, loss: 1.1717 2022-04-19 04:07:55,419 - mmseg - INFO - Iter [15950/80000] lr: 1.150e-06, eta: 17:17:14, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7940, decode.acc_seg: 61.2240, aux.loss_ce: 0.3663, aux.acc_seg: 60.0825, loss: 1.1603 2022-04-19 04:08:42,070 - mmseg - INFO - Saving checkpoint at 16000 iterations 2022-04-19 04:08:52,456 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 04:08:52,457 - mmseg - INFO - Iter [16000/80000] lr: 1.149e-06, eta: 17:17:00, time: 1.141, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7953, decode.acc_seg: 62.2242, aux.loss_ce: 0.3712, aux.acc_seg: 60.4323, loss: 1.1665 2022-04-19 04:12:47,329 - mmseg - INFO - per class results: 2022-04-19 04:12:47,343 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.0 | 94.71 | | bicycle | 66.93 | 88.32 | | car | 64.27 | 81.17 | | motorcycle | 83.58 | 91.23 | | airplane | 82.59 | 94.83 | | bus | 83.8 | 91.91 | | train | 83.73 | 94.28 | | truck | 65.35 | 85.95 | | boat | 64.66 | 84.34 | | traffic light | 63.66 | 85.64 | | fire hydrant | 84.55 | 97.24 | | stop sign | 90.33 | 97.1 | | parking meter | 77.08 | 87.16 | | bench | 52.5 | 72.31 | | bird | 82.48 | 90.65 | | cat | 81.87 | 88.05 | | dog | 78.45 | 89.08 | | horse | 85.06 | 94.8 | | sheep | 86.59 | 96.75 | | cow | 87.15 | 92.64 | | elephant | 92.26 | 97.19 | | bear | 88.54 | 97.97 | | zebra | 91.01 | 95.57 | | giraffe | 85.81 | 93.79 | | backpack | 35.57 | 60.98 | | umbrella | 84.49 | 93.56 | | handbag | 36.36 | 51.96 | | tie | 4.99 | 5.35 | | suitcase | 81.61 | 92.25 | | frisbee | 73.44 | 88.29 | | skis | 36.54 | 46.41 | | snowboard | 57.39 | 72.04 | | sports ball | 52.75 | 59.18 | | kite | 69.02 | 87.26 | | baseball bat | 52.88 | 68.45 | | baseball glove | 73.07 | 86.59 | | skateboard | 78.55 | 89.37 | | surfboard | 79.4 | 90.5 | | tennis racket | 82.04 | 92.07 | | bottle | 50.38 | 72.65 | | wine glass | 57.72 | 82.42 | | cup | 53.53 | 76.11 | | fork | 37.27 | 48.17 | | knife | 32.55 | 43.04 | | spoon | 30.03 | 36.06 | | bowl | 47.02 | 65.89 | | banana | 68.97 | 93.59 | | apple | 56.69 | 78.32 | | sandwich | 53.28 | 70.9 | | orange | 74.15 | 85.31 | | broccoli | 54.08 | 85.47 | | carrot | 56.86 | 69.73 | | hot dog | 58.23 | 71.57 | | pizza | 77.33 | 95.45 | | donut | 75.0 | 89.23 | | cake | 69.73 | 86.25 | | chair | 49.37 | 73.57 | | couch | 54.71 | 84.68 | | potted plant | 30.94 | 47.05 | | bed | 62.52 | 82.35 | | dining table | 46.77 | 73.48 | | toilet | 81.9 | 94.88 | | tv | 71.48 | 87.49 | | laptop | 74.98 | 93.44 | | mouse | 69.02 | 76.57 | | remote | 57.07 | 73.96 | | keyboard | 61.17 | 73.25 | | cell phone | 74.0 | 90.45 | | microwave | 66.11 | 79.33 | | oven | 54.52 | 85.31 | | toaster | 0.0 | 0.0 | | sink | 56.26 | 87.32 | | refrigerator | 75.57 | 92.94 | | book | 50.98 | 74.63 | | clock | 68.22 | 88.65 | | vase | 59.06 | 84.02 | | scissors | 70.12 | 93.67 | | teddy bear | 79.29 | 93.61 | | hair drier | 0.0 | 0.0 | | toothbrush | 42.11 | 74.8 | | banner | 30.55 | 67.42 | | blanket | 0.26 | 0.27 | | branch | 20.12 | 24.66 | | bridge | 37.1 | 52.77 | | building-other | 54.47 | 67.96 | | bush | 28.83 | 37.08 | | cabinet | 56.1 | 77.69 | | cage | 26.41 | 53.13 | | cardboard | 48.05 | 64.98 | | carpet | 53.23 | 81.03 | | ceiling-other | 63.98 | 86.21 | | ceiling-tile | 0.0 | 0.0 | | cloth | 1.21 | 1.21 | | clothes | 12.79 | 14.3 | | clouds | 50.56 | 67.02 | | counter | 28.9 | 54.16 | | cupboard | 0.0 | 0.0 | | curtain | 65.87 | 86.21 | | desk-stuff | 43.84 | 64.23 | | dirt | 42.7 | 62.71 | | door-stuff | 45.69 | 71.58 | | fence | 28.8 | 43.45 | | floor-marble | 5.75 | 6.52 | | floor-other | 20.37 | 25.5 | | floor-stone | 4.02 | 4.91 | | floor-tile | 63.5 | 76.73 | | floor-wood | 58.88 | 83.91 | | flower | 40.7 | 57.67 | | fog | 13.96 | 16.15 | | food-other | 30.14 | 38.94 | | fruit | 42.04 | 57.09 | | furniture-other | 14.55 | 17.43 | | grass | 69.46 | 84.44 | | gravel | 28.74 | 40.86 | | ground-other | 5.25 | 5.93 | | hill | 13.26 | 16.41 | | house | 30.48 | 40.43 | | leaves | 18.29 | 20.08 | | light | 40.19 | 55.32 | | mat | 0.0 | 0.0 | | metal | 31.14 | 39.41 | | mirror-stuff | 45.59 | 57.6 | | moss | 0.0 | 0.0 | | mountain | 53.34 | 74.78 | | mud | 5.79 | 8.78 | | napkin | 1.59 | 1.61 | | net | 45.43 | 65.04 | | paper | 29.52 | 36.61 | | pavement | 50.28 | 67.28 | | pillow | 0.0 | 0.0 | | plant-other | 18.56 | 29.22 | | plastic | 18.34 | 22.11 | | platform | 26.17 | 43.28 | | playingfield | 70.0 | 90.03 | | railing | 3.99 | 4.52 | | railroad | 59.26 | 83.54 | | river | 49.35 | 71.73 | | road | 64.95 | 82.25 | | rock | 48.67 | 77.59 | | roof | 20.11 | 24.46 | | rug | 37.73 | 60.19 | | salad | 0.0 | 0.0 | | sand | 65.09 | 72.5 | | sea | 84.63 | 93.43 | | shelf | 34.57 | 50.57 | | sky-other | 71.75 | 86.29 | | skyscraper | 41.25 | 59.91 | | snow | 90.23 | 96.89 | | solid-other | 0.0 | 0.0 | | stairs | 25.85 | 50.46 | | stone | 1.01 | 1.09 | | straw | 27.77 | 33.17 | | structural-other | 0.34 | 0.36 | | table | 20.1 | 25.73 | | tent | 10.88 | 13.9 | | textile-other | 12.26 | 16.04 | | towel | 32.09 | 39.85 | | tree | 72.62 | 89.27 | | vegetable | 38.49 | 51.21 | | wall-brick | 45.08 | 65.37 | | wall-concrete | 60.53 | 82.76 | | wall-other | 19.76 | 27.34 | | wall-panel | 0.64 | 0.69 | | wall-stone | 28.1 | 36.21 | | wall-tile | 65.16 | 84.53 | | wall-wood | 38.85 | 59.19 | | water-other | 22.72 | 28.86 | | waterdrops | 0.0 | 0.0 | | window-blind | 52.44 | 65.74 | | window-other | 46.62 | 75.44 | | wood | 26.15 | 40.84 | +------------------+-------+-------+ 2022-04-19 04:12:47,344 - mmseg - INFO - Summary: 2022-04-19 04:12:47,344 - mmseg - INFO - +------+-------+-------+ | aAcc | mIoU | mAcc | +------+-------+-------+ | 72.4 | 47.19 | 60.45 | +------+-------+-------+ 2022-04-19 04:12:47,359 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 04:12:47,359 - mmseg - INFO - Iter(val) [625] aAcc: 0.7240, mIoU: 0.4719, mAcc: 0.6045, IoU.person: 0.8600, IoU.bicycle: 0.6693, IoU.car: 0.6427, IoU.motorcycle: 0.8358, IoU.airplane: 0.8259, IoU.bus: 0.8380, IoU.train: 0.8373, IoU.truck: 0.6535, IoU.boat: 0.6466, IoU.traffic light: 0.6366, IoU.fire hydrant: 0.8455, IoU.stop sign: 0.9033, IoU.parking meter: 0.7708, IoU.bench: 0.5250, IoU.bird: 0.8248, IoU.cat: 0.8187, IoU.dog: 0.7845, IoU.horse: 0.8506, IoU.sheep: 0.8659, IoU.cow: 0.8715, IoU.elephant: 0.9226, IoU.bear: 0.8854, IoU.zebra: 0.9101, IoU.giraffe: 0.8581, IoU.backpack: 0.3557, IoU.umbrella: 0.8449, IoU.handbag: 0.3636, IoU.tie: 0.0499, IoU.suitcase: 0.8161, IoU.frisbee: 0.7344, IoU.skis: 0.3654, IoU.snowboard: 0.5739, IoU.sports ball: 0.5275, IoU.kite: 0.6902, IoU.baseball bat: 0.5288, IoU.baseball glove: 0.7307, IoU.skateboard: 0.7855, IoU.surfboard: 0.7940, IoU.tennis racket: 0.8204, IoU.bottle: 0.5038, IoU.wine glass: 0.5772, IoU.cup: 0.5353, IoU.fork: 0.3727, IoU.knife: 0.3255, IoU.spoon: 0.3003, IoU.bowl: 0.4702, IoU.banana: 0.6897, IoU.apple: 0.5669, IoU.sandwich: 0.5328, IoU.orange: 0.7415, IoU.broccoli: 0.5408, IoU.carrot: 0.5686, IoU.hot dog: 0.5823, IoU.pizza: 0.7733, IoU.donut: 0.7500, IoU.cake: 0.6973, IoU.chair: 0.4937, IoU.couch: 0.5471, IoU.potted plant: 0.3094, IoU.bed: 0.6252, IoU.dining table: 0.4677, IoU.toilet: 0.8190, IoU.tv: 0.7148, IoU.laptop: 0.7498, IoU.mouse: 0.6902, IoU.remote: 0.5707, IoU.keyboard: 0.6117, IoU.cell phone: 0.7400, IoU.microwave: 0.6611, IoU.oven: 0.5452, IoU.toaster: 0.0000, IoU.sink: 0.5626, IoU.refrigerator: 0.7557, IoU.book: 0.5098, IoU.clock: 0.6822, IoU.vase: 0.5906, IoU.scissors: 0.7012, IoU.teddy bear: 0.7929, IoU.hair drier: 0.0000, IoU.toothbrush: 0.4211, IoU.banner: 0.3055, IoU.blanket: 0.0026, IoU.branch: 0.2012, IoU.bridge: 0.3710, IoU.building-other: 0.5447, IoU.bush: 0.2883, IoU.cabinet: 0.5610, IoU.cage: 0.2641, IoU.cardboard: 0.4805, IoU.carpet: 0.5323, IoU.ceiling-other: 0.6398, IoU.ceiling-tile: 0.0000, IoU.cloth: 0.0121, IoU.clothes: 0.1279, IoU.clouds: 0.5056, IoU.counter: 0.2890, IoU.cupboard: 0.0000, IoU.curtain: 0.6587, IoU.desk-stuff: 0.4384, IoU.dirt: 0.4270, IoU.door-stuff: 0.4569, IoU.fence: 0.2880, IoU.floor-marble: 0.0575, IoU.floor-other: 0.2037, IoU.floor-stone: 0.0402, IoU.floor-tile: 0.6350, IoU.floor-wood: 0.5888, IoU.flower: 0.4070, IoU.fog: 0.1396, IoU.food-other: 0.3014, IoU.fruit: 0.4204, IoU.furniture-other: 0.1455, IoU.grass: 0.6946, IoU.gravel: 0.2874, IoU.ground-other: 0.0525, IoU.hill: 0.1326, IoU.house: 0.3048, IoU.leaves: 0.1829, IoU.light: 0.4019, IoU.mat: 0.0000, IoU.metal: 0.3114, IoU.mirror-stuff: 0.4559, IoU.moss: 0.0000, IoU.mountain: 0.5334, IoU.mud: 0.0579, IoU.napkin: 0.0159, IoU.net: 0.4543, IoU.paper: 0.2952, IoU.pavement: 0.5028, IoU.pillow: 0.0000, IoU.plant-other: 0.1856, IoU.plastic: 0.1834, IoU.platform: 0.2617, IoU.playingfield: 0.7000, IoU.railing: 0.0399, IoU.railroad: 0.5926, IoU.river: 0.4935, IoU.road: 0.6495, IoU.rock: 0.4867, IoU.roof: 0.2011, IoU.rug: 0.3773, IoU.salad: 0.0000, IoU.sand: 0.6509, IoU.sea: 0.8463, IoU.shelf: 0.3457, IoU.sky-other: 0.7175, IoU.skyscraper: 0.4125, IoU.snow: 0.9023, IoU.solid-other: 0.0000, IoU.stairs: 0.2585, IoU.stone: 0.0101, IoU.straw: 0.2777, IoU.structural-other: 0.0034, IoU.table: 0.2010, IoU.tent: 0.1088, IoU.textile-other: 0.1226, IoU.towel: 0.3209, IoU.tree: 0.7262, IoU.vegetable: 0.3849, IoU.wall-brick: 0.4508, IoU.wall-concrete: 0.6053, IoU.wall-other: 0.1976, IoU.wall-panel: 0.0064, IoU.wall-stone: 0.2810, IoU.wall-tile: 0.6516, IoU.wall-wood: 0.3885, IoU.water-other: 0.2272, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5244, IoU.window-other: 0.4662, IoU.wood: 0.2615, Acc.person: 0.9471, Acc.bicycle: 0.8832, Acc.car: 0.8117, Acc.motorcycle: 0.9123, Acc.airplane: 0.9483, Acc.bus: 0.9191, Acc.train: 0.9428, Acc.truck: 0.8595, Acc.boat: 0.8434, Acc.traffic light: 0.8564, Acc.fire hydrant: 0.9724, Acc.stop sign: 0.9710, Acc.parking meter: 0.8716, Acc.bench: 0.7231, Acc.bird: 0.9065, Acc.cat: 0.8805, Acc.dog: 0.8908, Acc.horse: 0.9480, Acc.sheep: 0.9675, Acc.cow: 0.9264, Acc.elephant: 0.9719, Acc.bear: 0.9797, Acc.zebra: 0.9557, Acc.giraffe: 0.9379, Acc.backpack: 0.6098, Acc.umbrella: 0.9356, Acc.handbag: 0.5196, Acc.tie: 0.0535, Acc.suitcase: 0.9225, Acc.frisbee: 0.8829, Acc.skis: 0.4641, Acc.snowboard: 0.7204, Acc.sports ball: 0.5918, Acc.kite: 0.8726, Acc.baseball bat: 0.6845, Acc.baseball glove: 0.8659, Acc.skateboard: 0.8937, Acc.surfboard: 0.9050, Acc.tennis racket: 0.9207, Acc.bottle: 0.7265, Acc.wine glass: 0.8242, Acc.cup: 0.7611, Acc.fork: 0.4817, Acc.knife: 0.4304, Acc.spoon: 0.3606, Acc.bowl: 0.6589, Acc.banana: 0.9359, Acc.apple: 0.7832, Acc.sandwich: 0.7090, Acc.orange: 0.8531, Acc.broccoli: 0.8547, Acc.carrot: 0.6973, Acc.hot dog: 0.7157, Acc.pizza: 0.9545, Acc.donut: 0.8923, Acc.cake: 0.8625, Acc.chair: 0.7357, Acc.couch: 0.8468, Acc.potted plant: 0.4705, Acc.bed: 0.8235, Acc.dining table: 0.7348, Acc.toilet: 0.9488, Acc.tv: 0.8749, Acc.laptop: 0.9344, Acc.mouse: 0.7657, Acc.remote: 0.7396, Acc.keyboard: 0.7325, Acc.cell phone: 0.9045, Acc.microwave: 0.7933, Acc.oven: 0.8531, Acc.toaster: 0.0000, Acc.sink: 0.8732, Acc.refrigerator: 0.9294, Acc.book: 0.7463, Acc.clock: 0.8865, Acc.vase: 0.8402, Acc.scissors: 0.9367, Acc.teddy bear: 0.9361, Acc.hair drier: 0.0000, Acc.toothbrush: 0.7480, Acc.banner: 0.6742, Acc.blanket: 0.0027, Acc.branch: 0.2466, Acc.bridge: 0.5277, Acc.building-other: 0.6796, Acc.bush: 0.3708, Acc.cabinet: 0.7769, Acc.cage: 0.5313, Acc.cardboard: 0.6498, Acc.carpet: 0.8103, Acc.ceiling-other: 0.8621, Acc.ceiling-tile: 0.0000, Acc.cloth: 0.0121, Acc.clothes: 0.1430, Acc.clouds: 0.6702, Acc.counter: 0.5416, Acc.cupboard: 0.0000, Acc.curtain: 0.8621, Acc.desk-stuff: 0.6423, Acc.dirt: 0.6271, Acc.door-stuff: 0.7158, Acc.fence: 0.4345, Acc.floor-marble: 0.0652, Acc.floor-other: 0.2550, Acc.floor-stone: 0.0491, Acc.floor-tile: 0.7673, Acc.floor-wood: 0.8391, Acc.flower: 0.5767, Acc.fog: 0.1615, Acc.food-other: 0.3894, Acc.fruit: 0.5709, Acc.furniture-other: 0.1743, Acc.grass: 0.8444, Acc.gravel: 0.4086, Acc.ground-other: 0.0593, Acc.hill: 0.1641, Acc.house: 0.4043, Acc.leaves: 0.2008, Acc.light: 0.5532, Acc.mat: 0.0000, Acc.metal: 0.3941, Acc.mirror-stuff: 0.5760, Acc.moss: 0.0000, Acc.mountain: 0.7478, Acc.mud: 0.0878, Acc.napkin: 0.0161, Acc.net: 0.6504, Acc.paper: 0.3661, Acc.pavement: 0.6728, Acc.pillow: 0.0000, Acc.plant-other: 0.2922, Acc.plastic: 0.2211, Acc.platform: 0.4328, Acc.playingfield: 0.9003, Acc.railing: 0.0452, Acc.railroad: 0.8354, Acc.river: 0.7173, Acc.road: 0.8225, Acc.rock: 0.7759, Acc.roof: 0.2446, Acc.rug: 0.6019, Acc.salad: 0.0000, Acc.sand: 0.7250, Acc.sea: 0.9343, Acc.shelf: 0.5057, Acc.sky-other: 0.8629, Acc.skyscraper: 0.5991, Acc.snow: 0.9689, Acc.solid-other: 0.0000, Acc.stairs: 0.5046, Acc.stone: 0.0109, Acc.straw: 0.3317, Acc.structural-other: 0.0036, Acc.table: 0.2573, Acc.tent: 0.1390, Acc.textile-other: 0.1604, Acc.towel: 0.3985, Acc.tree: 0.8927, Acc.vegetable: 0.5121, Acc.wall-brick: 0.6537, Acc.wall-concrete: 0.8276, Acc.wall-other: 0.2734, Acc.wall-panel: 0.0069, Acc.wall-stone: 0.3621, Acc.wall-tile: 0.8453, Acc.wall-wood: 0.5919, Acc.water-other: 0.2886, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6574, Acc.window-other: 0.7544, Acc.wood: 0.4084 2022-04-19 04:13:33,757 - mmseg - INFO - Iter [16050/80000] lr: 1.148e-06, eta: 17:31:38, time: 5.626, data_time: 4.703, memory: 73037, decode.loss_ce: 0.7901, decode.acc_seg: 62.1919, aux.loss_ce: 0.3753, aux.acc_seg: 60.5946, loss: 1.1654 2022-04-19 04:14:20,117 - mmseg - INFO - Iter [16100/80000] lr: 1.147e-06, eta: 17:30:37, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7794, decode.acc_seg: 62.6236, aux.loss_ce: 0.3671, aux.acc_seg: 60.9837, loss: 1.1465 2022-04-19 04:15:06,618 - mmseg - INFO - Iter [16150/80000] lr: 1.146e-06, eta: 17:29:37, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8067, decode.acc_seg: 61.7173, aux.loss_ce: 0.3707, aux.acc_seg: 60.3394, loss: 1.1774 2022-04-19 04:15:53,068 - mmseg - INFO - Iter [16200/80000] lr: 1.145e-06, eta: 17:28:36, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7592, decode.acc_seg: 62.5696, aux.loss_ce: 0.3606, aux.acc_seg: 60.6585, loss: 1.1198 2022-04-19 04:16:39,700 - mmseg - INFO - Iter [16250/80000] lr: 1.144e-06, eta: 17:27:36, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7430, decode.acc_seg: 63.3429, aux.loss_ce: 0.3494, aux.acc_seg: 62.0494, loss: 1.0924 2022-04-19 04:17:26,663 - mmseg - INFO - Iter [16300/80000] lr: 1.143e-06, eta: 17:26:38, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7796, decode.acc_seg: 60.5477, aux.loss_ce: 0.3567, aux.acc_seg: 59.1944, loss: 1.1362 2022-04-19 04:18:13,691 - mmseg - INFO - Iter [16350/80000] lr: 1.142e-06, eta: 17:25:40, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7438, decode.acc_seg: 61.7807, aux.loss_ce: 0.3481, aux.acc_seg: 60.6194, loss: 1.0919 2022-04-19 04:19:00,418 - mmseg - INFO - Iter [16400/80000] lr: 1.141e-06, eta: 17:24:40, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7874, decode.acc_seg: 61.3220, aux.loss_ce: 0.3666, aux.acc_seg: 59.7074, loss: 1.1540 2022-04-19 04:19:47,009 - mmseg - INFO - Iter [16450/80000] lr: 1.141e-06, eta: 17:23:41, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7854, decode.acc_seg: 61.4009, aux.loss_ce: 0.3576, aux.acc_seg: 60.3427, loss: 1.1430 2022-04-19 04:20:33,639 - mmseg - INFO - Iter [16500/80000] lr: 1.140e-06, eta: 17:22:41, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.8194, decode.acc_seg: 60.1555, aux.loss_ce: 0.3760, aux.acc_seg: 58.6637, loss: 1.1954 2022-04-19 04:21:20,285 - mmseg - INFO - Iter [16550/80000] lr: 1.139e-06, eta: 17:21:42, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7452, decode.acc_seg: 62.5446, aux.loss_ce: 0.3499, aux.acc_seg: 60.4530, loss: 1.0951 2022-04-19 04:22:06,941 - mmseg - INFO - Iter [16600/80000] lr: 1.138e-06, eta: 17:20:43, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7381, decode.acc_seg: 63.4726, aux.loss_ce: 0.3428, aux.acc_seg: 62.3038, loss: 1.0809 2022-04-19 04:22:53,325 - mmseg - INFO - Iter [16650/80000] lr: 1.137e-06, eta: 17:19:43, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8077, decode.acc_seg: 60.9920, aux.loss_ce: 0.3790, aux.acc_seg: 59.2220, loss: 1.1867 2022-04-19 04:23:39,887 - mmseg - INFO - Iter [16700/80000] lr: 1.136e-06, eta: 17:18:43, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7394, decode.acc_seg: 63.9184, aux.loss_ce: 0.3424, aux.acc_seg: 62.6051, loss: 1.0818 2022-04-19 04:24:26,271 - mmseg - INFO - Iter [16750/80000] lr: 1.135e-06, eta: 17:17:43, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7880, decode.acc_seg: 61.7349, aux.loss_ce: 0.3656, aux.acc_seg: 60.2462, loss: 1.1537 2022-04-19 04:25:12,892 - mmseg - INFO - Iter [16800/80000] lr: 1.134e-06, eta: 17:16:44, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7512, decode.acc_seg: 63.2110, aux.loss_ce: 0.3504, aux.acc_seg: 61.9255, loss: 1.1016 2022-04-19 04:25:59,447 - mmseg - INFO - Iter [16850/80000] lr: 1.133e-06, eta: 17:15:45, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7899, decode.acc_seg: 62.6461, aux.loss_ce: 0.3656, aux.acc_seg: 60.6600, loss: 1.1555 2022-04-19 04:26:46,099 - mmseg - INFO - Iter [16900/80000] lr: 1.133e-06, eta: 17:14:46, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8080, decode.acc_seg: 62.3457, aux.loss_ce: 0.3732, aux.acc_seg: 60.9972, loss: 1.1812 2022-04-19 04:27:32,841 - mmseg - INFO - Iter [16950/80000] lr: 1.132e-06, eta: 17:13:48, time: 0.935, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7502, decode.acc_seg: 63.0471, aux.loss_ce: 0.3495, aux.acc_seg: 61.1621, loss: 1.0996 2022-04-19 04:28:19,337 - mmseg - INFO - Saving checkpoint at 17000 iterations 2022-04-19 04:28:31,380 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 04:28:31,394 - mmseg - INFO - Iter [17000/80000] lr: 1.131e-06, eta: 17:13:33, time: 1.170, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8140, decode.acc_seg: 59.4973, aux.loss_ce: 0.3749, aux.acc_seg: 58.2925, loss: 1.1889 2022-04-19 04:29:18,048 - mmseg - INFO - Iter [17050/80000] lr: 1.130e-06, eta: 17:12:35, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7943, decode.acc_seg: 61.7589, aux.loss_ce: 0.3659, aux.acc_seg: 60.4440, loss: 1.1602 2022-04-19 04:30:04,671 - mmseg - INFO - Iter [17100/80000] lr: 1.129e-06, eta: 17:11:36, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7934, decode.acc_seg: 63.7430, aux.loss_ce: 0.3611, aux.acc_seg: 62.2042, loss: 1.1545 2022-04-19 04:30:51,125 - mmseg - INFO - Iter [17150/80000] lr: 1.128e-06, eta: 17:10:37, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7976, decode.acc_seg: 62.0664, aux.loss_ce: 0.3614, aux.acc_seg: 60.8828, loss: 1.1590 2022-04-19 04:31:38,001 - mmseg - INFO - Iter [17200/80000] lr: 1.127e-06, eta: 17:09:39, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7643, decode.acc_seg: 63.0980, aux.loss_ce: 0.3532, aux.acc_seg: 61.4012, loss: 1.1175 2022-04-19 04:32:24,627 - mmseg - INFO - Iter [17250/80000] lr: 1.126e-06, eta: 17:08:41, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7662, decode.acc_seg: 60.9518, aux.loss_ce: 0.3580, aux.acc_seg: 59.3881, loss: 1.1242 2022-04-19 04:33:11,342 - mmseg - INFO - Iter [17300/80000] lr: 1.125e-06, eta: 17:07:43, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7781, decode.acc_seg: 62.9218, aux.loss_ce: 0.3635, aux.acc_seg: 61.0650, loss: 1.1416 2022-04-19 04:33:57,855 - mmseg - INFO - Iter [17350/80000] lr: 1.124e-06, eta: 17:06:44, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7740, decode.acc_seg: 62.4472, aux.loss_ce: 0.3561, aux.acc_seg: 60.8310, loss: 1.1301 2022-04-19 04:34:44,534 - mmseg - INFO - Iter [17400/80000] lr: 1.124e-06, eta: 17:05:46, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7407, decode.acc_seg: 61.6508, aux.loss_ce: 0.3430, aux.acc_seg: 60.4423, loss: 1.0837 2022-04-19 04:35:31,187 - mmseg - INFO - Iter [17450/80000] lr: 1.123e-06, eta: 17:04:48, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7833, decode.acc_seg: 61.5485, aux.loss_ce: 0.3614, aux.acc_seg: 60.0891, loss: 1.1446 2022-04-19 04:36:18,020 - mmseg - INFO - Iter [17500/80000] lr: 1.122e-06, eta: 17:03:50, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8181, decode.acc_seg: 61.3965, aux.loss_ce: 0.3764, aux.acc_seg: 59.3321, loss: 1.1945 2022-04-19 04:37:04,903 - mmseg - INFO - Iter [17550/80000] lr: 1.121e-06, eta: 17:02:53, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7862, decode.acc_seg: 62.4985, aux.loss_ce: 0.3640, aux.acc_seg: 60.8415, loss: 1.1502 2022-04-19 04:37:51,711 - mmseg - INFO - Iter [17600/80000] lr: 1.120e-06, eta: 17:01:56, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7684, decode.acc_seg: 62.9110, aux.loss_ce: 0.3566, aux.acc_seg: 61.1700, loss: 1.1250 2022-04-19 04:38:38,334 - mmseg - INFO - Iter [17650/80000] lr: 1.119e-06, eta: 17:00:58, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7599, decode.acc_seg: 61.7971, aux.loss_ce: 0.3495, aux.acc_seg: 60.4229, loss: 1.1094 2022-04-19 04:39:25,080 - mmseg - INFO - Iter [17700/80000] lr: 1.118e-06, eta: 17:00:00, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7823, decode.acc_seg: 61.9941, aux.loss_ce: 0.3576, aux.acc_seg: 60.7191, loss: 1.1399 2022-04-19 04:40:11,691 - mmseg - INFO - Iter [17750/80000] lr: 1.117e-06, eta: 16:59:02, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7513, decode.acc_seg: 61.7341, aux.loss_ce: 0.3519, aux.acc_seg: 59.6428, loss: 1.1032 2022-04-19 04:40:58,140 - mmseg - INFO - Iter [17800/80000] lr: 1.116e-06, eta: 16:58:04, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7817, decode.acc_seg: 61.5715, aux.loss_ce: 0.3575, aux.acc_seg: 60.1627, loss: 1.1392 2022-04-19 04:41:44,544 - mmseg - INFO - Iter [17850/80000] lr: 1.115e-06, eta: 16:57:05, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8220, decode.acc_seg: 60.8637, aux.loss_ce: 0.3739, aux.acc_seg: 59.6843, loss: 1.1959 2022-04-19 04:42:31,190 - mmseg - INFO - Iter [17900/80000] lr: 1.115e-06, eta: 16:56:08, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7822, decode.acc_seg: 60.6793, aux.loss_ce: 0.3584, aux.acc_seg: 59.2885, loss: 1.1406 2022-04-19 04:43:17,821 - mmseg - INFO - Iter [17950/80000] lr: 1.114e-06, eta: 16:55:10, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8044, decode.acc_seg: 61.8074, aux.loss_ce: 0.3703, aux.acc_seg: 60.2626, loss: 1.1747 2022-04-19 04:44:04,334 - mmseg - INFO - Saving checkpoint at 18000 iterations 2022-04-19 04:44:16,520 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 04:44:16,520 - mmseg - INFO - Iter [18000/80000] lr: 1.113e-06, eta: 16:54:54, time: 1.174, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7771, decode.acc_seg: 60.6151, aux.loss_ce: 0.3560, aux.acc_seg: 59.4071, loss: 1.1331 2022-04-19 04:45:03,507 - mmseg - INFO - Iter [18050/80000] lr: 1.112e-06, eta: 16:53:58, time: 0.940, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7767, decode.acc_seg: 62.9812, aux.loss_ce: 0.3540, aux.acc_seg: 61.8211, loss: 1.1307 2022-04-19 04:45:50,224 - mmseg - INFO - Iter [18100/80000] lr: 1.111e-06, eta: 16:53:00, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7899, decode.acc_seg: 62.0343, aux.loss_ce: 0.3616, aux.acc_seg: 60.6134, loss: 1.1514 2022-04-19 04:46:36,627 - mmseg - INFO - Iter [18150/80000] lr: 1.110e-06, eta: 16:52:02, time: 0.930, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7279, decode.acc_seg: 63.0495, aux.loss_ce: 0.3349, aux.acc_seg: 61.4929, loss: 1.0628 2022-04-19 04:47:23,240 - mmseg - INFO - Iter [18200/80000] lr: 1.109e-06, eta: 16:51:05, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8054, decode.acc_seg: 62.2808, aux.loss_ce: 0.3664, aux.acc_seg: 61.0573, loss: 1.1719 2022-04-19 04:48:09,716 - mmseg - INFO - Iter [18250/80000] lr: 1.108e-06, eta: 16:50:07, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7801, decode.acc_seg: 60.9767, aux.loss_ce: 0.3539, aux.acc_seg: 59.4257, loss: 1.1340 2022-04-19 04:48:56,223 - mmseg - INFO - Iter [18300/80000] lr: 1.107e-06, eta: 16:49:09, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7824, decode.acc_seg: 62.2946, aux.loss_ce: 0.3538, aux.acc_seg: 61.1181, loss: 1.1362 2022-04-19 04:49:42,822 - mmseg - INFO - Iter [18350/80000] lr: 1.106e-06, eta: 16:48:12, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7722, decode.acc_seg: 60.5441, aux.loss_ce: 0.3496, aux.acc_seg: 59.9951, loss: 1.1218 2022-04-19 04:50:29,572 - mmseg - INFO - Iter [18400/80000] lr: 1.106e-06, eta: 16:47:15, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8150, decode.acc_seg: 62.4998, aux.loss_ce: 0.3689, aux.acc_seg: 61.2961, loss: 1.1839 2022-04-19 04:51:16,443 - mmseg - INFO - Iter [18450/80000] lr: 1.105e-06, eta: 16:46:19, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8022, decode.acc_seg: 62.2346, aux.loss_ce: 0.3659, aux.acc_seg: 61.1951, loss: 1.1681 2022-04-19 04:52:03,252 - mmseg - INFO - Iter [18500/80000] lr: 1.104e-06, eta: 16:45:22, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7239, decode.acc_seg: 63.9952, aux.loss_ce: 0.3366, aux.acc_seg: 62.4893, loss: 1.0605 2022-04-19 04:52:49,948 - mmseg - INFO - Iter [18550/80000] lr: 1.103e-06, eta: 16:44:25, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7623, decode.acc_seg: 63.0923, aux.loss_ce: 0.3459, aux.acc_seg: 61.2037, loss: 1.1082 2022-04-19 04:53:36,629 - mmseg - INFO - Iter [18600/80000] lr: 1.102e-06, eta: 16:43:28, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7839, decode.acc_seg: 62.6522, aux.loss_ce: 0.3616, aux.acc_seg: 61.1955, loss: 1.1455 2022-04-19 04:54:23,304 - mmseg - INFO - Iter [18650/80000] lr: 1.101e-06, eta: 16:42:32, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7746, decode.acc_seg: 62.0226, aux.loss_ce: 0.3567, aux.acc_seg: 60.6044, loss: 1.1313 2022-04-19 04:55:09,906 - mmseg - INFO - Iter [18700/80000] lr: 1.100e-06, eta: 16:41:35, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8006, decode.acc_seg: 59.7305, aux.loss_ce: 0.3590, aux.acc_seg: 58.9485, loss: 1.1595 2022-04-19 04:55:56,357 - mmseg - INFO - Iter [18750/80000] lr: 1.099e-06, eta: 16:40:37, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7829, decode.acc_seg: 61.9120, aux.loss_ce: 0.3531, aux.acc_seg: 61.1202, loss: 1.1359 2022-04-19 04:56:42,873 - mmseg - INFO - Iter [18800/80000] lr: 1.098e-06, eta: 16:39:40, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7462, decode.acc_seg: 61.8876, aux.loss_ce: 0.3420, aux.acc_seg: 60.5210, loss: 1.0882 2022-04-19 04:57:29,592 - mmseg - INFO - Iter [18850/80000] lr: 1.098e-06, eta: 16:38:44, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7919, decode.acc_seg: 62.4979, aux.loss_ce: 0.3580, aux.acc_seg: 61.6759, loss: 1.1499 2022-04-19 04:58:16,226 - mmseg - INFO - Iter [18900/80000] lr: 1.097e-06, eta: 16:37:47, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7770, decode.acc_seg: 61.7307, aux.loss_ce: 0.3553, aux.acc_seg: 60.2827, loss: 1.1323 2022-04-19 04:59:02,549 - mmseg - INFO - Iter [18950/80000] lr: 1.096e-06, eta: 16:36:50, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7662, decode.acc_seg: 61.6254, aux.loss_ce: 0.3563, aux.acc_seg: 59.8935, loss: 1.1224 2022-04-19 04:59:49,279 - mmseg - INFO - Saving checkpoint at 19000 iterations 2022-04-19 05:00:02,705 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 05:00:02,716 - mmseg - INFO - Iter [19000/80000] lr: 1.095e-06, eta: 16:36:36, time: 1.201, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7922, decode.acc_seg: 61.6867, aux.loss_ce: 0.3623, aux.acc_seg: 60.4699, loss: 1.1544 2022-04-19 05:00:49,846 - mmseg - INFO - Iter [19050/80000] lr: 1.094e-06, eta: 16:35:41, time: 0.945, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7242, decode.acc_seg: 64.1937, aux.loss_ce: 0.3335, aux.acc_seg: 62.7445, loss: 1.0577 2022-04-19 05:01:36,244 - mmseg - INFO - Iter [19100/80000] lr: 1.093e-06, eta: 16:34:44, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7749, decode.acc_seg: 63.0723, aux.loss_ce: 0.3514, aux.acc_seg: 62.1734, loss: 1.1263 2022-04-19 05:02:22,905 - mmseg - INFO - Iter [19150/80000] lr: 1.092e-06, eta: 16:33:48, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7570, decode.acc_seg: 61.7401, aux.loss_ce: 0.3462, aux.acc_seg: 60.3819, loss: 1.1032 2022-04-19 05:03:09,631 - mmseg - INFO - Iter [19200/80000] lr: 1.091e-06, eta: 16:32:51, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8154, decode.acc_seg: 60.9566, aux.loss_ce: 0.3729, aux.acc_seg: 60.1724, loss: 1.1883 2022-04-19 05:03:56,234 - mmseg - INFO - Iter [19250/80000] lr: 1.090e-06, eta: 16:31:55, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7776, decode.acc_seg: 62.3271, aux.loss_ce: 0.3543, aux.acc_seg: 60.9167, loss: 1.1319 2022-04-19 05:04:42,722 - mmseg - INFO - Iter [19300/80000] lr: 1.089e-06, eta: 16:30:58, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7544, decode.acc_seg: 62.6422, aux.loss_ce: 0.3473, aux.acc_seg: 60.9039, loss: 1.1016 2022-04-19 05:05:29,539 - mmseg - INFO - Iter [19350/80000] lr: 1.089e-06, eta: 16:30:02, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8313, decode.acc_seg: 59.6815, aux.loss_ce: 0.3735, aux.acc_seg: 58.7504, loss: 1.2047 2022-04-19 05:06:15,954 - mmseg - INFO - Iter [19400/80000] lr: 1.088e-06, eta: 16:29:05, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7577, decode.acc_seg: 63.1719, aux.loss_ce: 0.3448, aux.acc_seg: 62.0452, loss: 1.1024 2022-04-19 05:07:02,490 - mmseg - INFO - Iter [19450/80000] lr: 1.087e-06, eta: 16:28:09, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7864, decode.acc_seg: 62.1559, aux.loss_ce: 0.3586, aux.acc_seg: 60.7421, loss: 1.1449 2022-04-19 05:07:49,075 - mmseg - INFO - Iter [19500/80000] lr: 1.086e-06, eta: 16:27:12, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7963, decode.acc_seg: 61.6194, aux.loss_ce: 0.3631, aux.acc_seg: 60.4562, loss: 1.1594 2022-04-19 05:08:35,861 - mmseg - INFO - Iter [19550/80000] lr: 1.085e-06, eta: 16:26:17, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7749, decode.acc_seg: 62.3075, aux.loss_ce: 0.3523, aux.acc_seg: 61.1920, loss: 1.1272 2022-04-19 05:09:22,329 - mmseg - INFO - Iter [19600/80000] lr: 1.084e-06, eta: 16:25:20, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7671, decode.acc_seg: 62.3672, aux.loss_ce: 0.3487, aux.acc_seg: 60.7554, loss: 1.1158 2022-04-19 05:10:09,092 - mmseg - INFO - Iter [19650/80000] lr: 1.083e-06, eta: 16:24:25, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7527, decode.acc_seg: 61.8136, aux.loss_ce: 0.3403, aux.acc_seg: 60.6386, loss: 1.0930 2022-04-19 05:10:55,782 - mmseg - INFO - Iter [19700/80000] lr: 1.082e-06, eta: 16:23:29, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7896, decode.acc_seg: 61.1968, aux.loss_ce: 0.3614, aux.acc_seg: 59.9377, loss: 1.1510 2022-04-19 05:11:42,321 - mmseg - INFO - Iter [19750/80000] lr: 1.081e-06, eta: 16:22:33, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7436, decode.acc_seg: 64.1480, aux.loss_ce: 0.3418, aux.acc_seg: 62.8642, loss: 1.0853 2022-04-19 05:12:29,021 - mmseg - INFO - Iter [19800/80000] lr: 1.080e-06, eta: 16:21:37, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7771, decode.acc_seg: 62.5932, aux.loss_ce: 0.3520, aux.acc_seg: 61.7458, loss: 1.1292 2022-04-19 05:13:15,416 - mmseg - INFO - Iter [19850/80000] lr: 1.080e-06, eta: 16:20:40, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7697, decode.acc_seg: 61.8823, aux.loss_ce: 0.3481, aux.acc_seg: 61.0816, loss: 1.1178 2022-04-19 05:14:01,945 - mmseg - INFO - Iter [19900/80000] lr: 1.079e-06, eta: 16:19:44, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7911, decode.acc_seg: 61.5499, aux.loss_ce: 0.3590, aux.acc_seg: 60.1754, loss: 1.1502 2022-04-19 05:14:48,842 - mmseg - INFO - Iter [19950/80000] lr: 1.078e-06, eta: 16:18:49, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7553, decode.acc_seg: 61.5732, aux.loss_ce: 0.3362, aux.acc_seg: 60.8420, loss: 1.0915 2022-04-19 05:15:35,671 - mmseg - INFO - Saving checkpoint at 20000 iterations 2022-04-19 05:15:48,144 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 05:15:48,145 - mmseg - INFO - Iter [20000/80000] lr: 1.077e-06, eta: 16:18:31, time: 1.185, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7769, decode.acc_seg: 63.6138, aux.loss_ce: 0.3516, aux.acc_seg: 62.5052, loss: 1.1284 2022-04-19 05:16:35,441 - mmseg - INFO - Iter [20050/80000] lr: 1.076e-06, eta: 16:17:38, time: 0.947, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7635, decode.acc_seg: 62.0576, aux.loss_ce: 0.3426, aux.acc_seg: 61.2718, loss: 1.1061 2022-04-19 05:17:21,988 - mmseg - INFO - Iter [20100/80000] lr: 1.075e-06, eta: 16:16:42, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7407, decode.acc_seg: 62.7465, aux.loss_ce: 0.3362, aux.acc_seg: 61.4805, loss: 1.0768 2022-04-19 05:18:08,398 - mmseg - INFO - Iter [20150/80000] lr: 1.074e-06, eta: 16:15:45, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7783, decode.acc_seg: 63.2500, aux.loss_ce: 0.3491, aux.acc_seg: 61.8825, loss: 1.1274 2022-04-19 05:18:55,042 - mmseg - INFO - Iter [20200/80000] lr: 1.073e-06, eta: 16:14:50, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7754, decode.acc_seg: 61.6770, aux.loss_ce: 0.3514, aux.acc_seg: 60.7720, loss: 1.1268 2022-04-19 05:19:41,890 - mmseg - INFO - Iter [20250/80000] lr: 1.072e-06, eta: 16:13:55, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7435, decode.acc_seg: 61.8951, aux.loss_ce: 0.3380, aux.acc_seg: 61.0690, loss: 1.0815 2022-04-19 05:20:28,878 - mmseg - INFO - Iter [20300/80000] lr: 1.071e-06, eta: 16:13:00, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7712, decode.acc_seg: 61.6618, aux.loss_ce: 0.3463, aux.acc_seg: 60.3128, loss: 1.1175 2022-04-19 05:21:15,890 - mmseg - INFO - Iter [20350/80000] lr: 1.071e-06, eta: 16:12:06, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7665, decode.acc_seg: 63.0977, aux.loss_ce: 0.3478, aux.acc_seg: 61.8617, loss: 1.1143 2022-04-19 05:22:02,632 - mmseg - INFO - Iter [20400/80000] lr: 1.070e-06, eta: 16:11:11, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7335, decode.acc_seg: 63.8841, aux.loss_ce: 0.3310, aux.acc_seg: 63.2308, loss: 1.0644 2022-04-19 05:22:49,099 - mmseg - INFO - Iter [20450/80000] lr: 1.069e-06, eta: 16:10:15, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7539, decode.acc_seg: 63.9108, aux.loss_ce: 0.3403, aux.acc_seg: 62.8619, loss: 1.0942 2022-04-19 05:23:35,900 - mmseg - INFO - Iter [20500/80000] lr: 1.068e-06, eta: 16:09:20, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7588, decode.acc_seg: 61.9602, aux.loss_ce: 0.3418, aux.acc_seg: 60.6951, loss: 1.1006 2022-04-19 05:24:22,553 - mmseg - INFO - Iter [20550/80000] lr: 1.067e-06, eta: 16:08:24, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7592, decode.acc_seg: 62.6809, aux.loss_ce: 0.3400, aux.acc_seg: 61.6227, loss: 1.0993 2022-04-19 05:25:08,982 - mmseg - INFO - Iter [20600/80000] lr: 1.066e-06, eta: 16:07:29, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7823, decode.acc_seg: 62.3979, aux.loss_ce: 0.3515, aux.acc_seg: 61.2626, loss: 1.1338 2022-04-19 05:25:55,542 - mmseg - INFO - Iter [20650/80000] lr: 1.065e-06, eta: 16:06:33, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7840, decode.acc_seg: 61.1682, aux.loss_ce: 0.3543, aux.acc_seg: 60.0795, loss: 1.1383 2022-04-19 05:26:41,988 - mmseg - INFO - Iter [20700/80000] lr: 1.064e-06, eta: 16:05:37, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7754, decode.acc_seg: 61.8567, aux.loss_ce: 0.3444, aux.acc_seg: 61.1704, loss: 1.1198 2022-04-19 05:27:28,352 - mmseg - INFO - Iter [20750/80000] lr: 1.063e-06, eta: 16:04:41, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7532, decode.acc_seg: 61.7303, aux.loss_ce: 0.3374, aux.acc_seg: 60.5317, loss: 1.0905 2022-04-19 05:28:14,841 - mmseg - INFO - Iter [20800/80000] lr: 1.063e-06, eta: 16:03:46, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7529, decode.acc_seg: 62.0939, aux.loss_ce: 0.3422, aux.acc_seg: 60.8108, loss: 1.0951 2022-04-19 05:29:01,523 - mmseg - INFO - Iter [20850/80000] lr: 1.062e-06, eta: 16:02:51, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7774, decode.acc_seg: 60.4173, aux.loss_ce: 0.3475, aux.acc_seg: 59.7164, loss: 1.1249 2022-04-19 05:29:48,155 - mmseg - INFO - Iter [20900/80000] lr: 1.061e-06, eta: 16:01:56, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7403, decode.acc_seg: 62.2825, aux.loss_ce: 0.3364, aux.acc_seg: 61.0108, loss: 1.0767 2022-04-19 05:30:34,830 - mmseg - INFO - Iter [20950/80000] lr: 1.060e-06, eta: 16:01:01, time: 0.935, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7517, decode.acc_seg: 60.1390, aux.loss_ce: 0.3411, aux.acc_seg: 59.0904, loss: 1.0929 2022-04-19 05:31:21,239 - mmseg - INFO - Saving checkpoint at 21000 iterations 2022-04-19 05:31:32,515 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 05:31:32,515 - mmseg - INFO - Iter [21000/80000] lr: 1.059e-06, eta: 16:00:37, time: 1.154, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7451, decode.acc_seg: 64.1984, aux.loss_ce: 0.3361, aux.acc_seg: 63.0121, loss: 1.0812 2022-04-19 05:32:19,480 - mmseg - INFO - Iter [21050/80000] lr: 1.058e-06, eta: 15:59:43, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 0.8156, decode.acc_seg: 61.7423, aux.loss_ce: 0.3655, aux.acc_seg: 60.5746, loss: 1.1811 2022-04-19 05:33:06,125 - mmseg - INFO - Iter [21100/80000] lr: 1.057e-06, eta: 15:58:48, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7730, decode.acc_seg: 61.3382, aux.loss_ce: 0.3500, aux.acc_seg: 60.0771, loss: 1.1230 2022-04-19 05:33:52,626 - mmseg - INFO - Iter [21150/80000] lr: 1.056e-06, eta: 15:57:53, time: 0.932, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7811, decode.acc_seg: 62.7712, aux.loss_ce: 0.3531, aux.acc_seg: 61.7819, loss: 1.1342 2022-04-19 05:34:39,300 - mmseg - INFO - Iter [21200/80000] lr: 1.055e-06, eta: 15:56:58, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7589, decode.acc_seg: 62.7964, aux.loss_ce: 0.3391, aux.acc_seg: 61.9196, loss: 1.0980 2022-04-19 05:35:25,942 - mmseg - INFO - Iter [21250/80000] lr: 1.054e-06, eta: 15:56:03, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8343, decode.acc_seg: 61.0315, aux.loss_ce: 0.3688, aux.acc_seg: 60.2071, loss: 1.2031 2022-04-19 05:36:12,525 - mmseg - INFO - Iter [21300/80000] lr: 1.054e-06, eta: 15:55:08, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7564, decode.acc_seg: 62.6973, aux.loss_ce: 0.3377, aux.acc_seg: 61.6654, loss: 1.0941 2022-04-19 05:36:59,022 - mmseg - INFO - Iter [21350/80000] lr: 1.053e-06, eta: 15:54:13, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7840, decode.acc_seg: 62.1869, aux.loss_ce: 0.3529, aux.acc_seg: 60.9002, loss: 1.1369 2022-04-19 05:37:45,580 - mmseg - INFO - Iter [21400/80000] lr: 1.052e-06, eta: 15:53:18, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7481, decode.acc_seg: 62.3724, aux.loss_ce: 0.3418, aux.acc_seg: 60.8138, loss: 1.0899 2022-04-19 05:38:32,168 - mmseg - INFO - Iter [21450/80000] lr: 1.051e-06, eta: 15:52:23, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7404, decode.acc_seg: 63.4154, aux.loss_ce: 0.3353, aux.acc_seg: 62.4016, loss: 1.0758 2022-04-19 05:39:19,060 - mmseg - INFO - Iter [21500/80000] lr: 1.050e-06, eta: 15:51:29, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7579, decode.acc_seg: 62.1439, aux.loss_ce: 0.3386, aux.acc_seg: 61.1247, loss: 1.0965 2022-04-19 05:40:05,607 - mmseg - INFO - Iter [21550/80000] lr: 1.049e-06, eta: 15:50:34, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7560, decode.acc_seg: 62.3869, aux.loss_ce: 0.3396, aux.acc_seg: 61.2874, loss: 1.0956 2022-04-19 05:40:52,372 - mmseg - INFO - Iter [21600/80000] lr: 1.048e-06, eta: 15:49:40, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8079, decode.acc_seg: 62.5432, aux.loss_ce: 0.3626, aux.acc_seg: 61.0259, loss: 1.1704 2022-04-19 05:41:39,070 - mmseg - INFO - Iter [21650/80000] lr: 1.047e-06, eta: 15:48:45, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8231, decode.acc_seg: 62.9848, aux.loss_ce: 0.3671, aux.acc_seg: 61.7612, loss: 1.1902 2022-04-19 05:42:25,645 - mmseg - INFO - Iter [21700/80000] lr: 1.046e-06, eta: 15:47:51, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7374, decode.acc_seg: 62.5893, aux.loss_ce: 0.3286, aux.acc_seg: 61.6651, loss: 1.0660 2022-04-19 05:43:12,104 - mmseg - INFO - Iter [21750/80000] lr: 1.045e-06, eta: 15:46:56, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7254, decode.acc_seg: 64.0989, aux.loss_ce: 0.3280, aux.acc_seg: 63.1211, loss: 1.0534 2022-04-19 05:43:58,641 - mmseg - INFO - Iter [21800/80000] lr: 1.045e-06, eta: 15:46:01, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7594, decode.acc_seg: 62.0851, aux.loss_ce: 0.3406, aux.acc_seg: 60.6274, loss: 1.1000 2022-04-19 05:44:45,277 - mmseg - INFO - Iter [21850/80000] lr: 1.044e-06, eta: 15:45:06, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8008, decode.acc_seg: 61.1041, aux.loss_ce: 0.3560, aux.acc_seg: 60.1853, loss: 1.1568 2022-04-19 05:45:31,781 - mmseg - INFO - Iter [21900/80000] lr: 1.043e-06, eta: 15:44:12, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7850, decode.acc_seg: 62.4798, aux.loss_ce: 0.3531, aux.acc_seg: 61.6031, loss: 1.1380 2022-04-19 05:46:18,366 - mmseg - INFO - Iter [21950/80000] lr: 1.042e-06, eta: 15:43:17, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7793, decode.acc_seg: 61.5373, aux.loss_ce: 0.3513, aux.acc_seg: 60.1395, loss: 1.1306 2022-04-19 05:47:04,651 - mmseg - INFO - Saving checkpoint at 22000 iterations 2022-04-19 05:47:17,316 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 05:47:17,324 - mmseg - INFO - Iter [22000/80000] lr: 1.041e-06, eta: 15:42:55, time: 1.178, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7343, decode.acc_seg: 64.4852, aux.loss_ce: 0.3315, aux.acc_seg: 63.1874, loss: 1.0659 2022-04-19 05:48:04,309 - mmseg - INFO - Iter [22050/80000] lr: 1.040e-06, eta: 15:42:02, time: 0.941, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7843, decode.acc_seg: 62.5702, aux.loss_ce: 0.3525, aux.acc_seg: 61.4655, loss: 1.1368 2022-04-19 05:48:50,920 - mmseg - INFO - Iter [22100/80000] lr: 1.039e-06, eta: 15:41:08, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7493, decode.acc_seg: 63.1130, aux.loss_ce: 0.3339, aux.acc_seg: 62.4979, loss: 1.0832 2022-04-19 05:49:37,567 - mmseg - INFO - Iter [22150/80000] lr: 1.038e-06, eta: 15:40:13, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7814, decode.acc_seg: 62.1771, aux.loss_ce: 0.3488, aux.acc_seg: 61.4208, loss: 1.1301 2022-04-19 05:50:27,062 - mmseg - INFO - Iter [22200/80000] lr: 1.037e-06, eta: 15:39:26, time: 0.990, data_time: 0.056, memory: 73037, decode.loss_ce: 0.7412, decode.acc_seg: 63.4773, aux.loss_ce: 0.3322, aux.acc_seg: 62.6850, loss: 1.0733 2022-04-19 05:51:14,134 - mmseg - INFO - Iter [22250/80000] lr: 1.036e-06, eta: 15:38:33, time: 0.942, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7386, decode.acc_seg: 60.9338, aux.loss_ce: 0.3317, aux.acc_seg: 59.7487, loss: 1.0703 2022-04-19 05:52:01,185 - mmseg - INFO - Iter [22300/80000] lr: 1.036e-06, eta: 15:37:40, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7415, decode.acc_seg: 63.0528, aux.loss_ce: 0.3347, aux.acc_seg: 61.7820, loss: 1.0761 2022-04-19 05:52:47,717 - mmseg - INFO - Iter [22350/80000] lr: 1.035e-06, eta: 15:36:46, time: 0.932, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7586, decode.acc_seg: 62.5522, aux.loss_ce: 0.3454, aux.acc_seg: 61.1634, loss: 1.1040 2022-04-19 05:53:34,572 - mmseg - INFO - Iter [22400/80000] lr: 1.034e-06, eta: 15:35:52, time: 0.935, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7454, decode.acc_seg: 63.0847, aux.loss_ce: 0.3420, aux.acc_seg: 61.9740, loss: 1.0874 2022-04-19 05:54:21,226 - mmseg - INFO - Iter [22450/80000] lr: 1.033e-06, eta: 15:34:58, time: 0.935, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7013, decode.acc_seg: 64.0499, aux.loss_ce: 0.3204, aux.acc_seg: 62.9805, loss: 1.0217 2022-04-19 05:55:07,551 - mmseg - INFO - Iter [22500/80000] lr: 1.032e-06, eta: 15:34:03, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7565, decode.acc_seg: 62.3226, aux.loss_ce: 0.3442, aux.acc_seg: 60.9120, loss: 1.1008 2022-04-19 05:55:54,621 - mmseg - INFO - Iter [22550/80000] lr: 1.031e-06, eta: 15:33:10, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7406, decode.acc_seg: 62.8274, aux.loss_ce: 0.3371, aux.acc_seg: 61.7342, loss: 1.0777 2022-04-19 05:56:40,984 - mmseg - INFO - Iter [22600/80000] lr: 1.030e-06, eta: 15:32:15, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7384, decode.acc_seg: 64.5188, aux.loss_ce: 0.3373, aux.acc_seg: 63.2956, loss: 1.0757 2022-04-19 05:57:27,547 - mmseg - INFO - Iter [22650/80000] lr: 1.029e-06, eta: 15:31:21, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7479, decode.acc_seg: 62.6344, aux.loss_ce: 0.3415, aux.acc_seg: 61.6126, loss: 1.0894 2022-04-19 05:58:14,295 - mmseg - INFO - Iter [22700/80000] lr: 1.028e-06, eta: 15:30:27, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7721, decode.acc_seg: 60.9183, aux.loss_ce: 0.3453, aux.acc_seg: 59.9094, loss: 1.1174 2022-04-19 05:59:00,774 - mmseg - INFO - Iter [22750/80000] lr: 1.028e-06, eta: 15:29:33, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7026, decode.acc_seg: 65.0426, aux.loss_ce: 0.3155, aux.acc_seg: 64.1131, loss: 1.0181 2022-04-19 05:59:47,147 - mmseg - INFO - Iter [22800/80000] lr: 1.027e-06, eta: 15:28:38, time: 0.928, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7318, decode.acc_seg: 63.2754, aux.loss_ce: 0.3353, aux.acc_seg: 61.5513, loss: 1.0671 2022-04-19 06:00:34,883 - mmseg - INFO - Iter [22850/80000] lr: 1.026e-06, eta: 15:27:47, time: 0.954, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7463, decode.acc_seg: 62.9583, aux.loss_ce: 0.3373, aux.acc_seg: 62.0247, loss: 1.0836 2022-04-19 06:01:21,652 - mmseg - INFO - Iter [22900/80000] lr: 1.025e-06, eta: 15:26:54, time: 0.936, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7450, decode.acc_seg: 62.4649, aux.loss_ce: 0.3376, aux.acc_seg: 61.6303, loss: 1.0826 2022-04-19 06:02:08,254 - mmseg - INFO - Iter [22950/80000] lr: 1.024e-06, eta: 15:26:00, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7351, decode.acc_seg: 63.5051, aux.loss_ce: 0.3330, aux.acc_seg: 62.2746, loss: 1.0681 2022-04-19 06:02:54,869 - mmseg - INFO - Saving checkpoint at 23000 iterations 2022-04-19 06:03:07,675 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 06:03:07,683 - mmseg - INFO - Iter [23000/80000] lr: 1.023e-06, eta: 15:25:38, time: 1.187, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7428, decode.acc_seg: 62.8121, aux.loss_ce: 0.3344, aux.acc_seg: 61.3037, loss: 1.0772 2022-04-19 06:03:54,406 - mmseg - INFO - Iter [23050/80000] lr: 1.022e-06, eta: 15:24:44, time: 0.936, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7356, decode.acc_seg: 62.7476, aux.loss_ce: 0.3355, aux.acc_seg: 61.9224, loss: 1.0712 2022-04-19 06:04:40,951 - mmseg - INFO - Iter [23100/80000] lr: 1.021e-06, eta: 15:23:50, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7226, decode.acc_seg: 63.5591, aux.loss_ce: 0.3302, aux.acc_seg: 61.7120, loss: 1.0528 2022-04-19 06:05:27,783 - mmseg - INFO - Iter [23150/80000] lr: 1.020e-06, eta: 15:22:57, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7056, decode.acc_seg: 63.4101, aux.loss_ce: 0.3174, aux.acc_seg: 62.2050, loss: 1.0230 2022-04-19 06:06:14,476 - mmseg - INFO - Iter [23200/80000] lr: 1.019e-06, eta: 15:22:03, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7678, decode.acc_seg: 62.0155, aux.loss_ce: 0.3468, aux.acc_seg: 60.9299, loss: 1.1146 2022-04-19 06:07:00,905 - mmseg - INFO - Iter [23250/80000] lr: 1.019e-06, eta: 15:21:09, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7273, decode.acc_seg: 63.3682, aux.loss_ce: 0.3300, aux.acc_seg: 62.2563, loss: 1.0573 2022-04-19 06:07:47,514 - mmseg - INFO - Iter [23300/80000] lr: 1.018e-06, eta: 15:20:15, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7588, decode.acc_seg: 61.7082, aux.loss_ce: 0.3411, aux.acc_seg: 60.9307, loss: 1.0999 2022-04-19 06:08:34,003 - mmseg - INFO - Iter [23350/80000] lr: 1.017e-06, eta: 15:19:21, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7304, decode.acc_seg: 63.4183, aux.loss_ce: 0.3281, aux.acc_seg: 61.9633, loss: 1.0585 2022-04-19 06:09:20,586 - mmseg - INFO - Iter [23400/80000] lr: 1.016e-06, eta: 15:18:27, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7241, decode.acc_seg: 63.4603, aux.loss_ce: 0.3282, aux.acc_seg: 62.4715, loss: 1.0523 2022-04-19 06:10:07,174 - mmseg - INFO - Iter [23450/80000] lr: 1.015e-06, eta: 15:17:34, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7514, decode.acc_seg: 61.8023, aux.loss_ce: 0.3383, aux.acc_seg: 60.7161, loss: 1.0897 2022-04-19 06:10:53,682 - mmseg - INFO - Iter [23500/80000] lr: 1.014e-06, eta: 15:16:40, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7642, decode.acc_seg: 62.6899, aux.loss_ce: 0.3418, aux.acc_seg: 62.0696, loss: 1.1060 2022-04-19 06:11:40,202 - mmseg - INFO - Iter [23550/80000] lr: 1.013e-06, eta: 15:15:46, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7568, decode.acc_seg: 62.0281, aux.loss_ce: 0.3427, aux.acc_seg: 60.9551, loss: 1.0994 2022-04-19 06:12:26,971 - mmseg - INFO - Iter [23600/80000] lr: 1.012e-06, eta: 15:14:53, time: 0.936, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7354, decode.acc_seg: 63.1053, aux.loss_ce: 0.3365, aux.acc_seg: 61.4322, loss: 1.0719 2022-04-19 06:13:13,414 - mmseg - INFO - Iter [23650/80000] lr: 1.011e-06, eta: 15:13:59, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7641, decode.acc_seg: 62.3754, aux.loss_ce: 0.3473, aux.acc_seg: 61.2220, loss: 1.1115 2022-04-19 06:14:00,640 - mmseg - INFO - Iter [23700/80000] lr: 1.010e-06, eta: 15:13:07, time: 0.945, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7625, decode.acc_seg: 62.3916, aux.loss_ce: 0.3392, aux.acc_seg: 61.6320, loss: 1.1017 2022-04-19 06:14:47,255 - mmseg - INFO - Iter [23750/80000] lr: 1.010e-06, eta: 15:12:13, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7661, decode.acc_seg: 61.0040, aux.loss_ce: 0.3463, aux.acc_seg: 59.5297, loss: 1.1123 2022-04-19 06:15:33,706 - mmseg - INFO - Iter [23800/80000] lr: 1.009e-06, eta: 15:11:19, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7409, decode.acc_seg: 62.6031, aux.loss_ce: 0.3341, aux.acc_seg: 61.2623, loss: 1.0750 2022-04-19 06:16:20,088 - mmseg - INFO - Iter [23850/80000] lr: 1.008e-06, eta: 15:10:25, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7218, decode.acc_seg: 62.3074, aux.loss_ce: 0.3244, aux.acc_seg: 61.0752, loss: 1.0462 2022-04-19 06:17:06,773 - mmseg - INFO - Iter [23900/80000] lr: 1.007e-06, eta: 15:09:32, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7520, decode.acc_seg: 62.5963, aux.loss_ce: 0.3382, aux.acc_seg: 61.6776, loss: 1.0902 2022-04-19 06:17:53,478 - mmseg - INFO - Iter [23950/80000] lr: 1.006e-06, eta: 15:08:39, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7651, decode.acc_seg: 62.2248, aux.loss_ce: 0.3500, aux.acc_seg: 61.1239, loss: 1.1151 2022-04-19 06:18:40,348 - mmseg - INFO - Saving checkpoint at 24000 iterations 2022-04-19 06:18:53,268 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 06:18:53,269 - mmseg - INFO - Iter [24000/80000] lr: 1.005e-06, eta: 15:08:16, time: 1.195, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7726, decode.acc_seg: 61.7144, aux.loss_ce: 0.3479, aux.acc_seg: 60.7086, loss: 1.1204 2022-04-19 06:22:48,026 - mmseg - INFO - per class results: 2022-04-19 06:22:48,037 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 85.7 | 95.57 | | bicycle | 69.66 | 86.92 | | car | 64.65 | 87.3 | | motorcycle | 84.37 | 90.91 | | airplane | 78.38 | 94.13 | | bus | 85.01 | 92.37 | | train | 83.4 | 96.51 | | truck | 66.2 | 85.08 | | boat | 64.08 | 86.0 | | traffic light | 64.26 | 86.26 | | fire hydrant | 82.94 | 97.72 | | stop sign | 90.27 | 98.01 | | parking meter | 76.71 | 86.92 | | bench | 55.33 | 74.22 | | bird | 82.46 | 90.62 | | cat | 83.06 | 91.18 | | dog | 80.51 | 90.11 | | horse | 86.63 | 94.73 | | sheep | 87.08 | 96.48 | | cow | 87.58 | 93.15 | | elephant | 91.63 | 98.04 | | bear | 91.26 | 97.12 | | zebra | 91.65 | 97.37 | | giraffe | 85.57 | 95.17 | | backpack | 37.53 | 63.94 | | umbrella | 86.35 | 91.31 | | handbag | 37.81 | 52.34 | | tie | 3.75 | 4.51 | | suitcase | 79.96 | 93.46 | | frisbee | 79.14 | 88.48 | | skis | 36.0 | 41.74 | | snowboard | 61.98 | 75.28 | | sports ball | 58.17 | 65.88 | | kite | 72.4 | 87.63 | | baseball bat | 53.68 | 75.25 | | baseball glove | 74.05 | 84.49 | | skateboard | 78.99 | 90.71 | | surfboard | 80.38 | 87.81 | | tennis racket | 83.34 | 93.04 | | bottle | 49.91 | 67.18 | | wine glass | 58.57 | 83.29 | | cup | 53.19 | 80.54 | | fork | 43.69 | 62.09 | | knife | 35.77 | 49.78 | | spoon | 40.05 | 54.82 | | bowl | 48.96 | 63.43 | | banana | 70.12 | 92.58 | | apple | 54.06 | 78.27 | | sandwich | 54.53 | 79.05 | | orange | 72.62 | 84.02 | | broccoli | 56.36 | 79.28 | | carrot | 59.64 | 76.51 | | hot dog | 59.55 | 75.13 | | pizza | 75.57 | 92.9 | | donut | 75.61 | 94.44 | | cake | 69.3 | 86.13 | | chair | 50.17 | 76.09 | | couch | 58.22 | 81.11 | | potted plant | 28.82 | 48.52 | | bed | 62.99 | 83.26 | | dining table | 46.77 | 71.12 | | toilet | 79.93 | 96.33 | | tv | 70.68 | 83.54 | | laptop | 74.38 | 95.37 | | mouse | 70.45 | 75.86 | | remote | 58.18 | 74.75 | | keyboard | 62.84 | 70.9 | | cell phone | 75.22 | 87.61 | | microwave | 66.52 | 82.94 | | oven | 55.0 | 86.49 | | toaster | 40.19 | 40.19 | | sink | 59.39 | 87.13 | | refrigerator | 74.57 | 93.06 | | book | 48.97 | 68.19 | | clock | 71.98 | 81.68 | | vase | 60.78 | 81.77 | | scissors | 73.72 | 92.23 | | teddy bear | 78.46 | 93.73 | | hair drier | 10.74 | 10.74 | | toothbrush | 54.72 | 67.82 | | banner | 34.12 | 71.98 | | blanket | 0.21 | 0.23 | | branch | 14.18 | 16.38 | | bridge | 37.93 | 56.95 | | building-other | 53.89 | 72.09 | | bush | 30.64 | 40.87 | | cabinet | 56.76 | 77.88 | | cage | 25.69 | 47.0 | | cardboard | 48.11 | 62.5 | | carpet | 51.28 | 79.33 | | ceiling-other | 65.16 | 84.48 | | ceiling-tile | 0.0 | 0.0 | | cloth | 0.03 | 0.05 | | clothes | 15.48 | 18.99 | | clouds | 51.98 | 73.84 | | counter | 27.91 | 59.81 | | cupboard | 0.0 | 0.0 | | curtain | 67.0 | 83.06 | | desk-stuff | 46.76 | 70.53 | | dirt | 42.46 | 64.52 | | door-stuff | 44.58 | 72.71 | | fence | 32.15 | 52.81 | | floor-marble | 8.89 | 10.63 | | floor-other | 19.99 | 26.11 | | floor-stone | 7.07 | 9.83 | | floor-tile | 63.39 | 74.38 | | floor-wood | 61.11 | 77.93 | | flower | 39.43 | 55.64 | | fog | 13.82 | 15.82 | | food-other | 29.01 | 38.47 | | fruit | 42.58 | 60.04 | | furniture-other | 13.51 | 15.73 | | grass | 70.8 | 84.1 | | gravel | 24.72 | 31.71 | | ground-other | 2.65 | 3.06 | | hill | 20.89 | 32.52 | | house | 28.29 | 34.27 | | leaves | 30.96 | 42.6 | | light | 41.45 | 56.31 | | mat | 0.0 | 0.0 | | metal | 30.52 | 39.5 | | mirror-stuff | 52.7 | 73.46 | | moss | 0.0 | 0.0 | | mountain | 51.52 | 68.76 | | mud | 8.29 | 18.54 | | napkin | 5.35 | 5.73 | | net | 46.77 | 69.63 | | paper | 32.31 | 43.95 | | pavement | 49.52 | 65.07 | | pillow | 10.35 | 10.78 | | plant-other | 16.26 | 21.55 | | plastic | 22.71 | 30.18 | | platform | 29.55 | 52.29 | | playingfield | 70.39 | 89.69 | | railing | 9.0 | 16.97 | | railroad | 59.0 | 86.05 | | river | 52.12 | 78.3 | | road | 64.95 | 85.14 | | rock | 44.68 | 65.52 | | roof | 20.63 | 25.17 | | rug | 27.14 | 34.65 | | salad | 2.61 | 3.09 | | sand | 64.06 | 68.62 | | sea | 84.93 | 93.91 | | shelf | 35.64 | 49.85 | | sky-other | 71.36 | 83.08 | | skyscraper | 38.75 | 65.08 | | snow | 90.36 | 95.43 | | solid-other | 0.0 | 0.0 | | stairs | 27.65 | 56.03 | | stone | 17.26 | 22.8 | | straw | 27.74 | 34.37 | | structural-other | 0.41 | 0.42 | | table | 19.66 | 25.17 | | tent | 9.18 | 12.47 | | textile-other | 14.21 | 19.06 | | towel | 31.8 | 40.42 | | tree | 72.84 | 89.68 | | vegetable | 40.87 | 51.92 | | wall-brick | 46.13 | 66.48 | | wall-concrete | 60.39 | 79.5 | | wall-other | 20.69 | 27.96 | | wall-panel | 2.69 | 3.06 | | wall-stone | 26.51 | 32.18 | | wall-tile | 67.76 | 83.66 | | wall-wood | 42.09 | 55.49 | | water-other | 22.01 | 26.86 | | waterdrops | 0.0 | 0.0 | | window-blind | 53.02 | 66.67 | | window-other | 46.43 | 72.54 | | wood | 24.62 | 32.1 | +------------------+-------+-------+ 2022-04-19 06:22:48,038 - mmseg - INFO - Summary: 2022-04-19 06:22:48,038 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 72.58 | 48.44 | 61.65 | +-------+-------+-------+ 2022-04-19 06:22:48,053 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 06:22:48,055 - mmseg - INFO - Iter(val) [625] aAcc: 0.7258, mIoU: 0.4844, mAcc: 0.6165, IoU.person: 0.8570, IoU.bicycle: 0.6966, IoU.car: 0.6465, IoU.motorcycle: 0.8437, IoU.airplane: 0.7838, IoU.bus: 0.8501, IoU.train: 0.8340, IoU.truck: 0.6620, IoU.boat: 0.6408, IoU.traffic light: 0.6426, IoU.fire hydrant: 0.8294, IoU.stop sign: 0.9027, IoU.parking meter: 0.7671, IoU.bench: 0.5533, IoU.bird: 0.8246, IoU.cat: 0.8306, IoU.dog: 0.8051, IoU.horse: 0.8663, IoU.sheep: 0.8708, IoU.cow: 0.8758, IoU.elephant: 0.9163, IoU.bear: 0.9126, IoU.zebra: 0.9165, IoU.giraffe: 0.8557, IoU.backpack: 0.3753, IoU.umbrella: 0.8635, IoU.handbag: 0.3781, IoU.tie: 0.0375, IoU.suitcase: 0.7996, IoU.frisbee: 0.7914, IoU.skis: 0.3600, IoU.snowboard: 0.6198, IoU.sports ball: 0.5817, IoU.kite: 0.7240, IoU.baseball bat: 0.5368, IoU.baseball glove: 0.7405, IoU.skateboard: 0.7899, IoU.surfboard: 0.8038, IoU.tennis racket: 0.8334, IoU.bottle: 0.4991, IoU.wine glass: 0.5857, IoU.cup: 0.5319, IoU.fork: 0.4369, IoU.knife: 0.3577, IoU.spoon: 0.4005, IoU.bowl: 0.4896, IoU.banana: 0.7012, IoU.apple: 0.5406, IoU.sandwich: 0.5453, IoU.orange: 0.7262, IoU.broccoli: 0.5636, IoU.carrot: 0.5964, IoU.hot dog: 0.5955, IoU.pizza: 0.7557, IoU.donut: 0.7561, IoU.cake: 0.6930, IoU.chair: 0.5017, IoU.couch: 0.5822, IoU.potted plant: 0.2882, IoU.bed: 0.6299, IoU.dining table: 0.4677, IoU.toilet: 0.7993, IoU.tv: 0.7068, IoU.laptop: 0.7438, IoU.mouse: 0.7045, IoU.remote: 0.5818, IoU.keyboard: 0.6284, IoU.cell phone: 0.7522, IoU.microwave: 0.6652, IoU.oven: 0.5500, IoU.toaster: 0.4019, IoU.sink: 0.5939, IoU.refrigerator: 0.7457, IoU.book: 0.4897, IoU.clock: 0.7198, IoU.vase: 0.6078, IoU.scissors: 0.7372, IoU.teddy bear: 0.7846, IoU.hair drier: 0.1074, IoU.toothbrush: 0.5472, IoU.banner: 0.3412, IoU.blanket: 0.0021, IoU.branch: 0.1418, IoU.bridge: 0.3793, IoU.building-other: 0.5389, IoU.bush: 0.3064, IoU.cabinet: 0.5676, IoU.cage: 0.2569, IoU.cardboard: 0.4811, IoU.carpet: 0.5128, IoU.ceiling-other: 0.6516, IoU.ceiling-tile: 0.0000, IoU.cloth: 0.0003, IoU.clothes: 0.1548, IoU.clouds: 0.5198, IoU.counter: 0.2791, IoU.cupboard: 0.0000, IoU.curtain: 0.6700, IoU.desk-stuff: 0.4676, IoU.dirt: 0.4246, IoU.door-stuff: 0.4458, IoU.fence: 0.3215, IoU.floor-marble: 0.0889, IoU.floor-other: 0.1999, IoU.floor-stone: 0.0707, IoU.floor-tile: 0.6339, IoU.floor-wood: 0.6111, IoU.flower: 0.3943, IoU.fog: 0.1382, IoU.food-other: 0.2901, IoU.fruit: 0.4258, IoU.furniture-other: 0.1351, IoU.grass: 0.7080, IoU.gravel: 0.2472, IoU.ground-other: 0.0265, IoU.hill: 0.2089, IoU.house: 0.2829, IoU.leaves: 0.3096, IoU.light: 0.4145, IoU.mat: 0.0000, IoU.metal: 0.3052, IoU.mirror-stuff: 0.5270, IoU.moss: 0.0000, IoU.mountain: 0.5152, IoU.mud: 0.0829, IoU.napkin: 0.0535, IoU.net: 0.4677, IoU.paper: 0.3231, IoU.pavement: 0.4952, IoU.pillow: 0.1035, IoU.plant-other: 0.1626, IoU.plastic: 0.2271, IoU.platform: 0.2955, IoU.playingfield: 0.7039, IoU.railing: 0.0900, IoU.railroad: 0.5900, IoU.river: 0.5212, IoU.road: 0.6495, IoU.rock: 0.4468, IoU.roof: 0.2063, IoU.rug: 0.2714, IoU.salad: 0.0261, IoU.sand: 0.6406, IoU.sea: 0.8493, IoU.shelf: 0.3564, IoU.sky-other: 0.7136, IoU.skyscraper: 0.3875, IoU.snow: 0.9036, IoU.solid-other: 0.0000, IoU.stairs: 0.2765, IoU.stone: 0.1726, IoU.straw: 0.2774, IoU.structural-other: 0.0041, IoU.table: 0.1966, IoU.tent: 0.0918, IoU.textile-other: 0.1421, IoU.towel: 0.3180, IoU.tree: 0.7284, IoU.vegetable: 0.4087, IoU.wall-brick: 0.4613, IoU.wall-concrete: 0.6039, IoU.wall-other: 0.2069, IoU.wall-panel: 0.0269, IoU.wall-stone: 0.2651, IoU.wall-tile: 0.6776, IoU.wall-wood: 0.4209, IoU.water-other: 0.2201, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5302, IoU.window-other: 0.4643, IoU.wood: 0.2462, Acc.person: 0.9557, Acc.bicycle: 0.8692, Acc.car: 0.8730, Acc.motorcycle: 0.9091, Acc.airplane: 0.9413, Acc.bus: 0.9237, Acc.train: 0.9651, Acc.truck: 0.8508, Acc.boat: 0.8600, Acc.traffic light: 0.8626, Acc.fire hydrant: 0.9772, Acc.stop sign: 0.9801, Acc.parking meter: 0.8692, Acc.bench: 0.7422, Acc.bird: 0.9062, Acc.cat: 0.9118, Acc.dog: 0.9011, Acc.horse: 0.9473, Acc.sheep: 0.9648, Acc.cow: 0.9315, Acc.elephant: 0.9804, Acc.bear: 0.9712, Acc.zebra: 0.9737, Acc.giraffe: 0.9517, Acc.backpack: 0.6394, Acc.umbrella: 0.9131, Acc.handbag: 0.5234, Acc.tie: 0.0451, Acc.suitcase: 0.9346, Acc.frisbee: 0.8848, Acc.skis: 0.4174, Acc.snowboard: 0.7528, Acc.sports ball: 0.6588, Acc.kite: 0.8763, Acc.baseball bat: 0.7525, Acc.baseball glove: 0.8449, Acc.skateboard: 0.9071, Acc.surfboard: 0.8781, Acc.tennis racket: 0.9304, Acc.bottle: 0.6718, Acc.wine glass: 0.8329, Acc.cup: 0.8054, Acc.fork: 0.6209, Acc.knife: 0.4978, Acc.spoon: 0.5482, Acc.bowl: 0.6343, Acc.banana: 0.9258, Acc.apple: 0.7827, Acc.sandwich: 0.7905, Acc.orange: 0.8402, Acc.broccoli: 0.7928, Acc.carrot: 0.7651, Acc.hot dog: 0.7513, Acc.pizza: 0.9290, Acc.donut: 0.9444, Acc.cake: 0.8613, Acc.chair: 0.7609, Acc.couch: 0.8111, Acc.potted plant: 0.4852, Acc.bed: 0.8326, Acc.dining table: 0.7112, Acc.toilet: 0.9633, Acc.tv: 0.8354, Acc.laptop: 0.9537, Acc.mouse: 0.7586, Acc.remote: 0.7475, Acc.keyboard: 0.7090, Acc.cell phone: 0.8761, Acc.microwave: 0.8294, Acc.oven: 0.8649, Acc.toaster: 0.4019, Acc.sink: 0.8713, Acc.refrigerator: 0.9306, Acc.book: 0.6819, Acc.clock: 0.8168, Acc.vase: 0.8177, Acc.scissors: 0.9223, Acc.teddy bear: 0.9373, Acc.hair drier: 0.1074, Acc.toothbrush: 0.6782, Acc.banner: 0.7198, Acc.blanket: 0.0023, Acc.branch: 0.1638, Acc.bridge: 0.5695, Acc.building-other: 0.7209, Acc.bush: 0.4087, Acc.cabinet: 0.7788, Acc.cage: 0.4700, Acc.cardboard: 0.6250, Acc.carpet: 0.7933, Acc.ceiling-other: 0.8448, Acc.ceiling-tile: 0.0000, Acc.cloth: 0.0005, Acc.clothes: 0.1899, Acc.clouds: 0.7384, Acc.counter: 0.5981, Acc.cupboard: 0.0000, Acc.curtain: 0.8306, Acc.desk-stuff: 0.7053, Acc.dirt: 0.6452, Acc.door-stuff: 0.7271, Acc.fence: 0.5281, Acc.floor-marble: 0.1063, Acc.floor-other: 0.2611, Acc.floor-stone: 0.0983, Acc.floor-tile: 0.7438, Acc.floor-wood: 0.7793, Acc.flower: 0.5564, Acc.fog: 0.1582, Acc.food-other: 0.3847, Acc.fruit: 0.6004, Acc.furniture-other: 0.1573, Acc.grass: 0.8410, Acc.gravel: 0.3171, Acc.ground-other: 0.0306, Acc.hill: 0.3252, Acc.house: 0.3427, Acc.leaves: 0.4260, Acc.light: 0.5631, Acc.mat: 0.0000, Acc.metal: 0.3950, Acc.mirror-stuff: 0.7346, Acc.moss: 0.0000, Acc.mountain: 0.6876, Acc.mud: 0.1854, Acc.napkin: 0.0573, Acc.net: 0.6963, Acc.paper: 0.4395, Acc.pavement: 0.6507, Acc.pillow: 0.1078, Acc.plant-other: 0.2155, Acc.plastic: 0.3018, Acc.platform: 0.5229, Acc.playingfield: 0.8969, Acc.railing: 0.1697, Acc.railroad: 0.8605, Acc.river: 0.7830, Acc.road: 0.8514, Acc.rock: 0.6552, Acc.roof: 0.2517, Acc.rug: 0.3465, Acc.salad: 0.0309, Acc.sand: 0.6862, Acc.sea: 0.9391, Acc.shelf: 0.4985, Acc.sky-other: 0.8308, Acc.skyscraper: 0.6508, Acc.snow: 0.9543, Acc.solid-other: 0.0000, Acc.stairs: 0.5603, Acc.stone: 0.2280, Acc.straw: 0.3437, Acc.structural-other: 0.0042, Acc.table: 0.2517, Acc.tent: 0.1247, Acc.textile-other: 0.1906, Acc.towel: 0.4042, Acc.tree: 0.8968, Acc.vegetable: 0.5192, Acc.wall-brick: 0.6648, Acc.wall-concrete: 0.7950, Acc.wall-other: 0.2796, Acc.wall-panel: 0.0306, Acc.wall-stone: 0.3218, Acc.wall-tile: 0.8366, Acc.wall-wood: 0.5549, Acc.water-other: 0.2686, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6667, Acc.window-other: 0.7254, Acc.wood: 0.3210 2022-04-19 06:23:34,294 - mmseg - INFO - Iter [24050/80000] lr: 1.004e-06, eta: 15:16:28, time: 5.621, data_time: 4.702, memory: 73037, decode.loss_ce: 0.7327, decode.acc_seg: 62.9404, aux.loss_ce: 0.3345, aux.acc_seg: 61.9033, loss: 1.0672 2022-04-19 06:24:20,893 - mmseg - INFO - Iter [24100/80000] lr: 1.003e-06, eta: 15:15:33, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7217, decode.acc_seg: 63.9071, aux.loss_ce: 0.3262, aux.acc_seg: 62.7813, loss: 1.0479 2022-04-19 06:25:07,578 - mmseg - INFO - Iter [24150/80000] lr: 1.002e-06, eta: 15:14:38, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7918, decode.acc_seg: 61.3594, aux.loss_ce: 0.3528, aux.acc_seg: 60.2538, loss: 1.1445 2022-04-19 06:25:54,268 - mmseg - INFO - Iter [24200/80000] lr: 1.001e-06, eta: 15:13:44, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6763, decode.acc_seg: 63.8167, aux.loss_ce: 0.3071, aux.acc_seg: 62.6992, loss: 0.9834 2022-04-19 06:26:40,869 - mmseg - INFO - Iter [24250/80000] lr: 1.001e-06, eta: 15:12:49, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.8062, decode.acc_seg: 62.2316, aux.loss_ce: 0.3559, aux.acc_seg: 61.3294, loss: 1.1621 2022-04-19 06:27:27,390 - mmseg - INFO - Iter [24300/80000] lr: 9.997e-07, eta: 15:11:54, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7420, decode.acc_seg: 62.7417, aux.loss_ce: 0.3385, aux.acc_seg: 61.5564, loss: 1.0805 2022-04-19 06:28:13,867 - mmseg - INFO - Iter [24350/80000] lr: 9.988e-07, eta: 15:10:58, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7064, decode.acc_seg: 63.3329, aux.loss_ce: 0.3165, aux.acc_seg: 62.1656, loss: 1.0229 2022-04-19 06:29:00,713 - mmseg - INFO - Iter [24400/80000] lr: 9.979e-07, eta: 15:10:04, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7665, decode.acc_seg: 61.4694, aux.loss_ce: 0.3410, aux.acc_seg: 60.7490, loss: 1.1075 2022-04-19 06:29:47,457 - mmseg - INFO - Iter [24450/80000] lr: 9.970e-07, eta: 15:09:10, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7479, decode.acc_seg: 61.8163, aux.loss_ce: 0.3335, aux.acc_seg: 61.1576, loss: 1.0814 2022-04-19 06:30:34,120 - mmseg - INFO - Iter [24500/80000] lr: 9.961e-07, eta: 15:08:15, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7140, decode.acc_seg: 64.1609, aux.loss_ce: 0.3195, aux.acc_seg: 63.0576, loss: 1.0335 2022-04-19 06:31:20,740 - mmseg - INFO - Iter [24550/80000] lr: 9.952e-07, eta: 15:07:20, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7340, decode.acc_seg: 63.4394, aux.loss_ce: 0.3300, aux.acc_seg: 62.5552, loss: 1.0640 2022-04-19 06:32:07,428 - mmseg - INFO - Iter [24600/80000] lr: 9.943e-07, eta: 15:06:26, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7261, decode.acc_seg: 63.2095, aux.loss_ce: 0.3241, aux.acc_seg: 62.2724, loss: 1.0502 2022-04-19 06:32:53,764 - mmseg - INFO - Iter [24650/80000] lr: 9.934e-07, eta: 15:05:31, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7047, decode.acc_seg: 63.6202, aux.loss_ce: 0.3152, aux.acc_seg: 62.7438, loss: 1.0199 2022-04-19 06:33:40,345 - mmseg - INFO - Iter [24700/80000] lr: 9.925e-07, eta: 15:04:36, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7486, decode.acc_seg: 64.2737, aux.loss_ce: 0.3382, aux.acc_seg: 63.0094, loss: 1.0868 2022-04-19 06:34:26,664 - mmseg - INFO - Iter [24750/80000] lr: 9.916e-07, eta: 15:03:41, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7329, decode.acc_seg: 63.1723, aux.loss_ce: 0.3252, aux.acc_seg: 62.3411, loss: 1.0581 2022-04-19 06:35:13,260 - mmseg - INFO - Iter [24800/80000] lr: 9.907e-07, eta: 15:02:46, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7379, decode.acc_seg: 62.9539, aux.loss_ce: 0.3318, aux.acc_seg: 62.1785, loss: 1.0698 2022-04-19 06:36:00,234 - mmseg - INFO - Iter [24850/80000] lr: 9.898e-07, eta: 15:01:52, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7596, decode.acc_seg: 61.0330, aux.loss_ce: 0.3370, aux.acc_seg: 60.2180, loss: 1.0965 2022-04-19 06:36:46,581 - mmseg - INFO - Iter [24900/80000] lr: 9.889e-07, eta: 15:00:57, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7183, decode.acc_seg: 63.3199, aux.loss_ce: 0.3231, aux.acc_seg: 62.2377, loss: 1.0414 2022-04-19 06:37:33,024 - mmseg - INFO - Iter [24950/80000] lr: 9.880e-07, eta: 15:00:03, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7302, decode.acc_seg: 64.0524, aux.loss_ce: 0.3280, aux.acc_seg: 63.0006, loss: 1.0582 2022-04-19 06:38:19,659 - mmseg - INFO - Saving checkpoint at 25000 iterations 2022-04-19 06:38:30,075 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 06:38:30,076 - mmseg - INFO - Iter [25000/80000] lr: 9.871e-07, eta: 14:59:31, time: 1.141, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7451, decode.acc_seg: 62.7717, aux.loss_ce: 0.3360, aux.acc_seg: 61.6929, loss: 1.0811 2022-04-19 06:39:17,277 - mmseg - INFO - Iter [25050/80000] lr: 9.862e-07, eta: 14:58:38, time: 0.944, data_time: 0.009, memory: 73037, decode.loss_ce: 0.7396, decode.acc_seg: 61.1470, aux.loss_ce: 0.3316, aux.acc_seg: 60.2547, loss: 1.0711 2022-04-19 06:40:04,139 - mmseg - INFO - Iter [25100/80000] lr: 9.853e-07, eta: 14:57:44, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7541, decode.acc_seg: 62.5890, aux.loss_ce: 0.3371, aux.acc_seg: 61.6564, loss: 1.0912 2022-04-19 06:40:50,984 - mmseg - INFO - Iter [25150/80000] lr: 9.844e-07, eta: 14:56:50, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7691, decode.acc_seg: 62.4361, aux.loss_ce: 0.3505, aux.acc_seg: 60.9517, loss: 1.1197 2022-04-19 06:41:37,858 - mmseg - INFO - Iter [25200/80000] lr: 9.835e-07, eta: 14:55:56, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7082, decode.acc_seg: 63.1694, aux.loss_ce: 0.3173, aux.acc_seg: 62.2233, loss: 1.0254 2022-04-19 06:42:24,464 - mmseg - INFO - Iter [25250/80000] lr: 9.826e-07, eta: 14:55:02, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7342, decode.acc_seg: 62.9641, aux.loss_ce: 0.3294, aux.acc_seg: 62.0673, loss: 1.0636 2022-04-19 06:43:10,945 - mmseg - INFO - Iter [25300/80000] lr: 9.817e-07, eta: 14:54:08, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7097, decode.acc_seg: 63.1189, aux.loss_ce: 0.3202, aux.acc_seg: 62.2467, loss: 1.0298 2022-04-19 06:43:58,088 - mmseg - INFO - Iter [25350/80000] lr: 9.808e-07, eta: 14:53:14, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7611, decode.acc_seg: 61.3756, aux.loss_ce: 0.3423, aux.acc_seg: 60.2666, loss: 1.1033 2022-04-19 06:44:44,867 - mmseg - INFO - Iter [25400/80000] lr: 9.799e-07, eta: 14:52:21, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7308, decode.acc_seg: 63.5603, aux.loss_ce: 0.3286, aux.acc_seg: 62.5897, loss: 1.0594 2022-04-19 06:45:31,478 - mmseg - INFO - Iter [25450/80000] lr: 9.791e-07, eta: 14:51:26, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7593, decode.acc_seg: 62.9448, aux.loss_ce: 0.3361, aux.acc_seg: 62.1252, loss: 1.0953 2022-04-19 06:46:18,589 - mmseg - INFO - Iter [25500/80000] lr: 9.782e-07, eta: 14:50:33, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7125, decode.acc_seg: 63.9229, aux.loss_ce: 0.3197, aux.acc_seg: 62.8978, loss: 1.0322 2022-04-19 06:47:05,468 - mmseg - INFO - Iter [25550/80000] lr: 9.773e-07, eta: 14:49:40, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7370, decode.acc_seg: 63.1887, aux.loss_ce: 0.3324, aux.acc_seg: 61.7116, loss: 1.0694 2022-04-19 06:47:52,036 - mmseg - INFO - Iter [25600/80000] lr: 9.764e-07, eta: 14:48:45, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7286, decode.acc_seg: 63.3685, aux.loss_ce: 0.3280, aux.acc_seg: 62.3684, loss: 1.0566 2022-04-19 06:48:38,702 - mmseg - INFO - Iter [25650/80000] lr: 9.755e-07, eta: 14:47:51, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7148, decode.acc_seg: 63.2276, aux.loss_ce: 0.3205, aux.acc_seg: 61.9465, loss: 1.0353 2022-04-19 06:49:25,296 - mmseg - INFO - Iter [25700/80000] lr: 9.746e-07, eta: 14:46:57, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7578, decode.acc_seg: 63.1984, aux.loss_ce: 0.3390, aux.acc_seg: 62.3601, loss: 1.0968 2022-04-19 06:50:11,778 - mmseg - INFO - Iter [25750/80000] lr: 9.737e-07, eta: 14:46:03, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7480, decode.acc_seg: 62.8867, aux.loss_ce: 0.3343, aux.acc_seg: 61.6524, loss: 1.0823 2022-04-19 06:50:58,215 - mmseg - INFO - Iter [25800/80000] lr: 9.728e-07, eta: 14:45:09, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7576, decode.acc_seg: 62.6250, aux.loss_ce: 0.3379, aux.acc_seg: 61.3059, loss: 1.0955 2022-04-19 06:51:44,753 - mmseg - INFO - Iter [25850/80000] lr: 9.719e-07, eta: 14:44:14, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6794, decode.acc_seg: 64.5332, aux.loss_ce: 0.3031, aux.acc_seg: 63.5404, loss: 0.9825 2022-04-19 06:52:31,441 - mmseg - INFO - Iter [25900/80000] lr: 9.710e-07, eta: 14:43:21, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7563, decode.acc_seg: 62.1909, aux.loss_ce: 0.3359, aux.acc_seg: 60.8106, loss: 1.0922 2022-04-19 06:53:18,166 - mmseg - INFO - Iter [25950/80000] lr: 9.701e-07, eta: 14:42:27, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7353, decode.acc_seg: 64.1146, aux.loss_ce: 0.3317, aux.acc_seg: 62.9832, loss: 1.0670 2022-04-19 06:54:04,552 - mmseg - INFO - Saving checkpoint at 26000 iterations 2022-04-19 06:54:15,439 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 06:54:15,440 - mmseg - INFO - Iter [26000/80000] lr: 9.692e-07, eta: 14:41:55, time: 1.145, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7405, decode.acc_seg: 62.5754, aux.loss_ce: 0.3295, aux.acc_seg: 61.4759, loss: 1.0700 2022-04-19 06:55:02,061 - mmseg - INFO - Iter [26050/80000] lr: 9.683e-07, eta: 14:41:01, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6983, decode.acc_seg: 63.9036, aux.loss_ce: 0.3141, aux.acc_seg: 62.9554, loss: 1.0124 2022-04-19 06:55:48,544 - mmseg - INFO - Iter [26100/80000] lr: 9.674e-07, eta: 14:40:07, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7085, decode.acc_seg: 62.8426, aux.loss_ce: 0.3205, aux.acc_seg: 61.7239, loss: 1.0290 2022-04-19 06:56:34,899 - mmseg - INFO - Iter [26150/80000] lr: 9.665e-07, eta: 14:39:13, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7237, decode.acc_seg: 63.7352, aux.loss_ce: 0.3226, aux.acc_seg: 62.6591, loss: 1.0462 2022-04-19 06:57:21,463 - mmseg - INFO - Iter [26200/80000] lr: 9.656e-07, eta: 14:38:19, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7173, decode.acc_seg: 63.9747, aux.loss_ce: 0.3230, aux.acc_seg: 63.0216, loss: 1.0403 2022-04-19 06:58:08,282 - mmseg - INFO - Iter [26250/80000] lr: 9.647e-07, eta: 14:37:25, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7434, decode.acc_seg: 63.4289, aux.loss_ce: 0.3352, aux.acc_seg: 62.4008, loss: 1.0787 2022-04-19 06:58:54,636 - mmseg - INFO - Iter [26300/80000] lr: 9.638e-07, eta: 14:36:31, time: 0.929, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7176, decode.acc_seg: 63.0236, aux.loss_ce: 0.3182, aux.acc_seg: 62.2383, loss: 1.0358 2022-04-19 06:59:41,237 - mmseg - INFO - Iter [26350/80000] lr: 9.629e-07, eta: 14:35:37, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7382, decode.acc_seg: 62.0843, aux.loss_ce: 0.3299, aux.acc_seg: 60.9840, loss: 1.0680 2022-04-19 07:00:27,779 - mmseg - INFO - Iter [26400/80000] lr: 9.620e-07, eta: 14:34:43, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7454, decode.acc_seg: 62.7203, aux.loss_ce: 0.3314, aux.acc_seg: 61.7352, loss: 1.0768 2022-04-19 07:01:14,465 - mmseg - INFO - Iter [26450/80000] lr: 9.611e-07, eta: 14:33:50, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7419, decode.acc_seg: 61.3567, aux.loss_ce: 0.3342, aux.acc_seg: 60.3809, loss: 1.0761 2022-04-19 07:02:00,803 - mmseg - INFO - Iter [26500/80000] lr: 9.602e-07, eta: 14:32:56, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7562, decode.acc_seg: 61.3509, aux.loss_ce: 0.3385, aux.acc_seg: 60.5720, loss: 1.0947 2022-04-19 07:02:47,373 - mmseg - INFO - Iter [26550/80000] lr: 9.593e-07, eta: 14:32:02, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7314, decode.acc_seg: 61.2876, aux.loss_ce: 0.3243, aux.acc_seg: 60.5081, loss: 1.0557 2022-04-19 07:03:33,895 - mmseg - INFO - Iter [26600/80000] lr: 9.584e-07, eta: 14:31:08, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7171, decode.acc_seg: 62.4806, aux.loss_ce: 0.3215, aux.acc_seg: 60.9593, loss: 1.0386 2022-04-19 07:04:20,417 - mmseg - INFO - Iter [26650/80000] lr: 9.575e-07, eta: 14:30:14, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7413, decode.acc_seg: 62.2153, aux.loss_ce: 0.3303, aux.acc_seg: 61.1593, loss: 1.0715 2022-04-19 07:05:06,790 - mmseg - INFO - Iter [26700/80000] lr: 9.566e-07, eta: 14:29:20, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7595, decode.acc_seg: 61.5584, aux.loss_ce: 0.3349, aux.acc_seg: 60.7858, loss: 1.0944 2022-04-19 07:05:53,236 - mmseg - INFO - Iter [26750/80000] lr: 9.557e-07, eta: 14:28:26, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7162, decode.acc_seg: 62.2221, aux.loss_ce: 0.3223, aux.acc_seg: 60.9487, loss: 1.0385 2022-04-19 07:06:46,258 - mmseg - INFO - Iter [26800/80000] lr: 9.548e-07, eta: 14:27:46, time: 1.060, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7528, decode.acc_seg: 63.4943, aux.loss_ce: 0.3336, aux.acc_seg: 62.7521, loss: 1.0865 2022-04-19 07:07:33,195 - mmseg - INFO - Iter [26850/80000] lr: 9.539e-07, eta: 14:26:53, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7516, decode.acc_seg: 62.7645, aux.loss_ce: 0.3378, aux.acc_seg: 61.5679, loss: 1.0894 2022-04-19 07:08:20,077 - mmseg - INFO - Iter [26900/80000] lr: 9.530e-07, eta: 14:26:00, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7312, decode.acc_seg: 61.8485, aux.loss_ce: 0.3236, aux.acc_seg: 61.2431, loss: 1.0548 2022-04-19 07:09:06,702 - mmseg - INFO - Iter [26950/80000] lr: 9.521e-07, eta: 14:25:06, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7467, decode.acc_seg: 62.9063, aux.loss_ce: 0.3301, aux.acc_seg: 62.0374, loss: 1.0769 2022-04-19 07:09:53,151 - mmseg - INFO - Saving checkpoint at 27000 iterations 2022-04-19 07:10:05,656 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 07:10:05,664 - mmseg - INFO - Iter [27000/80000] lr: 9.512e-07, eta: 14:24:37, time: 1.180, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7372, decode.acc_seg: 62.5436, aux.loss_ce: 0.3285, aux.acc_seg: 61.4238, loss: 1.0657 2022-04-19 07:10:52,673 - mmseg - INFO - Iter [27050/80000] lr: 9.503e-07, eta: 14:23:44, time: 0.942, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7434, decode.acc_seg: 63.0575, aux.loss_ce: 0.3313, aux.acc_seg: 62.1217, loss: 1.0746 2022-04-19 07:11:39,177 - mmseg - INFO - Iter [27100/80000] lr: 9.494e-07, eta: 14:22:51, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7620, decode.acc_seg: 59.8712, aux.loss_ce: 0.3351, aux.acc_seg: 59.0264, loss: 1.0971 2022-04-19 07:12:25,598 - mmseg - INFO - Iter [27150/80000] lr: 9.485e-07, eta: 14:21:57, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7429, decode.acc_seg: 63.2841, aux.loss_ce: 0.3349, aux.acc_seg: 61.8589, loss: 1.0778 2022-04-19 07:13:12,250 - mmseg - INFO - Iter [27200/80000] lr: 9.476e-07, eta: 14:21:03, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7142, decode.acc_seg: 62.7391, aux.loss_ce: 0.3186, aux.acc_seg: 62.0227, loss: 1.0328 2022-04-19 07:13:58,898 - mmseg - INFO - Iter [27250/80000] lr: 9.467e-07, eta: 14:20:10, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7382, decode.acc_seg: 63.3154, aux.loss_ce: 0.3303, aux.acc_seg: 62.7389, loss: 1.0684 2022-04-19 07:14:45,589 - mmseg - INFO - Iter [27300/80000] lr: 9.458e-07, eta: 14:19:17, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7303, decode.acc_seg: 63.0271, aux.loss_ce: 0.3240, aux.acc_seg: 61.9615, loss: 1.0542 2022-04-19 07:15:32,251 - mmseg - INFO - Iter [27350/80000] lr: 9.450e-07, eta: 14:18:24, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7730, decode.acc_seg: 61.6091, aux.loss_ce: 0.3400, aux.acc_seg: 61.1485, loss: 1.1130 2022-04-19 07:16:18,969 - mmseg - INFO - Iter [27400/80000] lr: 9.441e-07, eta: 14:17:30, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7602, decode.acc_seg: 62.7310, aux.loss_ce: 0.3362, aux.acc_seg: 61.4968, loss: 1.0965 2022-04-19 07:17:05,808 - mmseg - INFO - Iter [27450/80000] lr: 9.432e-07, eta: 14:16:38, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7564, decode.acc_seg: 62.3629, aux.loss_ce: 0.3398, aux.acc_seg: 61.5287, loss: 1.0963 2022-04-19 07:17:52,507 - mmseg - INFO - Iter [27500/80000] lr: 9.423e-07, eta: 14:15:44, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7594, decode.acc_seg: 62.4391, aux.loss_ce: 0.3409, aux.acc_seg: 61.7933, loss: 1.1003 2022-04-19 07:18:39,121 - mmseg - INFO - Iter [27550/80000] lr: 9.414e-07, eta: 14:14:51, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7209, decode.acc_seg: 63.1827, aux.loss_ce: 0.3234, aux.acc_seg: 62.3938, loss: 1.0443 2022-04-19 07:19:25,988 - mmseg - INFO - Iter [27600/80000] lr: 9.405e-07, eta: 14:13:58, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7262, decode.acc_seg: 62.8047, aux.loss_ce: 0.3224, aux.acc_seg: 61.5715, loss: 1.0486 2022-04-19 07:20:12,716 - mmseg - INFO - Iter [27650/80000] lr: 9.396e-07, eta: 14:13:05, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7243, decode.acc_seg: 63.5758, aux.loss_ce: 0.3220, aux.acc_seg: 62.5954, loss: 1.0463 2022-04-19 07:20:59,249 - mmseg - INFO - Iter [27700/80000] lr: 9.387e-07, eta: 14:12:12, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7374, decode.acc_seg: 64.3570, aux.loss_ce: 0.3278, aux.acc_seg: 63.9002, loss: 1.0652 2022-04-19 07:21:46,057 - mmseg - INFO - Iter [27750/80000] lr: 9.378e-07, eta: 14:11:19, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7578, decode.acc_seg: 62.2479, aux.loss_ce: 0.3351, aux.acc_seg: 61.3995, loss: 1.0929 2022-04-19 07:22:32,577 - mmseg - INFO - Iter [27800/80000] lr: 9.369e-07, eta: 14:10:26, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7106, decode.acc_seg: 62.3453, aux.loss_ce: 0.3189, aux.acc_seg: 61.1825, loss: 1.0295 2022-04-19 07:23:19,162 - mmseg - INFO - Iter [27850/80000] lr: 9.360e-07, eta: 14:09:33, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7233, decode.acc_seg: 63.2217, aux.loss_ce: 0.3217, aux.acc_seg: 62.5563, loss: 1.0450 2022-04-19 07:24:05,720 - mmseg - INFO - Iter [27900/80000] lr: 9.351e-07, eta: 14:08:40, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7200, decode.acc_seg: 64.1739, aux.loss_ce: 0.3189, aux.acc_seg: 63.1738, loss: 1.0389 2022-04-19 07:24:52,546 - mmseg - INFO - Iter [27950/80000] lr: 9.342e-07, eta: 14:07:47, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7533, decode.acc_seg: 62.4499, aux.loss_ce: 0.3358, aux.acc_seg: 61.5296, loss: 1.0891 2022-04-19 07:25:38,975 - mmseg - INFO - Saving checkpoint at 28000 iterations 2022-04-19 07:25:50,760 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 07:25:50,760 - mmseg - INFO - Iter [28000/80000] lr: 9.333e-07, eta: 14:07:15, time: 1.162, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7663, decode.acc_seg: 63.4081, aux.loss_ce: 0.3392, aux.acc_seg: 62.7817, loss: 1.1056 2022-04-19 07:26:37,877 - mmseg - INFO - Iter [28050/80000] lr: 9.324e-07, eta: 14:06:23, time: 0.944, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7318, decode.acc_seg: 63.0777, aux.loss_ce: 0.3273, aux.acc_seg: 62.2395, loss: 1.0590 2022-04-19 07:27:24,606 - mmseg - INFO - Iter [28100/80000] lr: 9.315e-07, eta: 14:05:31, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7601, decode.acc_seg: 61.7812, aux.loss_ce: 0.3384, aux.acc_seg: 60.7800, loss: 1.0985 2022-04-19 07:28:11,073 - mmseg - INFO - Iter [28150/80000] lr: 9.306e-07, eta: 14:04:37, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7418, decode.acc_seg: 62.4964, aux.loss_ce: 0.3327, aux.acc_seg: 61.5723, loss: 1.0745 2022-04-19 07:28:57,789 - mmseg - INFO - Iter [28200/80000] lr: 9.297e-07, eta: 14:03:44, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7511, decode.acc_seg: 62.0612, aux.loss_ce: 0.3331, aux.acc_seg: 61.3292, loss: 1.0842 2022-04-19 07:29:44,448 - mmseg - INFO - Iter [28250/80000] lr: 9.288e-07, eta: 14:02:51, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7793, decode.acc_seg: 62.1790, aux.loss_ce: 0.3406, aux.acc_seg: 61.9261, loss: 1.1199 2022-04-19 07:30:31,670 - mmseg - INFO - Iter [28300/80000] lr: 9.279e-07, eta: 14:02:00, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7219, decode.acc_seg: 63.3339, aux.loss_ce: 0.3204, aux.acc_seg: 62.2822, loss: 1.0423 2022-04-19 07:31:18,530 - mmseg - INFO - Iter [28350/80000] lr: 9.270e-07, eta: 14:01:07, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7089, decode.acc_seg: 63.7778, aux.loss_ce: 0.3173, aux.acc_seg: 62.8030, loss: 1.0262 2022-04-19 07:32:05,280 - mmseg - INFO - Iter [28400/80000] lr: 9.261e-07, eta: 14:00:14, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6964, decode.acc_seg: 63.3305, aux.loss_ce: 0.3118, aux.acc_seg: 62.5267, loss: 1.0082 2022-04-19 07:32:51,676 - mmseg - INFO - Iter [28450/80000] lr: 9.252e-07, eta: 13:59:21, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7650, decode.acc_seg: 61.4311, aux.loss_ce: 0.3355, aux.acc_seg: 60.8956, loss: 1.1004 2022-04-19 07:33:38,591 - mmseg - INFO - Iter [28500/80000] lr: 9.243e-07, eta: 13:58:29, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7086, decode.acc_seg: 63.1119, aux.loss_ce: 0.3135, aux.acc_seg: 62.4008, loss: 1.0221 2022-04-19 07:34:25,052 - mmseg - INFO - Iter [28550/80000] lr: 9.234e-07, eta: 13:57:36, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7758, decode.acc_seg: 61.9638, aux.loss_ce: 0.3436, aux.acc_seg: 61.1232, loss: 1.1194 2022-04-19 07:35:11,529 - mmseg - INFO - Iter [28600/80000] lr: 9.225e-07, eta: 13:56:43, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7060, decode.acc_seg: 63.7582, aux.loss_ce: 0.3178, aux.acc_seg: 62.3898, loss: 1.0238 2022-04-19 07:35:58,553 - mmseg - INFO - Iter [28650/80000] lr: 9.216e-07, eta: 13:55:50, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7425, decode.acc_seg: 62.9988, aux.loss_ce: 0.3328, aux.acc_seg: 62.2318, loss: 1.0753 2022-04-19 07:36:45,202 - mmseg - INFO - Iter [28700/80000] lr: 9.207e-07, eta: 13:54:58, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7615, decode.acc_seg: 62.0921, aux.loss_ce: 0.3383, aux.acc_seg: 61.2645, loss: 1.0998 2022-04-19 07:37:31,981 - mmseg - INFO - Iter [28750/80000] lr: 9.198e-07, eta: 13:54:05, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6883, decode.acc_seg: 63.4731, aux.loss_ce: 0.3051, aux.acc_seg: 62.2518, loss: 0.9934 2022-04-19 07:38:18,907 - mmseg - INFO - Iter [28800/80000] lr: 9.189e-07, eta: 13:53:13, time: 0.938, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7217, decode.acc_seg: 62.4922, aux.loss_ce: 0.3228, aux.acc_seg: 61.2755, loss: 1.0445 2022-04-19 07:39:05,539 - mmseg - INFO - Iter [28850/80000] lr: 9.180e-07, eta: 13:52:20, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7271, decode.acc_seg: 62.7902, aux.loss_ce: 0.3205, aux.acc_seg: 62.3252, loss: 1.0477 2022-04-19 07:39:52,305 - mmseg - INFO - Iter [28900/80000] lr: 9.171e-07, eta: 13:51:28, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7109, decode.acc_seg: 64.2723, aux.loss_ce: 0.3190, aux.acc_seg: 63.1331, loss: 1.0299 2022-04-19 07:40:38,929 - mmseg - INFO - Iter [28950/80000] lr: 9.162e-07, eta: 13:50:35, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7332, decode.acc_seg: 63.6698, aux.loss_ce: 0.3214, aux.acc_seg: 62.9696, loss: 1.0546 2022-04-19 07:41:25,597 - mmseg - INFO - Saving checkpoint at 29000 iterations 2022-04-19 07:41:40,642 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 07:41:40,652 - mmseg - INFO - Iter [29000/80000] lr: 9.153e-07, eta: 13:50:09, time: 1.233, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7829, decode.acc_seg: 62.5995, aux.loss_ce: 0.3455, aux.acc_seg: 61.7670, loss: 1.1285 2022-04-19 07:42:27,686 - mmseg - INFO - Iter [29050/80000] lr: 9.144e-07, eta: 13:49:17, time: 0.942, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7564, decode.acc_seg: 63.9530, aux.loss_ce: 0.3380, aux.acc_seg: 62.8865, loss: 1.0944 2022-04-19 07:43:14,782 - mmseg - INFO - Iter [29100/80000] lr: 9.135e-07, eta: 13:48:25, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7146, decode.acc_seg: 62.1376, aux.loss_ce: 0.3185, aux.acc_seg: 61.2370, loss: 1.0331 2022-04-19 07:44:01,315 - mmseg - INFO - Iter [29150/80000] lr: 9.126e-07, eta: 13:47:32, time: 0.933, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7237, decode.acc_seg: 64.4464, aux.loss_ce: 0.3207, aux.acc_seg: 63.7640, loss: 1.0445 2022-04-19 07:44:47,803 - mmseg - INFO - Iter [29200/80000] lr: 9.117e-07, eta: 13:46:40, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7228, decode.acc_seg: 64.4095, aux.loss_ce: 0.3225, aux.acc_seg: 63.4526, loss: 1.0453 2022-04-19 07:45:34,354 - mmseg - INFO - Iter [29250/80000] lr: 9.109e-07, eta: 13:45:47, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7121, decode.acc_seg: 63.5354, aux.loss_ce: 0.3196, aux.acc_seg: 62.3751, loss: 1.0317 2022-04-19 07:46:21,072 - mmseg - INFO - Iter [29300/80000] lr: 9.100e-07, eta: 13:44:54, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7436, decode.acc_seg: 62.9561, aux.loss_ce: 0.3333, aux.acc_seg: 61.7513, loss: 1.0769 2022-04-19 07:47:07,938 - mmseg - INFO - Iter [29350/80000] lr: 9.091e-07, eta: 13:44:02, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7175, decode.acc_seg: 63.8995, aux.loss_ce: 0.3229, aux.acc_seg: 62.7057, loss: 1.0403 2022-04-19 07:47:54,761 - mmseg - INFO - Iter [29400/80000] lr: 9.082e-07, eta: 13:43:10, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7507, decode.acc_seg: 62.7307, aux.loss_ce: 0.3309, aux.acc_seg: 61.7257, loss: 1.0815 2022-04-19 07:48:41,375 - mmseg - INFO - Iter [29450/80000] lr: 9.073e-07, eta: 13:42:17, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7550, decode.acc_seg: 62.8614, aux.loss_ce: 0.3355, aux.acc_seg: 61.8039, loss: 1.0905 2022-04-19 07:49:28,263 - mmseg - INFO - Iter [29500/80000] lr: 9.064e-07, eta: 13:41:25, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7538, decode.acc_seg: 61.7046, aux.loss_ce: 0.3352, aux.acc_seg: 60.7097, loss: 1.0891 2022-04-19 07:50:15,002 - mmseg - INFO - Iter [29550/80000] lr: 9.055e-07, eta: 13:40:33, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7170, decode.acc_seg: 64.0722, aux.loss_ce: 0.3192, aux.acc_seg: 62.9644, loss: 1.0362 2022-04-19 07:51:05,184 - mmseg - INFO - Iter [29600/80000] lr: 9.046e-07, eta: 13:39:47, time: 1.004, data_time: 0.059, memory: 73037, decode.loss_ce: 0.7220, decode.acc_seg: 62.9568, aux.loss_ce: 0.3223, aux.acc_seg: 61.3229, loss: 1.0443 2022-04-19 07:51:52,095 - mmseg - INFO - Iter [29650/80000] lr: 9.037e-07, eta: 13:38:54, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7200, decode.acc_seg: 63.3674, aux.loss_ce: 0.3173, aux.acc_seg: 62.7091, loss: 1.0374 2022-04-19 07:52:38,924 - mmseg - INFO - Iter [29700/80000] lr: 9.028e-07, eta: 13:38:02, time: 0.938, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7353, decode.acc_seg: 63.5269, aux.loss_ce: 0.3282, aux.acc_seg: 62.2706, loss: 1.0636 2022-04-19 07:53:26,113 - mmseg - INFO - Iter [29750/80000] lr: 9.019e-07, eta: 13:37:11, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7466, decode.acc_seg: 62.4821, aux.loss_ce: 0.3332, aux.acc_seg: 61.4022, loss: 1.0797 2022-04-19 07:54:12,816 - mmseg - INFO - Iter [29800/80000] lr: 9.010e-07, eta: 13:36:19, time: 0.936, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6837, decode.acc_seg: 64.8866, aux.loss_ce: 0.3089, aux.acc_seg: 63.9597, loss: 0.9926 2022-04-19 07:54:59,236 - mmseg - INFO - Iter [29850/80000] lr: 9.001e-07, eta: 13:35:26, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6608, decode.acc_seg: 65.2424, aux.loss_ce: 0.2977, aux.acc_seg: 64.3559, loss: 0.9585 2022-04-19 07:55:45,469 - mmseg - INFO - Iter [29900/80000] lr: 8.992e-07, eta: 13:34:33, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7234, decode.acc_seg: 63.3650, aux.loss_ce: 0.3267, aux.acc_seg: 61.7925, loss: 1.0501 2022-04-19 07:56:32,006 - mmseg - INFO - Iter [29950/80000] lr: 8.983e-07, eta: 13:33:40, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7439, decode.acc_seg: 62.8547, aux.loss_ce: 0.3320, aux.acc_seg: 61.7307, loss: 1.0760 2022-04-19 07:57:18,992 - mmseg - INFO - Saving checkpoint at 30000 iterations 2022-04-19 07:57:29,748 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 07:57:29,748 - mmseg - INFO - Iter [30000/80000] lr: 8.974e-07, eta: 13:33:06, time: 1.154, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7175, decode.acc_seg: 63.3329, aux.loss_ce: 0.3225, aux.acc_seg: 62.1187, loss: 1.0401 2022-04-19 07:58:16,760 - mmseg - INFO - Iter [30050/80000] lr: 8.965e-07, eta: 13:32:15, time: 0.941, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7135, decode.acc_seg: 62.6764, aux.loss_ce: 0.3215, aux.acc_seg: 61.2697, loss: 1.0350 2022-04-19 07:59:03,406 - mmseg - INFO - Iter [30100/80000] lr: 8.956e-07, eta: 13:31:22, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7182, decode.acc_seg: 63.1304, aux.loss_ce: 0.3215, aux.acc_seg: 62.2243, loss: 1.0396 2022-04-19 07:59:50,429 - mmseg - INFO - Iter [30150/80000] lr: 8.947e-07, eta: 13:30:31, time: 0.942, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7093, decode.acc_seg: 60.8706, aux.loss_ce: 0.3177, aux.acc_seg: 59.7867, loss: 1.0271 2022-04-19 08:00:37,118 - mmseg - INFO - Iter [30200/80000] lr: 8.938e-07, eta: 13:29:38, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7031, decode.acc_seg: 61.9471, aux.loss_ce: 0.3150, aux.acc_seg: 61.1686, loss: 1.0181 2022-04-19 08:01:23,419 - mmseg - INFO - Iter [30250/80000] lr: 8.929e-07, eta: 13:28:46, time: 0.928, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7149, decode.acc_seg: 63.7290, aux.loss_ce: 0.3231, aux.acc_seg: 62.6166, loss: 1.0380 2022-04-19 08:02:10,116 - mmseg - INFO - Iter [30300/80000] lr: 8.920e-07, eta: 13:27:54, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6922, decode.acc_seg: 63.4462, aux.loss_ce: 0.3107, aux.acc_seg: 62.2589, loss: 1.0028 2022-04-19 08:02:56,588 - mmseg - INFO - Iter [30350/80000] lr: 8.911e-07, eta: 13:27:01, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7258, decode.acc_seg: 64.0121, aux.loss_ce: 0.3276, aux.acc_seg: 62.5060, loss: 1.0533 2022-04-19 08:03:43,632 - mmseg - INFO - Iter [30400/80000] lr: 8.902e-07, eta: 13:26:09, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6854, decode.acc_seg: 63.4225, aux.loss_ce: 0.3105, aux.acc_seg: 62.1502, loss: 0.9958 2022-04-19 08:04:30,285 - mmseg - INFO - Iter [30450/80000] lr: 8.893e-07, eta: 13:25:17, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6953, decode.acc_seg: 62.6911, aux.loss_ce: 0.3159, aux.acc_seg: 61.6902, loss: 1.0112 2022-04-19 08:05:16,914 - mmseg - INFO - Iter [30500/80000] lr: 8.884e-07, eta: 13:24:25, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7214, decode.acc_seg: 63.7657, aux.loss_ce: 0.3194, aux.acc_seg: 63.0932, loss: 1.0408 2022-04-19 08:06:03,611 - mmseg - INFO - Iter [30550/80000] lr: 8.875e-07, eta: 13:23:33, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7182, decode.acc_seg: 63.6550, aux.loss_ce: 0.3132, aux.acc_seg: 62.7805, loss: 1.0314 2022-04-19 08:06:50,020 - mmseg - INFO - Iter [30600/80000] lr: 8.866e-07, eta: 13:22:40, time: 0.929, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7459, decode.acc_seg: 64.2335, aux.loss_ce: 0.3358, aux.acc_seg: 62.8103, loss: 1.0817 2022-04-19 08:07:36,556 - mmseg - INFO - Iter [30650/80000] lr: 8.857e-07, eta: 13:21:48, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7153, decode.acc_seg: 63.2252, aux.loss_ce: 0.3166, aux.acc_seg: 62.2414, loss: 1.0319 2022-04-19 08:08:23,238 - mmseg - INFO - Iter [30700/80000] lr: 8.848e-07, eta: 13:20:56, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6967, decode.acc_seg: 63.7123, aux.loss_ce: 0.3196, aux.acc_seg: 62.1181, loss: 1.0162 2022-04-19 08:09:09,831 - mmseg - INFO - Iter [30750/80000] lr: 8.839e-07, eta: 13:20:04, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6734, decode.acc_seg: 63.9462, aux.loss_ce: 0.3075, aux.acc_seg: 62.6970, loss: 0.9809 2022-04-19 08:09:56,473 - mmseg - INFO - Iter [30800/80000] lr: 8.830e-07, eta: 13:19:12, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6758, decode.acc_seg: 62.9321, aux.loss_ce: 0.3033, aux.acc_seg: 62.0237, loss: 0.9791 2022-04-19 08:10:43,102 - mmseg - INFO - Iter [30850/80000] lr: 8.821e-07, eta: 13:18:20, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6856, decode.acc_seg: 63.7462, aux.loss_ce: 0.3094, aux.acc_seg: 62.2875, loss: 0.9950 2022-04-19 08:11:30,024 - mmseg - INFO - Iter [30900/80000] lr: 8.812e-07, eta: 13:17:28, time: 0.938, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6827, decode.acc_seg: 63.7683, aux.loss_ce: 0.3095, aux.acc_seg: 62.5205, loss: 0.9922 2022-04-19 08:12:16,709 - mmseg - INFO - Iter [30950/80000] lr: 8.803e-07, eta: 13:16:36, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7467, decode.acc_seg: 64.0396, aux.loss_ce: 0.3344, aux.acc_seg: 62.7552, loss: 1.0811 2022-04-19 08:13:03,322 - mmseg - INFO - Saving checkpoint at 31000 iterations 2022-04-19 08:13:13,754 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 08:13:13,754 - mmseg - INFO - Iter [31000/80000] lr: 8.794e-07, eta: 13:16:01, time: 1.141, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6701, decode.acc_seg: 65.3990, aux.loss_ce: 0.3031, aux.acc_seg: 64.3128, loss: 0.9732 2022-04-19 08:14:00,761 - mmseg - INFO - Iter [31050/80000] lr: 8.785e-07, eta: 13:15:09, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6964, decode.acc_seg: 64.1628, aux.loss_ce: 0.3090, aux.acc_seg: 63.4729, loss: 1.0054 2022-04-19 08:14:47,577 - mmseg - INFO - Iter [31100/80000] lr: 8.776e-07, eta: 13:14:17, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7484, decode.acc_seg: 63.4139, aux.loss_ce: 0.3370, aux.acc_seg: 62.1091, loss: 1.0854 2022-04-19 08:15:34,388 - mmseg - INFO - Iter [31150/80000] lr: 8.768e-07, eta: 13:13:26, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6880, decode.acc_seg: 64.4348, aux.loss_ce: 0.3076, aux.acc_seg: 63.7093, loss: 0.9956 2022-04-19 08:16:21,217 - mmseg - INFO - Iter [31200/80000] lr: 8.759e-07, eta: 13:12:34, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7152, decode.acc_seg: 63.5243, aux.loss_ce: 0.3188, aux.acc_seg: 62.1252, loss: 1.0340 2022-04-19 08:17:08,362 - mmseg - INFO - Iter [31250/80000] lr: 8.750e-07, eta: 13:11:43, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6759, decode.acc_seg: 62.3908, aux.loss_ce: 0.3049, aux.acc_seg: 61.3671, loss: 0.9808 2022-04-19 08:17:55,059 - mmseg - INFO - Iter [31300/80000] lr: 8.741e-07, eta: 13:10:51, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6939, decode.acc_seg: 63.6947, aux.loss_ce: 0.3121, aux.acc_seg: 62.5845, loss: 1.0059 2022-04-19 08:18:41,535 - mmseg - INFO - Iter [31350/80000] lr: 8.732e-07, eta: 13:09:59, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7335, decode.acc_seg: 63.8729, aux.loss_ce: 0.3302, aux.acc_seg: 62.8040, loss: 1.0637 2022-04-19 08:19:28,209 - mmseg - INFO - Iter [31400/80000] lr: 8.723e-07, eta: 13:09:07, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7107, decode.acc_seg: 63.4308, aux.loss_ce: 0.3182, aux.acc_seg: 62.1505, loss: 1.0289 2022-04-19 08:20:14,982 - mmseg - INFO - Iter [31450/80000] lr: 8.714e-07, eta: 13:08:15, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6866, decode.acc_seg: 64.0027, aux.loss_ce: 0.3103, aux.acc_seg: 63.0492, loss: 0.9969 2022-04-19 08:21:01,588 - mmseg - INFO - Iter [31500/80000] lr: 8.705e-07, eta: 13:07:23, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6913, decode.acc_seg: 63.9356, aux.loss_ce: 0.3084, aux.acc_seg: 62.5187, loss: 0.9996 2022-04-19 08:21:48,300 - mmseg - INFO - Iter [31550/80000] lr: 8.696e-07, eta: 13:06:31, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6987, decode.acc_seg: 63.5556, aux.loss_ce: 0.3128, aux.acc_seg: 62.7215, loss: 1.0115 2022-04-19 08:22:35,217 - mmseg - INFO - Iter [31600/80000] lr: 8.687e-07, eta: 13:05:40, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7110, decode.acc_seg: 63.1244, aux.loss_ce: 0.3120, aux.acc_seg: 62.5008, loss: 1.0230 2022-04-19 08:23:22,333 - mmseg - INFO - Iter [31650/80000] lr: 8.678e-07, eta: 13:04:49, time: 0.944, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6934, decode.acc_seg: 64.6337, aux.loss_ce: 0.3112, aux.acc_seg: 63.4408, loss: 1.0046 2022-04-19 08:24:09,098 - mmseg - INFO - Iter [31700/80000] lr: 8.669e-07, eta: 13:03:57, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7321, decode.acc_seg: 64.1104, aux.loss_ce: 0.3295, aux.acc_seg: 62.8468, loss: 1.0617 2022-04-19 08:24:56,045 - mmseg - INFO - Iter [31750/80000] lr: 8.660e-07, eta: 13:03:06, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6876, decode.acc_seg: 64.1061, aux.loss_ce: 0.3047, aux.acc_seg: 63.7481, loss: 0.9923 2022-04-19 08:25:42,995 - mmseg - INFO - Iter [31800/80000] lr: 8.651e-07, eta: 13:02:15, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7318, decode.acc_seg: 62.4198, aux.loss_ce: 0.3287, aux.acc_seg: 61.5464, loss: 1.0605 2022-04-19 08:26:29,856 - mmseg - INFO - Iter [31850/80000] lr: 8.642e-07, eta: 13:01:23, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6850, decode.acc_seg: 63.6996, aux.loss_ce: 0.3058, aux.acc_seg: 62.9796, loss: 0.9908 2022-04-19 08:27:16,822 - mmseg - INFO - Iter [31900/80000] lr: 8.633e-07, eta: 13:00:32, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6890, decode.acc_seg: 63.1306, aux.loss_ce: 0.3070, aux.acc_seg: 62.1715, loss: 0.9960 2022-04-19 08:28:03,550 - mmseg - INFO - Iter [31950/80000] lr: 8.624e-07, eta: 12:59:40, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7279, decode.acc_seg: 62.1235, aux.loss_ce: 0.3273, aux.acc_seg: 61.1459, loss: 1.0553 2022-04-19 08:28:50,160 - mmseg - INFO - Saving checkpoint at 32000 iterations 2022-04-19 08:29:02,651 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 08:29:02,654 - mmseg - INFO - Iter [32000/80000] lr: 8.615e-07, eta: 12:59:07, time: 1.180, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6910, decode.acc_seg: 64.5542, aux.loss_ce: 0.3092, aux.acc_seg: 63.2582, loss: 1.0002 2022-04-19 08:32:57,687 - mmseg - INFO - per class results: 2022-04-19 08:32:57,710 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.32 | 95.14 | | bicycle | 70.46 | 84.38 | | car | 68.4 | 85.71 | | motorcycle | 84.67 | 92.2 | | airplane | 82.07 | 94.54 | | bus | 85.54 | 93.34 | | train | 82.22 | 95.37 | | truck | 67.08 | 85.29 | | boat | 65.26 | 86.08 | | traffic light | 66.21 | 87.02 | | fire hydrant | 83.75 | 97.87 | | stop sign | 89.51 | 98.43 | | parking meter | 75.28 | 91.11 | | bench | 57.53 | 73.94 | | bird | 83.25 | 90.98 | | cat | 82.5 | 90.57 | | dog | 77.31 | 84.92 | | horse | 85.89 | 95.81 | | sheep | 87.22 | 96.41 | | cow | 87.27 | 92.97 | | elephant | 90.91 | 98.22 | | bear | 90.68 | 96.36 | | zebra | 91.65 | 97.53 | | giraffe | 85.79 | 95.37 | | backpack | 37.08 | 67.69 | | umbrella | 85.87 | 93.43 | | handbag | 38.13 | 59.63 | | tie | 4.09 | 5.78 | | suitcase | 80.61 | 93.54 | | frisbee | 80.78 | 90.85 | | skis | 45.6 | 60.08 | | snowboard | 61.86 | 66.75 | | sports ball | 61.19 | 70.26 | | kite | 71.61 | 87.39 | | baseball bat | 54.92 | 70.9 | | baseball glove | 73.64 | 85.43 | | skateboard | 80.21 | 89.55 | | surfboard | 81.4 | 90.8 | | tennis racket | 83.98 | 93.15 | | bottle | 50.86 | 68.71 | | wine glass | 58.49 | 85.83 | | cup | 57.08 | 79.77 | | fork | 46.24 | 69.12 | | knife | 39.28 | 57.51 | | spoon | 39.54 | 52.21 | | bowl | 50.47 | 67.48 | | banana | 70.21 | 93.07 | | apple | 56.41 | 77.68 | | sandwich | 56.56 | 77.51 | | orange | 73.25 | 86.71 | | broccoli | 56.91 | 76.89 | | carrot | 57.5 | 77.58 | | hot dog | 57.2 | 69.8 | | pizza | 77.42 | 94.36 | | donut | 77.76 | 94.73 | | cake | 66.89 | 87.22 | | chair | 50.22 | 76.08 | | couch | 58.14 | 78.76 | | potted plant | 30.63 | 51.83 | | bed | 64.98 | 82.55 | | dining table | 46.35 | 66.42 | | toilet | 80.74 | 95.34 | | tv | 67.62 | 86.68 | | laptop | 75.64 | 94.88 | | mouse | 75.16 | 86.36 | | remote | 57.78 | 76.75 | | keyboard | 63.55 | 71.54 | | cell phone | 73.63 | 88.99 | | microwave | 67.68 | 81.89 | | oven | 54.06 | 88.92 | | toaster | 68.76 | 70.63 | | sink | 60.77 | 83.8 | | refrigerator | 75.84 | 92.45 | | book | 48.35 | 73.17 | | clock | 69.44 | 82.21 | | vase | 63.23 | 85.6 | | scissors | 71.05 | 96.16 | | teddy bear | 78.4 | 93.78 | | hair drier | 38.66 | 39.06 | | toothbrush | 46.61 | 75.24 | | banner | 31.26 | 64.73 | | blanket | 6.65 | 7.3 | | branch | 12.6 | 15.11 | | bridge | 38.02 | 57.3 | | building-other | 55.23 | 71.85 | | bush | 33.73 | 45.25 | | cabinet | 57.28 | 79.02 | | cage | 26.02 | 39.86 | | cardboard | 47.77 | 59.4 | | carpet | 55.04 | 75.8 | | ceiling-other | 65.4 | 81.78 | | ceiling-tile | 14.34 | 16.49 | | cloth | 0.26 | 0.26 | | clothes | 15.13 | 17.14 | | clouds | 50.53 | 67.61 | | counter | 26.51 | 62.25 | | cupboard | 0.0 | 0.0 | | curtain | 68.18 | 81.47 | | desk-stuff | 45.69 | 71.24 | | dirt | 43.12 | 70.98 | | door-stuff | 43.23 | 75.03 | | fence | 33.61 | 56.07 | | floor-marble | 9.38 | 11.48 | | floor-other | 21.16 | 26.78 | | floor-stone | 7.03 | 10.29 | | floor-tile | 62.95 | 75.57 | | floor-wood | 63.87 | 80.41 | | flower | 39.26 | 57.2 | | fog | 17.47 | 22.03 | | food-other | 29.67 | 38.66 | | fruit | 44.19 | 57.15 | | furniture-other | 15.49 | 18.33 | | grass | 70.11 | 85.78 | | gravel | 30.52 | 43.22 | | ground-other | 1.38 | 1.54 | | hill | 16.37 | 21.39 | | house | 28.93 | 34.97 | | leaves | 29.55 | 41.17 | | light | 41.43 | 57.25 | | mat | 0.0 | 0.0 | | metal | 31.13 | 39.2 | | mirror-stuff | 54.5 | 68.87 | | moss | 0.0 | 0.0 | | mountain | 54.42 | 71.93 | | mud | 5.58 | 7.5 | | napkin | 20.75 | 30.42 | | net | 49.4 | 66.7 | | paper | 32.06 | 45.68 | | pavement | 53.73 | 75.42 | | pillow | 9.9 | 11.03 | | plant-other | 19.29 | 28.72 | | plastic | 25.14 | 31.92 | | platform | 29.4 | 48.63 | | playingfield | 65.63 | 80.0 | | railing | 9.44 | 16.36 | | railroad | 59.72 | 84.56 | | river | 48.95 | 68.57 | | road | 66.71 | 79.8 | | rock | 45.07 | 68.87 | | roof | 20.34 | 24.93 | | rug | 37.61 | 54.51 | | salad | 0.0 | 0.0 | | sand | 68.15 | 73.05 | | sea | 85.21 | 94.49 | | shelf | 36.41 | 53.54 | | sky-other | 71.76 | 85.74 | | skyscraper | 39.71 | 52.97 | | snow | 89.8 | 96.04 | | solid-other | 0.0 | 0.0 | | stairs | 28.76 | 61.28 | | stone | 11.12 | 13.47 | | straw | 21.55 | 26.78 | | structural-other | 0.31 | 0.31 | | table | 23.21 | 32.76 | | tent | 9.27 | 11.75 | | textile-other | 18.37 | 32.46 | | towel | 36.32 | 46.09 | | tree | 73.87 | 87.34 | | vegetable | 42.28 | 57.52 | | wall-brick | 46.13 | 70.27 | | wall-concrete | 60.6 | 79.55 | | wall-other | 21.94 | 31.14 | | wall-panel | 1.76 | 1.88 | | wall-stone | 30.26 | 39.27 | | wall-tile | 68.72 | 87.31 | | wall-wood | 40.47 | 51.7 | | water-other | 21.81 | 26.94 | | waterdrops | 0.0 | 0.0 | | window-blind | 52.16 | 60.45 | | window-other | 45.51 | 73.15 | | wood | 27.47 | 37.21 | +------------------+-------+-------+ 2022-04-19 08:32:57,710 - mmseg - INFO - Summary: 2022-04-19 08:32:57,711 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 72.92 | 49.46 | 62.85 | +-------+-------+-------+ 2022-04-19 08:32:57,730 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 08:32:57,731 - mmseg - INFO - Iter(val) [625] aAcc: 0.7292, mIoU: 0.4946, mAcc: 0.6285, IoU.person: 0.8632, IoU.bicycle: 0.7046, IoU.car: 0.6840, IoU.motorcycle: 0.8467, IoU.airplane: 0.8207, IoU.bus: 0.8554, IoU.train: 0.8222, IoU.truck: 0.6708, IoU.boat: 0.6526, IoU.traffic light: 0.6621, IoU.fire hydrant: 0.8375, IoU.stop sign: 0.8951, IoU.parking meter: 0.7528, IoU.bench: 0.5753, IoU.bird: 0.8325, IoU.cat: 0.8250, IoU.dog: 0.7731, IoU.horse: 0.8589, IoU.sheep: 0.8722, IoU.cow: 0.8727, IoU.elephant: 0.9091, IoU.bear: 0.9068, IoU.zebra: 0.9165, IoU.giraffe: 0.8579, IoU.backpack: 0.3708, IoU.umbrella: 0.8587, IoU.handbag: 0.3813, IoU.tie: 0.0409, IoU.suitcase: 0.8061, IoU.frisbee: 0.8078, IoU.skis: 0.4560, IoU.snowboard: 0.6186, IoU.sports ball: 0.6119, IoU.kite: 0.7161, IoU.baseball bat: 0.5492, IoU.baseball glove: 0.7364, IoU.skateboard: 0.8021, IoU.surfboard: 0.8140, IoU.tennis racket: 0.8398, IoU.bottle: 0.5086, IoU.wine glass: 0.5849, IoU.cup: 0.5708, IoU.fork: 0.4624, IoU.knife: 0.3928, IoU.spoon: 0.3954, IoU.bowl: 0.5047, IoU.banana: 0.7021, IoU.apple: 0.5641, IoU.sandwich: 0.5656, IoU.orange: 0.7325, IoU.broccoli: 0.5691, IoU.carrot: 0.5750, IoU.hot dog: 0.5720, IoU.pizza: 0.7742, IoU.donut: 0.7776, IoU.cake: 0.6689, IoU.chair: 0.5022, IoU.couch: 0.5814, IoU.potted plant: 0.3063, IoU.bed: 0.6498, IoU.dining table: 0.4635, IoU.toilet: 0.8074, IoU.tv: 0.6762, IoU.laptop: 0.7564, IoU.mouse: 0.7516, IoU.remote: 0.5778, IoU.keyboard: 0.6355, IoU.cell phone: 0.7363, IoU.microwave: 0.6768, IoU.oven: 0.5406, IoU.toaster: 0.6876, IoU.sink: 0.6077, IoU.refrigerator: 0.7584, IoU.book: 0.4835, IoU.clock: 0.6944, IoU.vase: 0.6323, IoU.scissors: 0.7105, IoU.teddy bear: 0.7840, IoU.hair drier: 0.3866, IoU.toothbrush: 0.4661, IoU.banner: 0.3126, IoU.blanket: 0.0665, IoU.branch: 0.1260, IoU.bridge: 0.3802, IoU.building-other: 0.5523, IoU.bush: 0.3373, IoU.cabinet: 0.5728, IoU.cage: 0.2602, IoU.cardboard: 0.4777, IoU.carpet: 0.5504, IoU.ceiling-other: 0.6540, IoU.ceiling-tile: 0.1434, IoU.cloth: 0.0026, IoU.clothes: 0.1513, IoU.clouds: 0.5053, IoU.counter: 0.2651, IoU.cupboard: 0.0000, IoU.curtain: 0.6818, IoU.desk-stuff: 0.4569, IoU.dirt: 0.4312, IoU.door-stuff: 0.4323, IoU.fence: 0.3361, IoU.floor-marble: 0.0938, IoU.floor-other: 0.2116, IoU.floor-stone: 0.0703, IoU.floor-tile: 0.6295, IoU.floor-wood: 0.6387, IoU.flower: 0.3926, IoU.fog: 0.1747, IoU.food-other: 0.2967, IoU.fruit: 0.4419, IoU.furniture-other: 0.1549, IoU.grass: 0.7011, IoU.gravel: 0.3052, IoU.ground-other: 0.0138, IoU.hill: 0.1637, IoU.house: 0.2893, IoU.leaves: 0.2955, IoU.light: 0.4143, IoU.mat: 0.0000, IoU.metal: 0.3113, IoU.mirror-stuff: 0.5450, IoU.moss: 0.0000, IoU.mountain: 0.5442, IoU.mud: 0.0558, IoU.napkin: 0.2075, IoU.net: 0.4940, IoU.paper: 0.3206, IoU.pavement: 0.5373, IoU.pillow: 0.0990, IoU.plant-other: 0.1929, IoU.plastic: 0.2514, IoU.platform: 0.2940, IoU.playingfield: 0.6563, IoU.railing: 0.0944, IoU.railroad: 0.5972, IoU.river: 0.4895, IoU.road: 0.6671, IoU.rock: 0.4507, IoU.roof: 0.2034, IoU.rug: 0.3761, IoU.salad: 0.0000, IoU.sand: 0.6815, IoU.sea: 0.8521, IoU.shelf: 0.3641, IoU.sky-other: 0.7176, IoU.skyscraper: 0.3971, IoU.snow: 0.8980, IoU.solid-other: 0.0000, IoU.stairs: 0.2876, IoU.stone: 0.1112, IoU.straw: 0.2155, IoU.structural-other: 0.0031, IoU.table: 0.2321, IoU.tent: 0.0927, IoU.textile-other: 0.1837, IoU.towel: 0.3632, IoU.tree: 0.7387, IoU.vegetable: 0.4228, IoU.wall-brick: 0.4613, IoU.wall-concrete: 0.6060, IoU.wall-other: 0.2194, IoU.wall-panel: 0.0176, IoU.wall-stone: 0.3026, IoU.wall-tile: 0.6872, IoU.wall-wood: 0.4047, IoU.water-other: 0.2181, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5216, IoU.window-other: 0.4551, IoU.wood: 0.2747, Acc.person: 0.9514, Acc.bicycle: 0.8438, Acc.car: 0.8571, Acc.motorcycle: 0.9220, Acc.airplane: 0.9454, Acc.bus: 0.9334, Acc.train: 0.9537, Acc.truck: 0.8529, Acc.boat: 0.8608, Acc.traffic light: 0.8702, Acc.fire hydrant: 0.9787, Acc.stop sign: 0.9843, Acc.parking meter: 0.9111, Acc.bench: 0.7394, Acc.bird: 0.9098, Acc.cat: 0.9057, Acc.dog: 0.8492, Acc.horse: 0.9581, Acc.sheep: 0.9641, Acc.cow: 0.9297, Acc.elephant: 0.9822, Acc.bear: 0.9636, Acc.zebra: 0.9753, Acc.giraffe: 0.9537, Acc.backpack: 0.6769, Acc.umbrella: 0.9343, Acc.handbag: 0.5963, Acc.tie: 0.0578, Acc.suitcase: 0.9354, Acc.frisbee: 0.9085, Acc.skis: 0.6008, Acc.snowboard: 0.6675, Acc.sports ball: 0.7026, Acc.kite: 0.8739, Acc.baseball bat: 0.7090, Acc.baseball glove: 0.8543, Acc.skateboard: 0.8955, Acc.surfboard: 0.9080, Acc.tennis racket: 0.9315, Acc.bottle: 0.6871, Acc.wine glass: 0.8583, Acc.cup: 0.7977, Acc.fork: 0.6912, Acc.knife: 0.5751, Acc.spoon: 0.5221, Acc.bowl: 0.6748, Acc.banana: 0.9307, Acc.apple: 0.7768, Acc.sandwich: 0.7751, Acc.orange: 0.8671, Acc.broccoli: 0.7689, Acc.carrot: 0.7758, Acc.hot dog: 0.6980, Acc.pizza: 0.9436, Acc.donut: 0.9473, Acc.cake: 0.8722, Acc.chair: 0.7608, Acc.couch: 0.7876, Acc.potted plant: 0.5183, Acc.bed: 0.8255, Acc.dining table: 0.6642, Acc.toilet: 0.9534, Acc.tv: 0.8668, Acc.laptop: 0.9488, Acc.mouse: 0.8636, Acc.remote: 0.7675, Acc.keyboard: 0.7154, Acc.cell phone: 0.8899, Acc.microwave: 0.8189, Acc.oven: 0.8892, Acc.toaster: 0.7063, Acc.sink: 0.8380, Acc.refrigerator: 0.9245, Acc.book: 0.7317, Acc.clock: 0.8221, Acc.vase: 0.8560, Acc.scissors: 0.9616, Acc.teddy bear: 0.9378, Acc.hair drier: 0.3906, Acc.toothbrush: 0.7524, Acc.banner: 0.6473, Acc.blanket: 0.0730, Acc.branch: 0.1511, Acc.bridge: 0.5730, Acc.building-other: 0.7185, Acc.bush: 0.4525, Acc.cabinet: 0.7902, Acc.cage: 0.3986, Acc.cardboard: 0.5940, Acc.carpet: 0.7580, Acc.ceiling-other: 0.8178, Acc.ceiling-tile: 0.1649, Acc.cloth: 0.0026, Acc.clothes: 0.1714, Acc.clouds: 0.6761, Acc.counter: 0.6225, Acc.cupboard: 0.0000, Acc.curtain: 0.8147, Acc.desk-stuff: 0.7124, Acc.dirt: 0.7098, Acc.door-stuff: 0.7503, Acc.fence: 0.5607, Acc.floor-marble: 0.1148, Acc.floor-other: 0.2678, Acc.floor-stone: 0.1029, Acc.floor-tile: 0.7557, Acc.floor-wood: 0.8041, Acc.flower: 0.5720, Acc.fog: 0.2203, Acc.food-other: 0.3866, Acc.fruit: 0.5715, Acc.furniture-other: 0.1833, Acc.grass: 0.8578, Acc.gravel: 0.4322, Acc.ground-other: 0.0154, Acc.hill: 0.2139, Acc.house: 0.3497, Acc.leaves: 0.4117, Acc.light: 0.5725, Acc.mat: 0.0000, Acc.metal: 0.3920, Acc.mirror-stuff: 0.6887, Acc.moss: 0.0000, Acc.mountain: 0.7193, Acc.mud: 0.0750, Acc.napkin: 0.3042, Acc.net: 0.6670, Acc.paper: 0.4568, Acc.pavement: 0.7542, Acc.pillow: 0.1103, Acc.plant-other: 0.2872, Acc.plastic: 0.3192, Acc.platform: 0.4863, Acc.playingfield: 0.8000, Acc.railing: 0.1636, Acc.railroad: 0.8456, Acc.river: 0.6857, Acc.road: 0.7980, Acc.rock: 0.6887, Acc.roof: 0.2493, Acc.rug: 0.5451, Acc.salad: 0.0000, Acc.sand: 0.7305, Acc.sea: 0.9449, Acc.shelf: 0.5354, Acc.sky-other: 0.8574, Acc.skyscraper: 0.5297, Acc.snow: 0.9604, Acc.solid-other: 0.0000, Acc.stairs: 0.6128, Acc.stone: 0.1347, Acc.straw: 0.2678, Acc.structural-other: 0.0031, Acc.table: 0.3276, Acc.tent: 0.1175, Acc.textile-other: 0.3246, Acc.towel: 0.4609, Acc.tree: 0.8734, Acc.vegetable: 0.5752, Acc.wall-brick: 0.7027, Acc.wall-concrete: 0.7955, Acc.wall-other: 0.3114, Acc.wall-panel: 0.0188, Acc.wall-stone: 0.3927, Acc.wall-tile: 0.8731, Acc.wall-wood: 0.5170, Acc.water-other: 0.2694, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6045, Acc.window-other: 0.7315, Acc.wood: 0.3721 2022-04-19 08:33:44,252 - mmseg - INFO - Iter [32050/80000] lr: 8.606e-07, eta: 13:04:07, time: 5.634, data_time: 4.709, memory: 73037, decode.loss_ce: 0.7170, decode.acc_seg: 63.0244, aux.loss_ce: 0.3172, aux.acc_seg: 61.8159, loss: 1.0342 2022-04-19 08:34:30,771 - mmseg - INFO - Iter [32100/80000] lr: 8.597e-07, eta: 13:03:14, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7038, decode.acc_seg: 64.5051, aux.loss_ce: 0.3160, aux.acc_seg: 63.2090, loss: 1.0199 2022-04-19 08:35:17,305 - mmseg - INFO - Iter [32150/80000] lr: 8.588e-07, eta: 13:02:21, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7201, decode.acc_seg: 64.1665, aux.loss_ce: 0.3215, aux.acc_seg: 63.0224, loss: 1.0415 2022-04-19 08:36:03,800 - mmseg - INFO - Iter [32200/80000] lr: 8.579e-07, eta: 13:01:28, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6905, decode.acc_seg: 63.2157, aux.loss_ce: 0.3123, aux.acc_seg: 62.1342, loss: 1.0028 2022-04-19 08:36:50,416 - mmseg - INFO - Iter [32250/80000] lr: 8.570e-07, eta: 13:00:36, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7316, decode.acc_seg: 64.5501, aux.loss_ce: 0.3243, aux.acc_seg: 63.5907, loss: 1.0559 2022-04-19 08:37:37,117 - mmseg - INFO - Iter [32300/80000] lr: 8.561e-07, eta: 12:59:43, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6960, decode.acc_seg: 63.3662, aux.loss_ce: 0.3120, aux.acc_seg: 62.2239, loss: 1.0080 2022-04-19 08:38:23,683 - mmseg - INFO - Iter [32350/80000] lr: 8.552e-07, eta: 12:58:51, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6846, decode.acc_seg: 63.6925, aux.loss_ce: 0.3054, aux.acc_seg: 62.9626, loss: 0.9900 2022-04-19 08:39:10,084 - mmseg - INFO - Iter [32400/80000] lr: 8.543e-07, eta: 12:57:58, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6973, decode.acc_seg: 63.7118, aux.loss_ce: 0.3109, aux.acc_seg: 62.5813, loss: 1.0082 2022-04-19 08:39:56,495 - mmseg - INFO - Iter [32450/80000] lr: 8.534e-07, eta: 12:57:05, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7225, decode.acc_seg: 64.3802, aux.loss_ce: 0.3212, aux.acc_seg: 63.3693, loss: 1.0437 2022-04-19 08:40:43,278 - mmseg - INFO - Iter [32500/80000] lr: 8.525e-07, eta: 12:56:12, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7284, decode.acc_seg: 61.2974, aux.loss_ce: 0.3236, aux.acc_seg: 60.4348, loss: 1.0519 2022-04-19 08:41:29,949 - mmseg - INFO - Iter [32550/80000] lr: 8.516e-07, eta: 12:55:20, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7324, decode.acc_seg: 61.9976, aux.loss_ce: 0.3256, aux.acc_seg: 60.9185, loss: 1.0580 2022-04-19 08:42:16,333 - mmseg - INFO - Iter [32600/80000] lr: 8.507e-07, eta: 12:54:27, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6850, decode.acc_seg: 63.8697, aux.loss_ce: 0.3049, aux.acc_seg: 62.8646, loss: 0.9899 2022-04-19 08:43:02,834 - mmseg - INFO - Iter [32650/80000] lr: 8.498e-07, eta: 12:53:35, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7062, decode.acc_seg: 62.6609, aux.loss_ce: 0.3156, aux.acc_seg: 61.7318, loss: 1.0218 2022-04-19 08:43:49,263 - mmseg - INFO - Iter [32700/80000] lr: 8.489e-07, eta: 12:52:42, time: 0.929, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7310, decode.acc_seg: 63.9568, aux.loss_ce: 0.3260, aux.acc_seg: 62.5543, loss: 1.0570 2022-04-19 08:44:35,913 - mmseg - INFO - Iter [32750/80000] lr: 8.480e-07, eta: 12:51:49, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7477, decode.acc_seg: 62.1965, aux.loss_ce: 0.3272, aux.acc_seg: 61.4778, loss: 1.0749 2022-04-19 08:45:22,672 - mmseg - INFO - Iter [32800/80000] lr: 8.471e-07, eta: 12:50:57, time: 0.937, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7276, decode.acc_seg: 62.8247, aux.loss_ce: 0.3219, aux.acc_seg: 61.8635, loss: 1.0495 2022-04-19 08:46:09,416 - mmseg - INFO - Iter [32850/80000] lr: 8.462e-07, eta: 12:50:05, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7461, decode.acc_seg: 63.5836, aux.loss_ce: 0.3316, aux.acc_seg: 62.3838, loss: 1.0778 2022-04-19 08:46:55,999 - mmseg - INFO - Iter [32900/80000] lr: 8.453e-07, eta: 12:49:12, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7282, decode.acc_seg: 62.6301, aux.loss_ce: 0.3187, aux.acc_seg: 61.9971, loss: 1.0469 2022-04-19 08:47:42,574 - mmseg - INFO - Iter [32950/80000] lr: 8.444e-07, eta: 12:48:20, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6751, decode.acc_seg: 64.6823, aux.loss_ce: 0.3010, aux.acc_seg: 63.7506, loss: 0.9761 2022-04-19 08:48:29,198 - mmseg - INFO - Saving checkpoint at 33000 iterations 2022-04-19 08:48:39,591 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 08:48:39,592 - mmseg - INFO - Iter [33000/80000] lr: 8.435e-07, eta: 12:47:42, time: 1.140, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6727, decode.acc_seg: 65.2869, aux.loss_ce: 0.3030, aux.acc_seg: 63.7635, loss: 0.9757 2022-04-19 08:49:26,579 - mmseg - INFO - Iter [33050/80000] lr: 8.427e-07, eta: 12:46:51, time: 0.940, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6883, decode.acc_seg: 63.5173, aux.loss_ce: 0.3088, aux.acc_seg: 62.6150, loss: 0.9970 2022-04-19 08:50:13,055 - mmseg - INFO - Iter [33100/80000] lr: 8.418e-07, eta: 12:45:58, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7243, decode.acc_seg: 63.5497, aux.loss_ce: 0.3251, aux.acc_seg: 62.5060, loss: 1.0494 2022-04-19 08:51:00,082 - mmseg - INFO - Iter [33150/80000] lr: 8.409e-07, eta: 12:45:06, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7151, decode.acc_seg: 62.0797, aux.loss_ce: 0.3188, aux.acc_seg: 61.2606, loss: 1.0339 2022-04-19 08:51:46,673 - mmseg - INFO - Iter [33200/80000] lr: 8.400e-07, eta: 12:44:14, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6929, decode.acc_seg: 64.7497, aux.loss_ce: 0.3100, aux.acc_seg: 63.5822, loss: 1.0030 2022-04-19 08:52:33,138 - mmseg - INFO - Iter [33250/80000] lr: 8.391e-07, eta: 12:43:21, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7278, decode.acc_seg: 62.0774, aux.loss_ce: 0.3249, aux.acc_seg: 60.9850, loss: 1.0527 2022-04-19 08:53:19,629 - mmseg - INFO - Iter [33300/80000] lr: 8.382e-07, eta: 12:42:29, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7268, decode.acc_seg: 63.6182, aux.loss_ce: 0.3211, aux.acc_seg: 62.8246, loss: 1.0479 2022-04-19 08:54:06,225 - mmseg - INFO - Iter [33350/80000] lr: 8.373e-07, eta: 12:41:36, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7129, decode.acc_seg: 65.3946, aux.loss_ce: 0.3158, aux.acc_seg: 64.0117, loss: 1.0287 2022-04-19 08:54:52,564 - mmseg - INFO - Iter [33400/80000] lr: 8.364e-07, eta: 12:40:44, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6897, decode.acc_seg: 63.9426, aux.loss_ce: 0.3107, aux.acc_seg: 62.4486, loss: 1.0004 2022-04-19 08:55:39,066 - mmseg - INFO - Iter [33450/80000] lr: 8.355e-07, eta: 12:39:51, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6984, decode.acc_seg: 63.2013, aux.loss_ce: 0.3164, aux.acc_seg: 62.2406, loss: 1.0149 2022-04-19 08:56:25,644 - mmseg - INFO - Iter [33500/80000] lr: 8.346e-07, eta: 12:38:59, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7021, decode.acc_seg: 63.8918, aux.loss_ce: 0.3126, aux.acc_seg: 63.2038, loss: 1.0147 2022-04-19 08:57:12,254 - mmseg - INFO - Iter [33550/80000] lr: 8.337e-07, eta: 12:38:07, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6960, decode.acc_seg: 63.7690, aux.loss_ce: 0.3075, aux.acc_seg: 62.8180, loss: 1.0034 2022-04-19 08:57:59,127 - mmseg - INFO - Iter [33600/80000] lr: 8.328e-07, eta: 12:37:15, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7017, decode.acc_seg: 62.3763, aux.loss_ce: 0.3142, aux.acc_seg: 61.3195, loss: 1.0159 2022-04-19 08:58:45,463 - mmseg - INFO - Iter [33650/80000] lr: 8.319e-07, eta: 12:36:22, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7534, decode.acc_seg: 62.8259, aux.loss_ce: 0.3388, aux.acc_seg: 61.5399, loss: 1.0922 2022-04-19 08:59:32,412 - mmseg - INFO - Iter [33700/80000] lr: 8.310e-07, eta: 12:35:31, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7004, decode.acc_seg: 64.1039, aux.loss_ce: 0.3097, aux.acc_seg: 63.0550, loss: 1.0101 2022-04-19 09:00:18,940 - mmseg - INFO - Iter [33750/80000] lr: 8.301e-07, eta: 12:34:38, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7323, decode.acc_seg: 62.8919, aux.loss_ce: 0.3287, aux.acc_seg: 62.3941, loss: 1.0611 2022-04-19 09:01:05,744 - mmseg - INFO - Iter [33800/80000] lr: 8.292e-07, eta: 12:33:47, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6964, decode.acc_seg: 62.7427, aux.loss_ce: 0.3074, aux.acc_seg: 61.7902, loss: 1.0038 2022-04-19 09:01:52,638 - mmseg - INFO - Iter [33850/80000] lr: 8.283e-07, eta: 12:32:55, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7321, decode.acc_seg: 64.6121, aux.loss_ce: 0.3250, aux.acc_seg: 63.4137, loss: 1.0571 2022-04-19 09:02:39,648 - mmseg - INFO - Iter [33900/80000] lr: 8.274e-07, eta: 12:32:03, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6780, decode.acc_seg: 64.7114, aux.loss_ce: 0.3021, aux.acc_seg: 63.8881, loss: 0.9801 2022-04-19 09:03:26,947 - mmseg - INFO - Iter [33950/80000] lr: 8.265e-07, eta: 12:31:12, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7266, decode.acc_seg: 62.6947, aux.loss_ce: 0.3241, aux.acc_seg: 61.6398, loss: 1.0506 2022-04-19 09:04:13,777 - mmseg - INFO - Saving checkpoint at 34000 iterations 2022-04-19 09:04:25,738 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 09:04:25,749 - mmseg - INFO - Iter [34000/80000] lr: 8.256e-07, eta: 12:30:36, time: 1.173, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6440, decode.acc_seg: 65.5672, aux.loss_ce: 0.2879, aux.acc_seg: 64.8518, loss: 0.9319 2022-04-19 09:05:12,364 - mmseg - INFO - Iter [34050/80000] lr: 8.247e-07, eta: 12:29:44, time: 0.937, data_time: 0.011, memory: 73037, decode.loss_ce: 0.7136, decode.acc_seg: 64.4731, aux.loss_ce: 0.3154, aux.acc_seg: 63.8212, loss: 1.0290 2022-04-19 09:05:58,818 - mmseg - INFO - Iter [34100/80000] lr: 8.238e-07, eta: 12:28:52, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7291, decode.acc_seg: 62.7830, aux.loss_ce: 0.3240, aux.acc_seg: 62.0379, loss: 1.0531 2022-04-19 09:06:45,122 - mmseg - INFO - Iter [34150/80000] lr: 8.229e-07, eta: 12:28:00, time: 0.928, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7020, decode.acc_seg: 63.6602, aux.loss_ce: 0.3173, aux.acc_seg: 62.4393, loss: 1.0192 2022-04-19 09:07:31,616 - mmseg - INFO - Iter [34200/80000] lr: 8.220e-07, eta: 12:27:07, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7023, decode.acc_seg: 63.2361, aux.loss_ce: 0.3117, aux.acc_seg: 62.1841, loss: 1.0140 2022-04-19 09:08:18,099 - mmseg - INFO - Iter [34250/80000] lr: 8.211e-07, eta: 12:26:15, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6846, decode.acc_seg: 63.9387, aux.loss_ce: 0.3018, aux.acc_seg: 63.1960, loss: 0.9863 2022-04-19 09:09:04,840 - mmseg - INFO - Iter [34300/80000] lr: 8.202e-07, eta: 12:25:23, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6965, decode.acc_seg: 63.1175, aux.loss_ce: 0.3116, aux.acc_seg: 61.9079, loss: 1.0081 2022-04-19 09:09:51,427 - mmseg - INFO - Iter [34350/80000] lr: 8.193e-07, eta: 12:24:31, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7149, decode.acc_seg: 63.6221, aux.loss_ce: 0.3164, aux.acc_seg: 62.6236, loss: 1.0313 2022-04-19 09:10:38,016 - mmseg - INFO - Iter [34400/80000] lr: 8.184e-07, eta: 12:23:39, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7202, decode.acc_seg: 64.4305, aux.loss_ce: 0.3206, aux.acc_seg: 63.1381, loss: 1.0408 2022-04-19 09:11:24,581 - mmseg - INFO - Iter [34450/80000] lr: 8.175e-07, eta: 12:22:47, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7183, decode.acc_seg: 62.1767, aux.loss_ce: 0.3196, aux.acc_seg: 61.1462, loss: 1.0378 2022-04-19 09:12:11,297 - mmseg - INFO - Iter [34500/80000] lr: 8.166e-07, eta: 12:21:55, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7216, decode.acc_seg: 62.4340, aux.loss_ce: 0.3230, aux.acc_seg: 61.1129, loss: 1.0446 2022-04-19 09:12:58,132 - mmseg - INFO - Iter [34550/80000] lr: 8.157e-07, eta: 12:21:04, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6981, decode.acc_seg: 63.2219, aux.loss_ce: 0.3110, aux.acc_seg: 62.5050, loss: 1.0091 2022-04-19 09:13:44,643 - mmseg - INFO - Iter [34600/80000] lr: 8.148e-07, eta: 12:20:12, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6879, decode.acc_seg: 64.2434, aux.loss_ce: 0.3073, aux.acc_seg: 62.8340, loss: 0.9952 2022-04-19 09:14:31,437 - mmseg - INFO - Iter [34650/80000] lr: 8.139e-07, eta: 12:19:20, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6981, decode.acc_seg: 64.2090, aux.loss_ce: 0.3163, aux.acc_seg: 62.7447, loss: 1.0144 2022-04-19 09:15:18,089 - mmseg - INFO - Iter [34700/80000] lr: 8.130e-07, eta: 12:18:28, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7300, decode.acc_seg: 63.8910, aux.loss_ce: 0.3256, aux.acc_seg: 63.0365, loss: 1.0556 2022-04-19 09:16:04,981 - mmseg - INFO - Iter [34750/80000] lr: 8.121e-07, eta: 12:17:36, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7050, decode.acc_seg: 63.3273, aux.loss_ce: 0.3161, aux.acc_seg: 62.1574, loss: 1.0211 2022-04-19 09:16:51,749 - mmseg - INFO - Iter [34800/80000] lr: 8.112e-07, eta: 12:16:45, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7256, decode.acc_seg: 63.9204, aux.loss_ce: 0.3249, aux.acc_seg: 62.9816, loss: 1.0505 2022-04-19 09:17:38,574 - mmseg - INFO - Iter [34850/80000] lr: 8.103e-07, eta: 12:15:53, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7033, decode.acc_seg: 63.7890, aux.loss_ce: 0.3164, aux.acc_seg: 62.7632, loss: 1.0197 2022-04-19 09:18:25,293 - mmseg - INFO - Iter [34900/80000] lr: 8.094e-07, eta: 12:15:02, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6935, decode.acc_seg: 63.5166, aux.loss_ce: 0.3076, aux.acc_seg: 62.6940, loss: 1.0011 2022-04-19 09:19:11,908 - mmseg - INFO - Iter [34950/80000] lr: 8.086e-07, eta: 12:14:10, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7051, decode.acc_seg: 63.8341, aux.loss_ce: 0.3129, aux.acc_seg: 62.8705, loss: 1.0180 2022-04-19 09:19:58,657 - mmseg - INFO - Saving checkpoint at 35000 iterations 2022-04-19 09:20:10,879 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 09:20:10,879 - mmseg - INFO - Iter [35000/80000] lr: 8.077e-07, eta: 12:13:34, time: 1.178, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6947, decode.acc_seg: 64.2591, aux.loss_ce: 0.3054, aux.acc_seg: 63.3844, loss: 1.0002 2022-04-19 09:20:58,026 - mmseg - INFO - Iter [35050/80000] lr: 8.068e-07, eta: 12:12:43, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7002, decode.acc_seg: 64.2500, aux.loss_ce: 0.3099, aux.acc_seg: 63.3498, loss: 1.0101 2022-04-19 09:21:44,671 - mmseg - INFO - Iter [35100/80000] lr: 8.059e-07, eta: 12:11:51, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7128, decode.acc_seg: 62.7522, aux.loss_ce: 0.3124, aux.acc_seg: 61.9175, loss: 1.0252 2022-04-19 09:22:31,216 - mmseg - INFO - Iter [35150/80000] lr: 8.050e-07, eta: 12:10:59, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7345, decode.acc_seg: 62.1727, aux.loss_ce: 0.3235, aux.acc_seg: 61.4587, loss: 1.0579 2022-04-19 09:23:17,918 - mmseg - INFO - Iter [35200/80000] lr: 8.041e-07, eta: 12:10:07, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7466, decode.acc_seg: 62.7898, aux.loss_ce: 0.3273, aux.acc_seg: 62.2278, loss: 1.0739 2022-04-19 09:24:04,937 - mmseg - INFO - Iter [35250/80000] lr: 8.032e-07, eta: 12:09:16, time: 0.940, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7418, decode.acc_seg: 62.5000, aux.loss_ce: 0.3286, aux.acc_seg: 61.4002, loss: 1.0704 2022-04-19 09:24:51,763 - mmseg - INFO - Iter [35300/80000] lr: 8.023e-07, eta: 12:08:24, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6652, decode.acc_seg: 64.0721, aux.loss_ce: 0.2936, aux.acc_seg: 63.3284, loss: 0.9588 2022-04-19 09:25:38,697 - mmseg - INFO - Iter [35350/80000] lr: 8.014e-07, eta: 12:07:33, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7218, decode.acc_seg: 63.0527, aux.loss_ce: 0.3216, aux.acc_seg: 61.9125, loss: 1.0434 2022-04-19 09:26:24,977 - mmseg - INFO - Iter [35400/80000] lr: 8.005e-07, eta: 12:06:41, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7213, decode.acc_seg: 62.7954, aux.loss_ce: 0.3232, aux.acc_seg: 61.6683, loss: 1.0445 2022-04-19 09:27:11,649 - mmseg - INFO - Iter [35450/80000] lr: 7.996e-07, eta: 12:05:49, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7190, decode.acc_seg: 62.8082, aux.loss_ce: 0.3169, aux.acc_seg: 62.0992, loss: 1.0359 2022-04-19 09:27:57,952 - mmseg - INFO - Iter [35500/80000] lr: 7.987e-07, eta: 12:04:57, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6998, decode.acc_seg: 65.2914, aux.loss_ce: 0.3118, aux.acc_seg: 64.2054, loss: 1.0116 2022-04-19 09:28:44,594 - mmseg - INFO - Iter [35550/80000] lr: 7.978e-07, eta: 12:04:05, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7024, decode.acc_seg: 63.0594, aux.loss_ce: 0.3144, aux.acc_seg: 61.9479, loss: 1.0168 2022-04-19 09:29:31,146 - mmseg - INFO - Iter [35600/80000] lr: 7.969e-07, eta: 12:03:14, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6751, decode.acc_seg: 64.6511, aux.loss_ce: 0.3040, aux.acc_seg: 63.6510, loss: 0.9791 2022-04-19 09:30:17,725 - mmseg - INFO - Iter [35650/80000] lr: 7.960e-07, eta: 12:02:22, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7469, decode.acc_seg: 63.1130, aux.loss_ce: 0.3293, aux.acc_seg: 62.1849, loss: 1.0762 2022-04-19 09:31:04,256 - mmseg - INFO - Iter [35700/80000] lr: 7.951e-07, eta: 12:01:30, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6701, decode.acc_seg: 63.8615, aux.loss_ce: 0.2952, aux.acc_seg: 63.3258, loss: 0.9652 2022-04-19 09:31:50,684 - mmseg - INFO - Iter [35750/80000] lr: 7.942e-07, eta: 12:00:38, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7545, decode.acc_seg: 63.0415, aux.loss_ce: 0.3360, aux.acc_seg: 61.8155, loss: 1.0905 2022-04-19 09:32:37,113 - mmseg - INFO - Iter [35800/80000] lr: 7.933e-07, eta: 11:59:46, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6915, decode.acc_seg: 66.2695, aux.loss_ce: 0.3054, aux.acc_seg: 65.4250, loss: 0.9968 2022-04-19 09:33:23,445 - mmseg - INFO - Iter [35850/80000] lr: 7.924e-07, eta: 11:58:55, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7082, decode.acc_seg: 63.1888, aux.loss_ce: 0.3163, aux.acc_seg: 62.0205, loss: 1.0245 2022-04-19 09:34:09,836 - mmseg - INFO - Iter [35900/80000] lr: 7.915e-07, eta: 11:58:03, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7018, decode.acc_seg: 63.7938, aux.loss_ce: 0.3107, aux.acc_seg: 62.4415, loss: 1.0124 2022-04-19 09:34:56,309 - mmseg - INFO - Iter [35950/80000] lr: 7.906e-07, eta: 11:57:11, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6746, decode.acc_seg: 63.9761, aux.loss_ce: 0.3010, aux.acc_seg: 62.9443, loss: 0.9756 2022-04-19 09:35:42,834 - mmseg - INFO - Saving checkpoint at 36000 iterations 2022-04-19 09:35:53,558 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 09:35:53,558 - mmseg - INFO - Iter [36000/80000] lr: 7.897e-07, eta: 11:56:32, time: 1.145, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7192, decode.acc_seg: 64.0507, aux.loss_ce: 0.3185, aux.acc_seg: 63.1303, loss: 1.0377 2022-04-19 09:36:40,192 - mmseg - INFO - Iter [36050/80000] lr: 7.888e-07, eta: 11:55:41, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7047, decode.acc_seg: 63.0877, aux.loss_ce: 0.3129, aux.acc_seg: 61.9189, loss: 1.0176 2022-04-19 09:37:27,095 - mmseg - INFO - Iter [36100/80000] lr: 7.879e-07, eta: 11:54:49, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6886, decode.acc_seg: 62.9799, aux.loss_ce: 0.3093, aux.acc_seg: 61.4243, loss: 0.9979 2022-04-19 09:38:13,945 - mmseg - INFO - Iter [36150/80000] lr: 7.870e-07, eta: 11:53:58, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6957, decode.acc_seg: 65.0808, aux.loss_ce: 0.3050, aux.acc_seg: 64.3297, loss: 1.0007 2022-04-19 09:39:00,902 - mmseg - INFO - Iter [36200/80000] lr: 7.861e-07, eta: 11:53:07, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7332, decode.acc_seg: 63.1221, aux.loss_ce: 0.3230, aux.acc_seg: 62.1527, loss: 1.0562 2022-04-19 09:39:47,937 - mmseg - INFO - Iter [36250/80000] lr: 7.852e-07, eta: 11:52:16, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7201, decode.acc_seg: 63.7970, aux.loss_ce: 0.3159, aux.acc_seg: 62.9093, loss: 1.0361 2022-04-19 09:40:35,033 - mmseg - INFO - Iter [36300/80000] lr: 7.843e-07, eta: 11:51:25, time: 0.942, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6781, decode.acc_seg: 64.8959, aux.loss_ce: 0.3020, aux.acc_seg: 63.5827, loss: 0.9800 2022-04-19 09:41:21,901 - mmseg - INFO - Iter [36350/80000] lr: 7.834e-07, eta: 11:50:34, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7084, decode.acc_seg: 63.6020, aux.loss_ce: 0.3123, aux.acc_seg: 62.5428, loss: 1.0206 2022-04-19 09:42:08,559 - mmseg - INFO - Iter [36400/80000] lr: 7.825e-07, eta: 11:49:43, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6898, decode.acc_seg: 63.4104, aux.loss_ce: 0.3083, aux.acc_seg: 62.8306, loss: 0.9981 2022-04-19 09:42:55,264 - mmseg - INFO - Iter [36450/80000] lr: 7.816e-07, eta: 11:48:51, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7631, decode.acc_seg: 61.6231, aux.loss_ce: 0.3396, aux.acc_seg: 60.3746, loss: 1.1028 2022-04-19 09:43:42,245 - mmseg - INFO - Iter [36500/80000] lr: 7.807e-07, eta: 11:48:00, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7063, decode.acc_seg: 64.0327, aux.loss_ce: 0.3097, aux.acc_seg: 63.0251, loss: 1.0160 2022-04-19 09:44:29,271 - mmseg - INFO - Iter [36550/80000] lr: 7.798e-07, eta: 11:47:09, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6759, decode.acc_seg: 64.2350, aux.loss_ce: 0.3027, aux.acc_seg: 63.0428, loss: 0.9786 2022-04-19 09:45:16,222 - mmseg - INFO - Iter [36600/80000] lr: 7.789e-07, eta: 11:46:18, time: 0.940, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6907, decode.acc_seg: 63.6257, aux.loss_ce: 0.3071, aux.acc_seg: 63.0012, loss: 0.9978 2022-04-19 09:46:03,111 - mmseg - INFO - Iter [36650/80000] lr: 7.780e-07, eta: 11:45:27, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7503, decode.acc_seg: 63.5166, aux.loss_ce: 0.3286, aux.acc_seg: 62.2424, loss: 1.0789 2022-04-19 09:46:49,916 - mmseg - INFO - Iter [36700/80000] lr: 7.771e-07, eta: 11:44:36, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7134, decode.acc_seg: 63.1667, aux.loss_ce: 0.3171, aux.acc_seg: 61.9146, loss: 1.0305 2022-04-19 09:47:36,825 - mmseg - INFO - Iter [36750/80000] lr: 7.762e-07, eta: 11:43:45, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6901, decode.acc_seg: 64.3291, aux.loss_ce: 0.3045, aux.acc_seg: 63.8326, loss: 0.9945 2022-04-19 09:48:23,564 - mmseg - INFO - Iter [36800/80000] lr: 7.753e-07, eta: 11:42:53, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6934, decode.acc_seg: 62.0160, aux.loss_ce: 0.3132, aux.acc_seg: 60.9300, loss: 1.0066 2022-04-19 09:49:10,602 - mmseg - INFO - Iter [36850/80000] lr: 7.745e-07, eta: 11:42:03, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6742, decode.acc_seg: 64.1603, aux.loss_ce: 0.3015, aux.acc_seg: 63.1584, loss: 0.9757 2022-04-19 09:49:57,260 - mmseg - INFO - Iter [36900/80000] lr: 7.736e-07, eta: 11:41:11, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6796, decode.acc_seg: 63.6052, aux.loss_ce: 0.3039, aux.acc_seg: 62.5225, loss: 0.9835 2022-04-19 09:50:44,016 - mmseg - INFO - Iter [36950/80000] lr: 7.727e-07, eta: 11:40:20, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7088, decode.acc_seg: 63.5481, aux.loss_ce: 0.3104, aux.acc_seg: 62.8265, loss: 1.0193 2022-04-19 09:51:33,829 - mmseg - INFO - Saving checkpoint at 37000 iterations 2022-04-19 09:51:48,421 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 09:51:48,602 - mmseg - INFO - Iter [37000/80000] lr: 7.718e-07, eta: 11:39:49, time: 1.288, data_time: 0.055, memory: 73037, decode.loss_ce: 0.7015, decode.acc_seg: 64.3598, aux.loss_ce: 0.3173, aux.acc_seg: 63.5310, loss: 1.0189 2022-04-19 09:52:35,420 - mmseg - INFO - Iter [37050/80000] lr: 7.709e-07, eta: 11:38:58, time: 0.940, data_time: 0.012, memory: 73037, decode.loss_ce: 0.7335, decode.acc_seg: 63.1798, aux.loss_ce: 0.3279, aux.acc_seg: 62.0413, loss: 1.0614 2022-04-19 09:53:21,835 - mmseg - INFO - Iter [37100/80000] lr: 7.700e-07, eta: 11:38:07, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6870, decode.acc_seg: 64.9484, aux.loss_ce: 0.3047, aux.acc_seg: 63.6022, loss: 0.9917 2022-04-19 09:54:08,573 - mmseg - INFO - Iter [37150/80000] lr: 7.691e-07, eta: 11:37:16, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6528, decode.acc_seg: 64.7477, aux.loss_ce: 0.2979, aux.acc_seg: 63.5826, loss: 0.9507 2022-04-19 09:54:55,508 - mmseg - INFO - Iter [37200/80000] lr: 7.682e-07, eta: 11:36:25, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6845, decode.acc_seg: 63.1725, aux.loss_ce: 0.3028, aux.acc_seg: 62.5774, loss: 0.9873 2022-04-19 09:55:42,154 - mmseg - INFO - Iter [37250/80000] lr: 7.673e-07, eta: 11:35:33, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6599, decode.acc_seg: 63.6299, aux.loss_ce: 0.2985, aux.acc_seg: 62.2484, loss: 0.9584 2022-04-19 09:56:28,661 - mmseg - INFO - Iter [37300/80000] lr: 7.664e-07, eta: 11:34:42, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6757, decode.acc_seg: 62.5946, aux.loss_ce: 0.3038, aux.acc_seg: 61.2668, loss: 0.9794 2022-04-19 09:57:15,397 - mmseg - INFO - Iter [37350/80000] lr: 7.655e-07, eta: 11:33:51, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6776, decode.acc_seg: 63.5820, aux.loss_ce: 0.3067, aux.acc_seg: 62.9538, loss: 0.9844 2022-04-19 09:58:02,375 - mmseg - INFO - Iter [37400/80000] lr: 7.646e-07, eta: 11:33:00, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7015, decode.acc_seg: 64.4031, aux.loss_ce: 0.3194, aux.acc_seg: 63.1048, loss: 1.0209 2022-04-19 09:58:48,885 - mmseg - INFO - Iter [37450/80000] lr: 7.637e-07, eta: 11:32:08, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6480, decode.acc_seg: 65.5835, aux.loss_ce: 0.2888, aux.acc_seg: 64.5898, loss: 0.9368 2022-04-19 09:59:35,351 - mmseg - INFO - Iter [37500/80000] lr: 7.628e-07, eta: 11:31:17, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6882, decode.acc_seg: 64.6115, aux.loss_ce: 0.3096, aux.acc_seg: 63.6290, loss: 0.9979 2022-04-19 10:00:21,911 - mmseg - INFO - Iter [37550/80000] lr: 7.619e-07, eta: 11:30:26, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6799, decode.acc_seg: 63.9992, aux.loss_ce: 0.3048, aux.acc_seg: 62.7697, loss: 0.9847 2022-04-19 10:01:08,819 - mmseg - INFO - Iter [37600/80000] lr: 7.610e-07, eta: 11:29:35, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6716, decode.acc_seg: 63.4264, aux.loss_ce: 0.3072, aux.acc_seg: 62.0013, loss: 0.9787 2022-04-19 10:01:55,496 - mmseg - INFO - Iter [37650/80000] lr: 7.601e-07, eta: 11:28:44, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7114, decode.acc_seg: 61.8988, aux.loss_ce: 0.3177, aux.acc_seg: 60.7553, loss: 1.0290 2022-04-19 10:02:42,263 - mmseg - INFO - Iter [37700/80000] lr: 7.592e-07, eta: 11:27:52, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6405, decode.acc_seg: 63.9825, aux.loss_ce: 0.2874, aux.acc_seg: 62.8290, loss: 0.9280 2022-04-19 10:03:28,639 - mmseg - INFO - Iter [37750/80000] lr: 7.583e-07, eta: 11:27:01, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6936, decode.acc_seg: 64.4721, aux.loss_ce: 0.3152, aux.acc_seg: 62.8657, loss: 1.0088 2022-04-19 10:04:15,575 - mmseg - INFO - Iter [37800/80000] lr: 7.574e-07, eta: 11:26:10, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6806, decode.acc_seg: 64.3941, aux.loss_ce: 0.3064, aux.acc_seg: 63.2560, loss: 0.9869 2022-04-19 10:05:02,111 - mmseg - INFO - Iter [37850/80000] lr: 7.565e-07, eta: 11:25:19, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6622, decode.acc_seg: 66.4627, aux.loss_ce: 0.3002, aux.acc_seg: 65.2572, loss: 0.9624 2022-04-19 10:05:48,933 - mmseg - INFO - Iter [37900/80000] lr: 7.556e-07, eta: 11:24:28, time: 0.937, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6861, decode.acc_seg: 65.7331, aux.loss_ce: 0.3085, aux.acc_seg: 64.7525, loss: 0.9946 2022-04-19 10:06:35,350 - mmseg - INFO - Iter [37950/80000] lr: 7.547e-07, eta: 11:23:37, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6489, decode.acc_seg: 64.7360, aux.loss_ce: 0.2920, aux.acc_seg: 63.9166, loss: 0.9409 2022-04-19 10:07:21,897 - mmseg - INFO - Saving checkpoint at 38000 iterations 2022-04-19 10:07:39,599 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 10:07:39,600 - mmseg - INFO - Iter [38000/80000] lr: 7.538e-07, eta: 11:23:05, time: 1.284, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6879, decode.acc_seg: 65.0143, aux.loss_ce: 0.3083, aux.acc_seg: 64.0539, loss: 0.9962 2022-04-19 10:08:26,716 - mmseg - INFO - Iter [38050/80000] lr: 7.529e-07, eta: 11:22:14, time: 0.943, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6683, decode.acc_seg: 64.5520, aux.loss_ce: 0.2964, aux.acc_seg: 63.4194, loss: 0.9646 2022-04-19 10:09:13,562 - mmseg - INFO - Iter [38100/80000] lr: 7.520e-07, eta: 11:21:23, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6247, decode.acc_seg: 65.4387, aux.loss_ce: 0.2816, aux.acc_seg: 64.4395, loss: 0.9063 2022-04-19 10:10:00,616 - mmseg - INFO - Iter [38150/80000] lr: 7.511e-07, eta: 11:20:33, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6877, decode.acc_seg: 65.7074, aux.loss_ce: 0.3082, aux.acc_seg: 64.7250, loss: 0.9959 2022-04-19 10:10:47,229 - mmseg - INFO - Iter [38200/80000] lr: 7.502e-07, eta: 11:19:41, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6627, decode.acc_seg: 64.3923, aux.loss_ce: 0.2969, aux.acc_seg: 63.2607, loss: 0.9595 2022-04-19 10:11:33,618 - mmseg - INFO - Iter [38250/80000] lr: 7.493e-07, eta: 11:18:50, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6784, decode.acc_seg: 63.4244, aux.loss_ce: 0.3004, aux.acc_seg: 62.8621, loss: 0.9787 2022-04-19 10:12:20,376 - mmseg - INFO - Iter [38300/80000] lr: 7.484e-07, eta: 11:17:59, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6940, decode.acc_seg: 63.6599, aux.loss_ce: 0.3124, aux.acc_seg: 62.3890, loss: 1.0065 2022-04-19 10:13:06,926 - mmseg - INFO - Iter [38350/80000] lr: 7.475e-07, eta: 11:17:08, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6923, decode.acc_seg: 64.1593, aux.loss_ce: 0.3093, aux.acc_seg: 62.9235, loss: 1.0017 2022-04-19 10:13:54,077 - mmseg - INFO - Iter [38400/80000] lr: 7.466e-07, eta: 11:16:17, time: 0.941, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6489, decode.acc_seg: 63.5864, aux.loss_ce: 0.2938, aux.acc_seg: 62.5587, loss: 0.9427 2022-04-19 10:14:40,620 - mmseg - INFO - Iter [38450/80000] lr: 7.457e-07, eta: 11:15:26, time: 0.933, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6695, decode.acc_seg: 64.8070, aux.loss_ce: 0.3007, aux.acc_seg: 63.5929, loss: 0.9702 2022-04-19 10:15:27,046 - mmseg - INFO - Iter [38500/80000] lr: 7.448e-07, eta: 11:14:35, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6691, decode.acc_seg: 64.3689, aux.loss_ce: 0.2994, aux.acc_seg: 63.3162, loss: 0.9685 2022-04-19 10:16:13,732 - mmseg - INFO - Iter [38550/80000] lr: 7.439e-07, eta: 11:13:44, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6836, decode.acc_seg: 62.3071, aux.loss_ce: 0.3028, aux.acc_seg: 61.5822, loss: 0.9864 2022-04-19 10:17:00,358 - mmseg - INFO - Iter [38600/80000] lr: 7.430e-07, eta: 11:12:53, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6627, decode.acc_seg: 64.6093, aux.loss_ce: 0.2971, aux.acc_seg: 63.4634, loss: 0.9599 2022-04-19 10:17:46,707 - mmseg - INFO - Iter [38650/80000] lr: 7.421e-07, eta: 11:12:01, time: 0.929, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6909, decode.acc_seg: 64.8388, aux.loss_ce: 0.3098, aux.acc_seg: 63.5281, loss: 1.0007 2022-04-19 10:18:33,163 - mmseg - INFO - Iter [38700/80000] lr: 7.412e-07, eta: 11:11:10, time: 0.929, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6838, decode.acc_seg: 63.5199, aux.loss_ce: 0.3038, aux.acc_seg: 62.6156, loss: 0.9875 2022-04-19 10:19:19,568 - mmseg - INFO - Iter [38750/80000] lr: 7.404e-07, eta: 11:10:19, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6850, decode.acc_seg: 62.8415, aux.loss_ce: 0.3034, aux.acc_seg: 61.7822, loss: 0.9885 2022-04-19 10:20:06,084 - mmseg - INFO - Iter [38800/80000] lr: 7.395e-07, eta: 11:09:28, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6507, decode.acc_seg: 64.9688, aux.loss_ce: 0.2924, aux.acc_seg: 63.6879, loss: 0.9431 2022-04-19 10:20:52,712 - mmseg - INFO - Iter [38850/80000] lr: 7.386e-07, eta: 11:08:37, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6963, decode.acc_seg: 65.3259, aux.loss_ce: 0.3114, aux.acc_seg: 64.3983, loss: 1.0077 2022-04-19 10:21:39,183 - mmseg - INFO - Iter [38900/80000] lr: 7.377e-07, eta: 11:07:46, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6638, decode.acc_seg: 63.0022, aux.loss_ce: 0.2964, aux.acc_seg: 62.2243, loss: 0.9601 2022-04-19 10:22:25,557 - mmseg - INFO - Iter [38950/80000] lr: 7.368e-07, eta: 11:06:55, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7004, decode.acc_seg: 63.8167, aux.loss_ce: 0.3101, aux.acc_seg: 63.0165, loss: 1.0105 2022-04-19 10:23:12,439 - mmseg - INFO - Saving checkpoint at 39000 iterations 2022-04-19 10:23:27,177 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 10:23:27,178 - mmseg - INFO - Iter [39000/80000] lr: 7.359e-07, eta: 11:06:19, time: 1.232, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6965, decode.acc_seg: 65.2061, aux.loss_ce: 0.3125, aux.acc_seg: 63.8856, loss: 1.0090 2022-04-19 10:24:14,252 - mmseg - INFO - Iter [39050/80000] lr: 7.350e-07, eta: 11:05:29, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6933, decode.acc_seg: 63.0315, aux.loss_ce: 0.3072, aux.acc_seg: 62.0136, loss: 1.0005 2022-04-19 10:25:00,803 - mmseg - INFO - Iter [39100/80000] lr: 7.341e-07, eta: 11:04:38, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6943, decode.acc_seg: 63.9233, aux.loss_ce: 0.3164, aux.acc_seg: 62.2147, loss: 1.0107 2022-04-19 10:25:47,531 - mmseg - INFO - Iter [39150/80000] lr: 7.332e-07, eta: 11:03:47, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7132, decode.acc_seg: 63.2667, aux.loss_ce: 0.3168, aux.acc_seg: 62.6958, loss: 1.0300 2022-04-19 10:26:34,175 - mmseg - INFO - Iter [39200/80000] lr: 7.323e-07, eta: 11:02:56, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6714, decode.acc_seg: 64.0100, aux.loss_ce: 0.3022, aux.acc_seg: 62.8243, loss: 0.9735 2022-04-19 10:27:20,686 - mmseg - INFO - Iter [39250/80000] lr: 7.314e-07, eta: 11:02:05, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7015, decode.acc_seg: 63.0131, aux.loss_ce: 0.3102, aux.acc_seg: 62.1309, loss: 1.0117 2022-04-19 10:28:07,340 - mmseg - INFO - Iter [39300/80000] lr: 7.305e-07, eta: 11:01:14, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6829, decode.acc_seg: 64.5459, aux.loss_ce: 0.3030, aux.acc_seg: 63.9046, loss: 0.9859 2022-04-19 10:28:53,898 - mmseg - INFO - Iter [39350/80000] lr: 7.296e-07, eta: 11:00:23, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7009, decode.acc_seg: 63.6331, aux.loss_ce: 0.3138, aux.acc_seg: 62.4929, loss: 1.0148 2022-04-19 10:29:40,618 - mmseg - INFO - Iter [39400/80000] lr: 7.287e-07, eta: 10:59:32, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6641, decode.acc_seg: 64.1566, aux.loss_ce: 0.3024, aux.acc_seg: 62.9513, loss: 0.9665 2022-04-19 10:30:27,385 - mmseg - INFO - Iter [39450/80000] lr: 7.278e-07, eta: 10:58:41, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6625, decode.acc_seg: 64.7063, aux.loss_ce: 0.2953, aux.acc_seg: 63.6632, loss: 0.9579 2022-04-19 10:31:13,898 - mmseg - INFO - Iter [39500/80000] lr: 7.269e-07, eta: 10:57:50, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6552, decode.acc_seg: 63.3829, aux.loss_ce: 0.2963, aux.acc_seg: 62.0689, loss: 0.9515 2022-04-19 10:32:00,423 - mmseg - INFO - Iter [39550/80000] lr: 7.260e-07, eta: 10:56:59, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6791, decode.acc_seg: 65.3428, aux.loss_ce: 0.3014, aux.acc_seg: 64.6586, loss: 0.9806 2022-04-19 10:32:46,766 - mmseg - INFO - Iter [39600/80000] lr: 7.251e-07, eta: 10:56:08, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6605, decode.acc_seg: 63.1259, aux.loss_ce: 0.2963, aux.acc_seg: 62.0215, loss: 0.9568 2022-04-19 10:33:33,364 - mmseg - INFO - Iter [39650/80000] lr: 7.242e-07, eta: 10:55:17, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6849, decode.acc_seg: 64.7422, aux.loss_ce: 0.3104, aux.acc_seg: 63.4208, loss: 0.9953 2022-04-19 10:34:19,804 - mmseg - INFO - Iter [39700/80000] lr: 7.233e-07, eta: 10:54:26, time: 0.929, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7069, decode.acc_seg: 62.5685, aux.loss_ce: 0.3139, aux.acc_seg: 61.6120, loss: 1.0208 2022-04-19 10:35:06,242 - mmseg - INFO - Iter [39750/80000] lr: 7.224e-07, eta: 10:53:35, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6806, decode.acc_seg: 64.0790, aux.loss_ce: 0.3012, aux.acc_seg: 63.2626, loss: 0.9819 2022-04-19 10:35:52,878 - mmseg - INFO - Iter [39800/80000] lr: 7.215e-07, eta: 10:52:44, time: 0.933, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6971, decode.acc_seg: 63.1237, aux.loss_ce: 0.3106, aux.acc_seg: 62.0891, loss: 1.0077 2022-04-19 10:36:39,271 - mmseg - INFO - Iter [39850/80000] lr: 7.206e-07, eta: 10:51:53, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7098, decode.acc_seg: 63.6244, aux.loss_ce: 0.3174, aux.acc_seg: 62.4516, loss: 1.0271 2022-04-19 10:37:26,190 - mmseg - INFO - Iter [39900/80000] lr: 7.197e-07, eta: 10:51:03, time: 0.937, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7004, decode.acc_seg: 62.2101, aux.loss_ce: 0.3099, aux.acc_seg: 61.4163, loss: 1.0103 2022-04-19 10:38:12,891 - mmseg - INFO - Iter [39950/80000] lr: 7.188e-07, eta: 10:50:12, time: 0.936, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7126, decode.acc_seg: 62.5279, aux.loss_ce: 0.3186, aux.acc_seg: 61.2536, loss: 1.0311 2022-04-19 10:38:59,283 - mmseg - INFO - Saving checkpoint at 40000 iterations 2022-04-19 10:39:10,927 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 10:39:10,928 - mmseg - INFO - Iter [40000/80000] lr: 7.179e-07, eta: 10:49:33, time: 1.161, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6857, decode.acc_seg: 63.2527, aux.loss_ce: 0.3077, aux.acc_seg: 62.2807, loss: 0.9934 2022-04-19 10:43:07,618 - mmseg - INFO - per class results: 2022-04-19 10:43:07,630 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.55 | 95.28 | | bicycle | 71.01 | 89.82 | | car | 65.94 | 86.42 | | motorcycle | 84.8 | 93.6 | | airplane | 79.47 | 95.44 | | bus | 85.19 | 92.79 | | train | 85.47 | 96.18 | | truck | 67.47 | 84.58 | | boat | 67.35 | 84.27 | | traffic light | 67.69 | 85.54 | | fire hydrant | 84.86 | 97.6 | | stop sign | 90.04 | 98.37 | | parking meter | 76.25 | 90.17 | | bench | 56.3 | 75.63 | | bird | 83.55 | 91.24 | | cat | 82.06 | 90.62 | | dog | 76.03 | 83.61 | | horse | 86.93 | 95.2 | | sheep | 86.83 | 97.05 | | cow | 87.66 | 93.71 | | elephant | 92.3 | 97.02 | | bear | 91.33 | 96.64 | | zebra | 92.06 | 97.19 | | giraffe | 86.09 | 95.41 | | backpack | 38.37 | 59.65 | | umbrella | 86.69 | 93.4 | | handbag | 38.12 | 57.99 | | tie | 4.36 | 7.3 | | suitcase | 80.44 | 94.52 | | frisbee | 82.17 | 90.67 | | skis | 48.2 | 62.13 | | snowboard | 65.39 | 75.59 | | sports ball | 60.6 | 70.78 | | kite | 71.2 | 87.33 | | baseball bat | 55.75 | 74.97 | | baseball glove | 73.34 | 85.13 | | skateboard | 80.46 | 89.93 | | surfboard | 81.9 | 89.3 | | tennis racket | 84.67 | 94.19 | | bottle | 53.12 | 76.09 | | wine glass | 59.35 | 80.09 | | cup | 55.5 | 81.96 | | fork | 45.8 | 60.56 | | knife | 38.71 | 52.82 | | spoon | 40.41 | 54.76 | | bowl | 48.14 | 63.95 | | banana | 70.04 | 93.48 | | apple | 55.94 | 78.98 | | sandwich | 48.76 | 68.62 | | orange | 72.75 | 86.34 | | broccoli | 59.87 | 83.28 | | carrot | 57.9 | 80.44 | | hot dog | 58.21 | 72.28 | | pizza | 76.12 | 91.73 | | donut | 77.99 | 94.12 | | cake | 66.64 | 86.61 | | chair | 52.5 | 74.1 | | couch | 59.57 | 81.37 | | potted plant | 31.84 | 50.82 | | bed | 65.54 | 82.81 | | dining table | 47.26 | 71.78 | | toilet | 83.27 | 95.25 | | tv | 73.48 | 87.38 | | laptop | 77.21 | 92.53 | | mouse | 71.77 | 90.6 | | remote | 62.83 | 82.7 | | keyboard | 66.27 | 79.63 | | cell phone | 76.89 | 88.44 | | microwave | 68.97 | 82.7 | | oven | 57.25 | 87.4 | | toaster | 64.63 | 66.41 | | sink | 61.96 | 86.81 | | refrigerator | 77.96 | 92.72 | | book | 51.66 | 74.37 | | clock | 71.17 | 83.94 | | vase | 62.3 | 82.52 | | scissors | 70.16 | 96.16 | | teddy bear | 79.73 | 93.01 | | hair drier | 47.53 | 51.28 | | toothbrush | 50.67 | 73.65 | | banner | 28.68 | 75.78 | | blanket | 6.83 | 8.41 | | branch | 11.34 | 12.8 | | bridge | 38.9 | 58.64 | | building-other | 55.8 | 71.61 | | bush | 33.84 | 43.96 | | cabinet | 57.78 | 77.39 | | cage | 21.5 | 31.75 | | cardboard | 49.32 | 66.16 | | carpet | 53.06 | 78.03 | | ceiling-other | 65.55 | 87.21 | | ceiling-tile | 0.26 | 0.26 | | cloth | 3.76 | 3.78 | | clothes | 15.5 | 17.89 | | clouds | 51.11 | 69.36 | | counter | 28.2 | 63.47 | | cupboard | 0.0 | 0.0 | | curtain | 66.06 | 86.21 | | desk-stuff | 48.36 | 72.72 | | dirt | 42.58 | 70.32 | | door-stuff | 45.45 | 71.22 | | fence | 33.19 | 54.52 | | floor-marble | 5.91 | 6.58 | | floor-other | 20.47 | 27.03 | | floor-stone | 8.39 | 12.0 | | floor-tile | 61.17 | 76.66 | | floor-wood | 61.88 | 80.69 | | flower | 39.63 | 62.66 | | fog | 17.58 | 20.34 | | food-other | 28.54 | 34.56 | | fruit | 43.02 | 57.24 | | furniture-other | 17.61 | 21.79 | | grass | 70.71 | 84.16 | | gravel | 28.55 | 36.98 | | ground-other | 2.23 | 2.53 | | hill | 11.02 | 13.14 | | house | 30.15 | 38.57 | | leaves | 28.09 | 34.91 | | light | 41.62 | 54.04 | | mat | 0.0 | 0.0 | | metal | 31.27 | 39.9 | | mirror-stuff | 54.64 | 79.28 | | moss | 0.0 | 0.0 | | mountain | 53.93 | 71.84 | | mud | 5.86 | 9.06 | | napkin | 13.11 | 16.94 | | net | 47.7 | 70.25 | | paper | 32.57 | 43.36 | | pavement | 48.69 | 62.74 | | pillow | 11.12 | 13.22 | | plant-other | 18.86 | 26.99 | | plastic | 22.34 | 26.88 | | platform | 28.53 | 49.58 | | playingfield | 65.79 | 81.19 | | railing | 7.87 | 12.88 | | railroad | 61.3 | 85.29 | | river | 46.87 | 68.52 | | road | 65.1 | 88.61 | | rock | 44.68 | 70.96 | | roof | 22.71 | 28.8 | | rug | 36.97 | 58.29 | | salad | 0.07 | 0.07 | | sand | 65.01 | 73.28 | | sea | 84.73 | 93.7 | | shelf | 36.16 | 49.51 | | sky-other | 72.52 | 86.0 | | skyscraper | 39.84 | 54.72 | | snow | 90.57 | 96.12 | | solid-other | 0.0 | 0.0 | | stairs | 30.3 | 61.87 | | stone | 2.48 | 2.85 | | straw | 29.66 | 39.77 | | structural-other | 0.38 | 0.39 | | table | 20.94 | 27.23 | | tent | 9.22 | 11.91 | | textile-other | 13.72 | 19.22 | | towel | 40.64 | 55.25 | | tree | 73.79 | 89.54 | | vegetable | 42.7 | 58.37 | | wall-brick | 46.04 | 70.14 | | wall-concrete | 61.45 | 81.21 | | wall-other | 20.41 | 27.55 | | wall-panel | 3.64 | 4.05 | | wall-stone | 28.09 | 37.47 | | wall-tile | 68.38 | 85.37 | | wall-wood | 41.16 | 59.53 | | water-other | 20.79 | 28.28 | | waterdrops | 0.0 | 0.0 | | window-blind | 54.15 | 65.39 | | window-other | 48.66 | 70.87 | | wood | 27.58 | 38.89 | +------------------+-------+-------+ 2022-04-19 10:43:07,631 - mmseg - INFO - Summary: 2022-04-19 10:43:07,631 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 73.01 | 49.53 | 62.98 | +-------+-------+-------+ 2022-04-19 10:43:07,650 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 10:43:07,650 - mmseg - INFO - Iter(val) [625] aAcc: 0.7301, mIoU: 0.4953, mAcc: 0.6298, IoU.person: 0.8655, IoU.bicycle: 0.7101, IoU.car: 0.6594, IoU.motorcycle: 0.8480, IoU.airplane: 0.7947, IoU.bus: 0.8519, IoU.train: 0.8547, IoU.truck: 0.6747, IoU.boat: 0.6735, IoU.traffic light: 0.6769, IoU.fire hydrant: 0.8486, IoU.stop sign: 0.9004, IoU.parking meter: 0.7625, IoU.bench: 0.5630, IoU.bird: 0.8355, IoU.cat: 0.8206, IoU.dog: 0.7603, IoU.horse: 0.8693, IoU.sheep: 0.8683, IoU.cow: 0.8766, IoU.elephant: 0.9230, IoU.bear: 0.9133, IoU.zebra: 0.9206, IoU.giraffe: 0.8609, IoU.backpack: 0.3837, IoU.umbrella: 0.8669, IoU.handbag: 0.3812, IoU.tie: 0.0436, IoU.suitcase: 0.8044, IoU.frisbee: 0.8217, IoU.skis: 0.4820, IoU.snowboard: 0.6539, IoU.sports ball: 0.6060, IoU.kite: 0.7120, IoU.baseball bat: 0.5575, IoU.baseball glove: 0.7334, IoU.skateboard: 0.8046, IoU.surfboard: 0.8190, IoU.tennis racket: 0.8467, IoU.bottle: 0.5312, IoU.wine glass: 0.5935, IoU.cup: 0.5550, IoU.fork: 0.4580, IoU.knife: 0.3871, IoU.spoon: 0.4041, IoU.bowl: 0.4814, IoU.banana: 0.7004, IoU.apple: 0.5594, IoU.sandwich: 0.4876, IoU.orange: 0.7275, IoU.broccoli: 0.5987, IoU.carrot: 0.5790, IoU.hot dog: 0.5821, IoU.pizza: 0.7612, IoU.donut: 0.7799, IoU.cake: 0.6664, IoU.chair: 0.5250, IoU.couch: 0.5957, IoU.potted plant: 0.3184, IoU.bed: 0.6554, IoU.dining table: 0.4726, IoU.toilet: 0.8327, IoU.tv: 0.7348, IoU.laptop: 0.7721, IoU.mouse: 0.7177, IoU.remote: 0.6283, IoU.keyboard: 0.6627, IoU.cell phone: 0.7689, IoU.microwave: 0.6897, IoU.oven: 0.5725, IoU.toaster: 0.6463, IoU.sink: 0.6196, IoU.refrigerator: 0.7796, IoU.book: 0.5166, IoU.clock: 0.7117, IoU.vase: 0.6230, IoU.scissors: 0.7016, IoU.teddy bear: 0.7973, IoU.hair drier: 0.4753, IoU.toothbrush: 0.5067, IoU.banner: 0.2868, IoU.blanket: 0.0683, IoU.branch: 0.1134, IoU.bridge: 0.3890, IoU.building-other: 0.5580, IoU.bush: 0.3384, IoU.cabinet: 0.5778, IoU.cage: 0.2150, IoU.cardboard: 0.4932, IoU.carpet: 0.5306, IoU.ceiling-other: 0.6555, IoU.ceiling-tile: 0.0026, IoU.cloth: 0.0376, IoU.clothes: 0.1550, IoU.clouds: 0.5111, IoU.counter: 0.2820, IoU.cupboard: 0.0000, IoU.curtain: 0.6606, IoU.desk-stuff: 0.4836, IoU.dirt: 0.4258, IoU.door-stuff: 0.4545, IoU.fence: 0.3319, IoU.floor-marble: 0.0591, IoU.floor-other: 0.2047, IoU.floor-stone: 0.0839, IoU.floor-tile: 0.6117, IoU.floor-wood: 0.6188, IoU.flower: 0.3963, IoU.fog: 0.1758, IoU.food-other: 0.2854, IoU.fruit: 0.4302, IoU.furniture-other: 0.1761, IoU.grass: 0.7071, IoU.gravel: 0.2855, IoU.ground-other: 0.0223, IoU.hill: 0.1102, IoU.house: 0.3015, IoU.leaves: 0.2809, IoU.light: 0.4162, IoU.mat: 0.0000, IoU.metal: 0.3127, IoU.mirror-stuff: 0.5464, IoU.moss: 0.0000, IoU.mountain: 0.5393, IoU.mud: 0.0586, IoU.napkin: 0.1311, IoU.net: 0.4770, IoU.paper: 0.3257, IoU.pavement: 0.4869, IoU.pillow: 0.1112, IoU.plant-other: 0.1886, IoU.plastic: 0.2234, IoU.platform: 0.2853, IoU.playingfield: 0.6579, IoU.railing: 0.0787, IoU.railroad: 0.6130, IoU.river: 0.4687, IoU.road: 0.6510, IoU.rock: 0.4468, IoU.roof: 0.2271, IoU.rug: 0.3697, IoU.salad: 0.0007, IoU.sand: 0.6501, IoU.sea: 0.8473, IoU.shelf: 0.3616, IoU.sky-other: 0.7252, IoU.skyscraper: 0.3984, IoU.snow: 0.9057, IoU.solid-other: 0.0000, IoU.stairs: 0.3030, IoU.stone: 0.0248, IoU.straw: 0.2966, IoU.structural-other: 0.0038, IoU.table: 0.2094, IoU.tent: 0.0922, IoU.textile-other: 0.1372, IoU.towel: 0.4064, IoU.tree: 0.7379, IoU.vegetable: 0.4270, IoU.wall-brick: 0.4604, IoU.wall-concrete: 0.6145, IoU.wall-other: 0.2041, IoU.wall-panel: 0.0364, IoU.wall-stone: 0.2809, IoU.wall-tile: 0.6838, IoU.wall-wood: 0.4116, IoU.water-other: 0.2079, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5415, IoU.window-other: 0.4866, IoU.wood: 0.2758, Acc.person: 0.9528, Acc.bicycle: 0.8982, Acc.car: 0.8642, Acc.motorcycle: 0.9360, Acc.airplane: 0.9544, Acc.bus: 0.9279, Acc.train: 0.9618, Acc.truck: 0.8458, Acc.boat: 0.8427, Acc.traffic light: 0.8554, Acc.fire hydrant: 0.9760, Acc.stop sign: 0.9837, Acc.parking meter: 0.9017, Acc.bench: 0.7563, Acc.bird: 0.9124, Acc.cat: 0.9062, Acc.dog: 0.8361, Acc.horse: 0.9520, Acc.sheep: 0.9705, Acc.cow: 0.9371, Acc.elephant: 0.9702, Acc.bear: 0.9664, Acc.zebra: 0.9719, Acc.giraffe: 0.9541, Acc.backpack: 0.5965, Acc.umbrella: 0.9340, Acc.handbag: 0.5799, Acc.tie: 0.0730, Acc.suitcase: 0.9452, Acc.frisbee: 0.9067, Acc.skis: 0.6213, Acc.snowboard: 0.7559, Acc.sports ball: 0.7078, Acc.kite: 0.8733, Acc.baseball bat: 0.7497, Acc.baseball glove: 0.8513, Acc.skateboard: 0.8993, Acc.surfboard: 0.8930, Acc.tennis racket: 0.9419, Acc.bottle: 0.7609, Acc.wine glass: 0.8009, Acc.cup: 0.8196, Acc.fork: 0.6056, Acc.knife: 0.5282, Acc.spoon: 0.5476, Acc.bowl: 0.6395, Acc.banana: 0.9348, Acc.apple: 0.7898, Acc.sandwich: 0.6862, Acc.orange: 0.8634, Acc.broccoli: 0.8328, Acc.carrot: 0.8044, Acc.hot dog: 0.7228, Acc.pizza: 0.9173, Acc.donut: 0.9412, Acc.cake: 0.8661, Acc.chair: 0.7410, Acc.couch: 0.8137, Acc.potted plant: 0.5082, Acc.bed: 0.8281, Acc.dining table: 0.7178, Acc.toilet: 0.9525, Acc.tv: 0.8738, Acc.laptop: 0.9253, Acc.mouse: 0.9060, Acc.remote: 0.8270, Acc.keyboard: 0.7963, Acc.cell phone: 0.8844, Acc.microwave: 0.8270, Acc.oven: 0.8740, Acc.toaster: 0.6641, Acc.sink: 0.8681, Acc.refrigerator: 0.9272, Acc.book: 0.7437, Acc.clock: 0.8394, Acc.vase: 0.8252, Acc.scissors: 0.9616, Acc.teddy bear: 0.9301, Acc.hair drier: 0.5128, Acc.toothbrush: 0.7365, Acc.banner: 0.7578, Acc.blanket: 0.0841, Acc.branch: 0.1280, Acc.bridge: 0.5864, Acc.building-other: 0.7161, Acc.bush: 0.4396, Acc.cabinet: 0.7739, Acc.cage: 0.3175, Acc.cardboard: 0.6616, Acc.carpet: 0.7803, Acc.ceiling-other: 0.8721, Acc.ceiling-tile: 0.0026, Acc.cloth: 0.0378, Acc.clothes: 0.1789, Acc.clouds: 0.6936, Acc.counter: 0.6347, Acc.cupboard: 0.0000, Acc.curtain: 0.8621, Acc.desk-stuff: 0.7272, Acc.dirt: 0.7032, Acc.door-stuff: 0.7122, Acc.fence: 0.5452, Acc.floor-marble: 0.0658, Acc.floor-other: 0.2703, Acc.floor-stone: 0.1200, Acc.floor-tile: 0.7666, Acc.floor-wood: 0.8069, Acc.flower: 0.6266, Acc.fog: 0.2034, Acc.food-other: 0.3456, Acc.fruit: 0.5724, Acc.furniture-other: 0.2179, Acc.grass: 0.8416, Acc.gravel: 0.3698, Acc.ground-other: 0.0253, Acc.hill: 0.1314, Acc.house: 0.3857, Acc.leaves: 0.3491, Acc.light: 0.5404, Acc.mat: 0.0000, Acc.metal: 0.3990, Acc.mirror-stuff: 0.7928, Acc.moss: 0.0000, Acc.mountain: 0.7184, Acc.mud: 0.0906, Acc.napkin: 0.1694, Acc.net: 0.7025, Acc.paper: 0.4336, Acc.pavement: 0.6274, Acc.pillow: 0.1322, Acc.plant-other: 0.2699, Acc.plastic: 0.2688, Acc.platform: 0.4958, Acc.playingfield: 0.8119, Acc.railing: 0.1288, Acc.railroad: 0.8529, Acc.river: 0.6852, Acc.road: 0.8861, Acc.rock: 0.7096, Acc.roof: 0.2880, Acc.rug: 0.5829, Acc.salad: 0.0007, Acc.sand: 0.7328, Acc.sea: 0.9370, Acc.shelf: 0.4951, Acc.sky-other: 0.8600, Acc.skyscraper: 0.5472, Acc.snow: 0.9612, Acc.solid-other: 0.0000, Acc.stairs: 0.6187, Acc.stone: 0.0285, Acc.straw: 0.3977, Acc.structural-other: 0.0039, Acc.table: 0.2723, Acc.tent: 0.1191, Acc.textile-other: 0.1922, Acc.towel: 0.5525, Acc.tree: 0.8954, Acc.vegetable: 0.5837, Acc.wall-brick: 0.7014, Acc.wall-concrete: 0.8121, Acc.wall-other: 0.2755, Acc.wall-panel: 0.0405, Acc.wall-stone: 0.3747, Acc.wall-tile: 0.8537, Acc.wall-wood: 0.5953, Acc.water-other: 0.2828, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6539, Acc.window-other: 0.7087, Acc.wood: 0.3889 2022-04-19 10:43:54,213 - mmseg - INFO - Iter [40050/80000] lr: 7.170e-07, eta: 10:52:38, time: 5.666, data_time: 4.740, memory: 73037, decode.loss_ce: 0.7105, decode.acc_seg: 63.6302, aux.loss_ce: 0.3154, aux.acc_seg: 62.5425, loss: 1.0259 2022-04-19 10:44:40,701 - mmseg - INFO - Iter [40100/80000] lr: 7.161e-07, eta: 10:51:47, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7154, decode.acc_seg: 63.1420, aux.loss_ce: 0.3185, aux.acc_seg: 61.9173, loss: 1.0339 2022-04-19 10:45:27,354 - mmseg - INFO - Iter [40150/80000] lr: 7.152e-07, eta: 10:50:55, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6502, decode.acc_seg: 65.2927, aux.loss_ce: 0.2914, aux.acc_seg: 64.2098, loss: 0.9416 2022-04-19 10:46:14,090 - mmseg - INFO - Iter [40200/80000] lr: 7.143e-07, eta: 10:50:04, time: 0.935, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6988, decode.acc_seg: 64.2018, aux.loss_ce: 0.3094, aux.acc_seg: 63.2133, loss: 1.0082 2022-04-19 10:47:00,707 - mmseg - INFO - Iter [40250/80000] lr: 7.134e-07, eta: 10:49:13, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7041, decode.acc_seg: 62.5079, aux.loss_ce: 0.3110, aux.acc_seg: 61.8391, loss: 1.0152 2022-04-19 10:47:47,815 - mmseg - INFO - Iter [40300/80000] lr: 7.125e-07, eta: 10:48:22, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6868, decode.acc_seg: 63.8852, aux.loss_ce: 0.3081, aux.acc_seg: 62.8823, loss: 0.9949 2022-04-19 10:48:34,499 - mmseg - INFO - Iter [40350/80000] lr: 7.116e-07, eta: 10:47:30, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6730, decode.acc_seg: 64.4079, aux.loss_ce: 0.3015, aux.acc_seg: 63.4605, loss: 0.9745 2022-04-19 10:49:21,396 - mmseg - INFO - Iter [40400/80000] lr: 7.107e-07, eta: 10:46:39, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6834, decode.acc_seg: 64.5082, aux.loss_ce: 0.3043, aux.acc_seg: 63.2264, loss: 0.9876 2022-04-19 10:50:08,180 - mmseg - INFO - Iter [40450/80000] lr: 7.098e-07, eta: 10:45:48, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7089, decode.acc_seg: 63.5462, aux.loss_ce: 0.3141, aux.acc_seg: 62.5897, loss: 1.0230 2022-04-19 10:50:55,024 - mmseg - INFO - Iter [40500/80000] lr: 7.089e-07, eta: 10:44:57, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6412, decode.acc_seg: 64.9889, aux.loss_ce: 0.2837, aux.acc_seg: 63.7295, loss: 0.9249 2022-04-19 10:51:42,145 - mmseg - INFO - Iter [40550/80000] lr: 7.080e-07, eta: 10:44:06, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6703, decode.acc_seg: 64.4618, aux.loss_ce: 0.3012, aux.acc_seg: 63.3099, loss: 0.9715 2022-04-19 10:52:28,918 - mmseg - INFO - Iter [40600/80000] lr: 7.071e-07, eta: 10:43:15, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6764, decode.acc_seg: 64.0084, aux.loss_ce: 0.3060, aux.acc_seg: 63.0798, loss: 0.9824 2022-04-19 10:53:15,644 - mmseg - INFO - Iter [40650/80000] lr: 7.063e-07, eta: 10:42:24, time: 0.935, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7170, decode.acc_seg: 63.6599, aux.loss_ce: 0.3210, aux.acc_seg: 62.3935, loss: 1.0379 2022-04-19 10:54:02,263 - mmseg - INFO - Iter [40700/80000] lr: 7.054e-07, eta: 10:41:33, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6685, decode.acc_seg: 63.5396, aux.loss_ce: 0.2990, aux.acc_seg: 62.8052, loss: 0.9675 2022-04-19 10:54:48,791 - mmseg - INFO - Iter [40750/80000] lr: 7.045e-07, eta: 10:40:42, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6993, decode.acc_seg: 63.8886, aux.loss_ce: 0.3138, aux.acc_seg: 62.5652, loss: 1.0131 2022-04-19 10:55:35,304 - mmseg - INFO - Iter [40800/80000] lr: 7.036e-07, eta: 10:39:50, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6818, decode.acc_seg: 64.5093, aux.loss_ce: 0.3001, aux.acc_seg: 63.7186, loss: 0.9819 2022-04-19 10:56:21,769 - mmseg - INFO - Iter [40850/80000] lr: 7.027e-07, eta: 10:38:59, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7159, decode.acc_seg: 64.3894, aux.loss_ce: 0.3216, aux.acc_seg: 63.2011, loss: 1.0375 2022-04-19 10:57:08,510 - mmseg - INFO - Iter [40900/80000] lr: 7.018e-07, eta: 10:38:08, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7181, decode.acc_seg: 62.7530, aux.loss_ce: 0.3175, aux.acc_seg: 61.9486, loss: 1.0356 2022-04-19 10:57:55,142 - mmseg - INFO - Iter [40950/80000] lr: 7.009e-07, eta: 10:37:17, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6791, decode.acc_seg: 63.2481, aux.loss_ce: 0.3021, aux.acc_seg: 62.3831, loss: 0.9812 2022-04-19 10:58:41,740 - mmseg - INFO - Saving checkpoint at 41000 iterations 2022-04-19 10:58:53,223 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 10:58:53,224 - mmseg - INFO - Iter [41000/80000] lr: 7.000e-07, eta: 10:36:36, time: 1.162, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6617, decode.acc_seg: 64.7618, aux.loss_ce: 0.2953, aux.acc_seg: 63.6941, loss: 0.9570 2022-04-19 10:59:39,999 - mmseg - INFO - Iter [41050/80000] lr: 6.991e-07, eta: 10:35:45, time: 0.935, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6799, decode.acc_seg: 64.6759, aux.loss_ce: 0.3069, aux.acc_seg: 63.2438, loss: 0.9868 2022-04-19 11:00:26,753 - mmseg - INFO - Iter [41100/80000] lr: 6.982e-07, eta: 10:34:54, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6849, decode.acc_seg: 64.6467, aux.loss_ce: 0.3043, aux.acc_seg: 64.1311, loss: 0.9892 2022-04-19 11:01:13,535 - mmseg - INFO - Iter [41150/80000] lr: 6.973e-07, eta: 10:34:03, time: 0.938, data_time: 0.008, memory: 73037, decode.loss_ce: 0.7141, decode.acc_seg: 63.4903, aux.loss_ce: 0.3155, aux.acc_seg: 62.9007, loss: 1.0296 2022-04-19 11:02:00,467 - mmseg - INFO - Iter [41200/80000] lr: 6.964e-07, eta: 10:33:12, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6564, decode.acc_seg: 64.4153, aux.loss_ce: 0.2926, aux.acc_seg: 63.4086, loss: 0.9490 2022-04-19 11:02:47,284 - mmseg - INFO - Iter [41250/80000] lr: 6.955e-07, eta: 10:32:21, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6633, decode.acc_seg: 64.9917, aux.loss_ce: 0.2963, aux.acc_seg: 64.1622, loss: 0.9596 2022-04-19 11:03:34,040 - mmseg - INFO - Iter [41300/80000] lr: 6.946e-07, eta: 10:31:30, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7075, decode.acc_seg: 63.8450, aux.loss_ce: 0.3140, aux.acc_seg: 63.1833, loss: 1.0215 2022-04-19 11:04:20,812 - mmseg - INFO - Iter [41350/80000] lr: 6.937e-07, eta: 10:30:39, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6835, decode.acc_seg: 64.3149, aux.loss_ce: 0.3040, aux.acc_seg: 63.2939, loss: 0.9875 2022-04-19 11:05:07,970 - mmseg - INFO - Iter [41400/80000] lr: 6.928e-07, eta: 10:29:49, time: 0.943, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6748, decode.acc_seg: 63.7264, aux.loss_ce: 0.3004, aux.acc_seg: 62.8826, loss: 0.9752 2022-04-19 11:05:54,525 - mmseg - INFO - Iter [41450/80000] lr: 6.919e-07, eta: 10:28:57, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6887, decode.acc_seg: 64.0947, aux.loss_ce: 0.3105, aux.acc_seg: 62.9258, loss: 0.9991 2022-04-19 11:06:41,204 - mmseg - INFO - Iter [41500/80000] lr: 6.910e-07, eta: 10:28:06, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6713, decode.acc_seg: 64.9584, aux.loss_ce: 0.2976, aux.acc_seg: 63.8089, loss: 0.9689 2022-04-19 11:07:27,944 - mmseg - INFO - Iter [41550/80000] lr: 6.901e-07, eta: 10:27:15, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6582, decode.acc_seg: 64.4568, aux.loss_ce: 0.2994, aux.acc_seg: 63.5467, loss: 0.9576 2022-04-19 11:08:14,889 - mmseg - INFO - Iter [41600/80000] lr: 6.892e-07, eta: 10:26:25, time: 0.939, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6906, decode.acc_seg: 65.9356, aux.loss_ce: 0.3082, aux.acc_seg: 64.8312, loss: 0.9988 2022-04-19 11:09:01,458 - mmseg - INFO - Iter [41650/80000] lr: 6.883e-07, eta: 10:25:34, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7001, decode.acc_seg: 63.5686, aux.loss_ce: 0.3078, aux.acc_seg: 63.0612, loss: 1.0079 2022-04-19 11:09:48,040 - mmseg - INFO - Iter [41700/80000] lr: 6.874e-07, eta: 10:24:42, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6754, decode.acc_seg: 65.0507, aux.loss_ce: 0.3010, aux.acc_seg: 63.8517, loss: 0.9765 2022-04-19 11:10:34,448 - mmseg - INFO - Iter [41750/80000] lr: 6.865e-07, eta: 10:23:51, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6574, decode.acc_seg: 64.5393, aux.loss_ce: 0.2932, aux.acc_seg: 63.8390, loss: 0.9506 2022-04-19 11:11:20,969 - mmseg - INFO - Iter [41800/80000] lr: 6.856e-07, eta: 10:23:00, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6627, decode.acc_seg: 64.2174, aux.loss_ce: 0.2960, aux.acc_seg: 63.1170, loss: 0.9587 2022-04-19 11:12:07,726 - mmseg - INFO - Iter [41850/80000] lr: 6.847e-07, eta: 10:22:09, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6531, decode.acc_seg: 63.9261, aux.loss_ce: 0.2970, aux.acc_seg: 62.2670, loss: 0.9501 2022-04-19 11:12:54,384 - mmseg - INFO - Iter [41900/80000] lr: 6.838e-07, eta: 10:21:18, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6437, decode.acc_seg: 65.4267, aux.loss_ce: 0.2836, aux.acc_seg: 64.9113, loss: 0.9272 2022-04-19 11:13:40,941 - mmseg - INFO - Iter [41950/80000] lr: 6.829e-07, eta: 10:20:27, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6902, decode.acc_seg: 64.6314, aux.loss_ce: 0.3074, aux.acc_seg: 63.3334, loss: 0.9976 2022-04-19 11:14:27,565 - mmseg - INFO - Saving checkpoint at 42000 iterations 2022-04-19 11:14:39,654 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 11:14:39,655 - mmseg - INFO - Iter [42000/80000] lr: 6.820e-07, eta: 10:19:47, time: 1.174, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6945, decode.acc_seg: 63.7294, aux.loss_ce: 0.3107, aux.acc_seg: 62.7564, loss: 1.0051 2022-04-19 11:15:26,453 - mmseg - INFO - Iter [42050/80000] lr: 6.811e-07, eta: 10:18:56, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6985, decode.acc_seg: 63.6393, aux.loss_ce: 0.3081, aux.acc_seg: 62.6700, loss: 1.0066 2022-04-19 11:16:13,072 - mmseg - INFO - Iter [42100/80000] lr: 6.802e-07, eta: 10:18:05, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7055, decode.acc_seg: 63.4396, aux.loss_ce: 0.3136, aux.acc_seg: 62.6868, loss: 1.0191 2022-04-19 11:16:59,823 - mmseg - INFO - Iter [42150/80000] lr: 6.793e-07, eta: 10:17:14, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6812, decode.acc_seg: 64.3654, aux.loss_ce: 0.3049, aux.acc_seg: 63.1831, loss: 0.9860 2022-04-19 11:17:46,485 - mmseg - INFO - Iter [42200/80000] lr: 6.784e-07, eta: 10:16:23, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6440, decode.acc_seg: 65.7833, aux.loss_ce: 0.2877, aux.acc_seg: 64.6497, loss: 0.9317 2022-04-19 11:18:33,175 - mmseg - INFO - Iter [42250/80000] lr: 6.775e-07, eta: 10:15:32, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6845, decode.acc_seg: 63.9952, aux.loss_ce: 0.3057, aux.acc_seg: 63.2656, loss: 0.9902 2022-04-19 11:19:19,958 - mmseg - INFO - Iter [42300/80000] lr: 6.766e-07, eta: 10:14:42, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6524, decode.acc_seg: 64.1551, aux.loss_ce: 0.2900, aux.acc_seg: 62.8403, loss: 0.9423 2022-04-19 11:20:06,499 - mmseg - INFO - Iter [42350/80000] lr: 6.757e-07, eta: 10:13:51, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6616, decode.acc_seg: 63.8087, aux.loss_ce: 0.2926, aux.acc_seg: 62.9354, loss: 0.9542 2022-04-19 11:20:53,392 - mmseg - INFO - Iter [42400/80000] lr: 6.748e-07, eta: 10:13:00, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6803, decode.acc_seg: 64.3537, aux.loss_ce: 0.3033, aux.acc_seg: 63.0176, loss: 0.9836 2022-04-19 11:21:39,864 - mmseg - INFO - Iter [42450/80000] lr: 6.739e-07, eta: 10:12:09, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6739, decode.acc_seg: 65.0111, aux.loss_ce: 0.3044, aux.acc_seg: 63.3969, loss: 0.9783 2022-04-19 11:22:26,277 - mmseg - INFO - Iter [42500/80000] lr: 6.730e-07, eta: 10:11:18, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6758, decode.acc_seg: 64.0694, aux.loss_ce: 0.3042, aux.acc_seg: 62.8712, loss: 0.9799 2022-04-19 11:23:12,881 - mmseg - INFO - Iter [42550/80000] lr: 6.721e-07, eta: 10:10:27, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6936, decode.acc_seg: 62.2610, aux.loss_ce: 0.3121, aux.acc_seg: 61.3672, loss: 1.0057 2022-04-19 11:24:01,960 - mmseg - INFO - Iter [42600/80000] lr: 6.713e-07, eta: 10:09:38, time: 0.982, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6671, decode.acc_seg: 64.5959, aux.loss_ce: 0.2959, aux.acc_seg: 63.1948, loss: 0.9629 2022-04-19 11:24:48,962 - mmseg - INFO - Iter [42650/80000] lr: 6.704e-07, eta: 10:08:47, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6839, decode.acc_seg: 65.5386, aux.loss_ce: 0.3031, aux.acc_seg: 64.9360, loss: 0.9870 2022-04-19 11:25:35,726 - mmseg - INFO - Iter [42700/80000] lr: 6.695e-07, eta: 10:07:57, time: 0.935, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6814, decode.acc_seg: 64.0621, aux.loss_ce: 0.3050, aux.acc_seg: 63.0131, loss: 0.9863 2022-04-19 11:26:22,029 - mmseg - INFO - Iter [42750/80000] lr: 6.686e-07, eta: 10:07:06, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6543, decode.acc_seg: 64.9357, aux.loss_ce: 0.2937, aux.acc_seg: 63.6565, loss: 0.9480 2022-04-19 11:27:08,567 - mmseg - INFO - Iter [42800/80000] lr: 6.677e-07, eta: 10:06:15, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6550, decode.acc_seg: 64.9686, aux.loss_ce: 0.2916, aux.acc_seg: 63.6324, loss: 0.9466 2022-04-19 11:27:55,155 - mmseg - INFO - Iter [42850/80000] lr: 6.668e-07, eta: 10:05:24, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.7133, decode.acc_seg: 63.5971, aux.loss_ce: 0.3180, aux.acc_seg: 62.7037, loss: 1.0313 2022-04-19 11:28:41,927 - mmseg - INFO - Iter [42900/80000] lr: 6.659e-07, eta: 10:04:33, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6417, decode.acc_seg: 64.9390, aux.loss_ce: 0.2868, aux.acc_seg: 63.7711, loss: 0.9286 2022-04-19 11:29:28,855 - mmseg - INFO - Iter [42950/80000] lr: 6.650e-07, eta: 10:03:42, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7013, decode.acc_seg: 63.4255, aux.loss_ce: 0.3152, aux.acc_seg: 62.3080, loss: 1.0165 2022-04-19 11:30:15,476 - mmseg - INFO - Saving checkpoint at 43000 iterations 2022-04-19 11:30:29,787 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 11:30:29,801 - mmseg - INFO - Iter [43000/80000] lr: 6.641e-07, eta: 10:03:04, time: 1.216, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7043, decode.acc_seg: 63.5947, aux.loss_ce: 0.3082, aux.acc_seg: 62.8875, loss: 1.0126 2022-04-19 11:31:16,946 - mmseg - INFO - Iter [43050/80000] lr: 6.632e-07, eta: 10:02:14, time: 0.946, data_time: 0.009, memory: 73037, decode.loss_ce: 0.6979, decode.acc_seg: 63.5137, aux.loss_ce: 0.3084, aux.acc_seg: 62.7482, loss: 1.0064 2022-04-19 11:32:03,845 - mmseg - INFO - Iter [43100/80000] lr: 6.623e-07, eta: 10:01:23, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6387, decode.acc_seg: 66.0630, aux.loss_ce: 0.2861, aux.acc_seg: 64.4663, loss: 0.9248 2022-04-19 11:32:50,343 - mmseg - INFO - Iter [43150/80000] lr: 6.614e-07, eta: 10:00:32, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6702, decode.acc_seg: 63.9817, aux.loss_ce: 0.2994, aux.acc_seg: 63.1979, loss: 0.9697 2022-04-19 11:33:36,773 - mmseg - INFO - Iter [43200/80000] lr: 6.605e-07, eta: 9:59:41, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6923, decode.acc_seg: 64.6087, aux.loss_ce: 0.3037, aux.acc_seg: 63.6027, loss: 0.9961 2022-04-19 11:34:23,283 - mmseg - INFO - Iter [43250/80000] lr: 6.596e-07, eta: 9:58:50, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6626, decode.acc_seg: 64.8185, aux.loss_ce: 0.2939, aux.acc_seg: 63.5187, loss: 0.9566 2022-04-19 11:35:09,817 - mmseg - INFO - Iter [43300/80000] lr: 6.587e-07, eta: 9:57:59, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6934, decode.acc_seg: 64.1158, aux.loss_ce: 0.3081, aux.acc_seg: 63.3008, loss: 1.0014 2022-04-19 11:35:56,418 - mmseg - INFO - Iter [43350/80000] lr: 6.578e-07, eta: 9:57:08, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7307, decode.acc_seg: 62.8166, aux.loss_ce: 0.3241, aux.acc_seg: 61.9269, loss: 1.0549 2022-04-19 11:36:42,910 - mmseg - INFO - Iter [43400/80000] lr: 6.569e-07, eta: 9:56:17, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7004, decode.acc_seg: 63.8025, aux.loss_ce: 0.3138, aux.acc_seg: 63.2223, loss: 1.0142 2022-04-19 11:37:29,425 - mmseg - INFO - Iter [43450/80000] lr: 6.560e-07, eta: 9:55:27, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6813, decode.acc_seg: 65.1903, aux.loss_ce: 0.3062, aux.acc_seg: 63.9631, loss: 0.9875 2022-04-19 11:38:15,696 - mmseg - INFO - Iter [43500/80000] lr: 6.551e-07, eta: 9:54:36, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7157, decode.acc_seg: 62.3590, aux.loss_ce: 0.3128, aux.acc_seg: 61.5793, loss: 1.0285 2022-04-19 11:39:02,227 - mmseg - INFO - Iter [43550/80000] lr: 6.542e-07, eta: 9:53:45, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7027, decode.acc_seg: 64.6721, aux.loss_ce: 0.3101, aux.acc_seg: 63.5701, loss: 1.0128 2022-04-19 11:39:48,786 - mmseg - INFO - Iter [43600/80000] lr: 6.533e-07, eta: 9:52:54, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7030, decode.acc_seg: 64.5304, aux.loss_ce: 0.3117, aux.acc_seg: 63.7027, loss: 1.0147 2022-04-19 11:40:35,814 - mmseg - INFO - Iter [43650/80000] lr: 6.524e-07, eta: 9:52:04, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6977, decode.acc_seg: 62.1262, aux.loss_ce: 0.3088, aux.acc_seg: 61.5098, loss: 1.0064 2022-04-19 11:41:22,589 - mmseg - INFO - Iter [43700/80000] lr: 6.515e-07, eta: 9:51:13, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7207, decode.acc_seg: 64.0924, aux.loss_ce: 0.3165, aux.acc_seg: 62.8378, loss: 1.0373 2022-04-19 11:42:08,962 - mmseg - INFO - Iter [43750/80000] lr: 6.506e-07, eta: 9:50:22, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6543, decode.acc_seg: 65.0364, aux.loss_ce: 0.2939, aux.acc_seg: 63.8470, loss: 0.9482 2022-04-19 11:42:55,708 - mmseg - INFO - Iter [43800/80000] lr: 6.497e-07, eta: 9:49:31, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6901, decode.acc_seg: 64.2964, aux.loss_ce: 0.3070, aux.acc_seg: 63.2430, loss: 0.9971 2022-04-19 11:43:42,211 - mmseg - INFO - Iter [43850/80000] lr: 6.488e-07, eta: 9:48:41, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6890, decode.acc_seg: 64.1912, aux.loss_ce: 0.3064, aux.acc_seg: 63.3383, loss: 0.9954 2022-04-19 11:44:28,653 - mmseg - INFO - Iter [43900/80000] lr: 6.479e-07, eta: 9:47:50, time: 0.931, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6860, decode.acc_seg: 62.7301, aux.loss_ce: 0.3092, aux.acc_seg: 61.4666, loss: 0.9951 2022-04-19 11:45:15,115 - mmseg - INFO - Iter [43950/80000] lr: 6.470e-07, eta: 9:46:59, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7053, decode.acc_seg: 63.7049, aux.loss_ce: 0.3133, aux.acc_seg: 63.0570, loss: 1.0186 2022-04-19 11:46:01,509 - mmseg - INFO - Saving checkpoint at 44000 iterations 2022-04-19 11:46:11,806 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 11:46:11,807 - mmseg - INFO - Iter [44000/80000] lr: 6.461e-07, eta: 9:46:17, time: 1.134, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6732, decode.acc_seg: 63.9474, aux.loss_ce: 0.3015, aux.acc_seg: 62.8558, loss: 0.9748 2022-04-19 11:46:58,359 - mmseg - INFO - Iter [44050/80000] lr: 6.452e-07, eta: 9:45:26, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6807, decode.acc_seg: 65.6441, aux.loss_ce: 0.3070, aux.acc_seg: 64.4200, loss: 0.9878 2022-04-19 11:47:44,929 - mmseg - INFO - Iter [44100/80000] lr: 6.443e-07, eta: 9:44:35, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.7137, decode.acc_seg: 63.0800, aux.loss_ce: 0.3169, aux.acc_seg: 62.0367, loss: 1.0305 2022-04-19 11:48:31,521 - mmseg - INFO - Iter [44150/80000] lr: 6.434e-07, eta: 9:43:44, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6957, decode.acc_seg: 63.7746, aux.loss_ce: 0.3102, aux.acc_seg: 62.5363, loss: 1.0059 2022-04-19 11:49:18,049 - mmseg - INFO - Iter [44200/80000] lr: 6.425e-07, eta: 9:42:54, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6708, decode.acc_seg: 64.4438, aux.loss_ce: 0.2979, aux.acc_seg: 63.5111, loss: 0.9687 2022-04-19 11:50:04,361 - mmseg - INFO - Iter [44250/80000] lr: 6.416e-07, eta: 9:42:03, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6931, decode.acc_seg: 65.4920, aux.loss_ce: 0.3098, aux.acc_seg: 64.3209, loss: 1.0030 2022-04-19 11:50:51,042 - mmseg - INFO - Iter [44300/80000] lr: 6.407e-07, eta: 9:41:12, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6779, decode.acc_seg: 64.1785, aux.loss_ce: 0.3037, aux.acc_seg: 63.1984, loss: 0.9816 2022-04-19 11:51:37,260 - mmseg - INFO - Iter [44350/80000] lr: 6.398e-07, eta: 9:40:21, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7039, decode.acc_seg: 63.0268, aux.loss_ce: 0.3107, aux.acc_seg: 62.3545, loss: 1.0145 2022-04-19 11:52:26,626 - mmseg - INFO - Iter [44400/80000] lr: 6.389e-07, eta: 9:39:33, time: 0.987, data_time: 0.054, memory: 73037, decode.loss_ce: 0.6891, decode.acc_seg: 63.5970, aux.loss_ce: 0.3094, aux.acc_seg: 62.5223, loss: 0.9986 2022-04-19 11:53:13,364 - mmseg - INFO - Iter [44450/80000] lr: 6.380e-07, eta: 9:38:42, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6352, decode.acc_seg: 66.6210, aux.loss_ce: 0.2893, aux.acc_seg: 65.1496, loss: 0.9246 2022-04-19 11:54:00,384 - mmseg - INFO - Iter [44500/80000] lr: 6.372e-07, eta: 9:37:52, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7192, decode.acc_seg: 62.5054, aux.loss_ce: 0.3194, aux.acc_seg: 61.5651, loss: 1.0386 2022-04-19 11:54:46,927 - mmseg - INFO - Iter [44550/80000] lr: 6.363e-07, eta: 9:37:01, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6538, decode.acc_seg: 63.5038, aux.loss_ce: 0.2929, aux.acc_seg: 62.6597, loss: 0.9466 2022-04-19 11:55:33,783 - mmseg - INFO - Iter [44600/80000] lr: 6.354e-07, eta: 9:36:11, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6304, decode.acc_seg: 66.2666, aux.loss_ce: 0.2824, aux.acc_seg: 65.0686, loss: 0.9129 2022-04-19 11:56:20,913 - mmseg - INFO - Iter [44650/80000] lr: 6.345e-07, eta: 9:35:21, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6718, decode.acc_seg: 64.7236, aux.loss_ce: 0.3054, aux.acc_seg: 63.6406, loss: 0.9772 2022-04-19 11:57:07,192 - mmseg - INFO - Iter [44700/80000] lr: 6.336e-07, eta: 9:34:30, time: 0.927, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6645, decode.acc_seg: 64.1126, aux.loss_ce: 0.2971, aux.acc_seg: 62.9001, loss: 0.9617 2022-04-19 11:57:53,690 - mmseg - INFO - Iter [44750/80000] lr: 6.327e-07, eta: 9:33:39, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6461, decode.acc_seg: 65.1084, aux.loss_ce: 0.2931, aux.acc_seg: 63.6863, loss: 0.9392 2022-04-19 11:58:40,331 - mmseg - INFO - Iter [44800/80000] lr: 6.318e-07, eta: 9:32:49, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6789, decode.acc_seg: 63.9680, aux.loss_ce: 0.3054, aux.acc_seg: 62.9970, loss: 0.9843 2022-04-19 11:59:27,482 - mmseg - INFO - Iter [44850/80000] lr: 6.309e-07, eta: 9:31:59, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6833, decode.acc_seg: 62.6505, aux.loss_ce: 0.3045, aux.acc_seg: 61.9191, loss: 0.9879 2022-04-19 12:00:15,612 - mmseg - INFO - Iter [44900/80000] lr: 6.300e-07, eta: 9:31:09, time: 0.963, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6805, decode.acc_seg: 64.7296, aux.loss_ce: 0.3034, aux.acc_seg: 64.0791, loss: 0.9839 2022-04-19 12:01:02,781 - mmseg - INFO - Iter [44950/80000] lr: 6.291e-07, eta: 9:30:19, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6629, decode.acc_seg: 65.3398, aux.loss_ce: 0.2963, aux.acc_seg: 63.9504, loss: 0.9593 2022-04-19 12:01:49,967 - mmseg - INFO - Saving checkpoint at 45000 iterations 2022-04-19 12:02:02,012 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 12:02:02,022 - mmseg - INFO - Iter [45000/80000] lr: 6.282e-07, eta: 9:29:38, time: 1.183, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6523, decode.acc_seg: 65.2349, aux.loss_ce: 0.2917, aux.acc_seg: 63.9232, loss: 0.9440 2022-04-19 12:02:49,001 - mmseg - INFO - Iter [45050/80000] lr: 6.273e-07, eta: 9:28:48, time: 0.941, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6493, decode.acc_seg: 64.7981, aux.loss_ce: 0.2934, aux.acc_seg: 63.4823, loss: 0.9427 2022-04-19 12:03:35,739 - mmseg - INFO - Iter [45100/80000] lr: 6.264e-07, eta: 9:27:58, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6649, decode.acc_seg: 64.8404, aux.loss_ce: 0.2982, aux.acc_seg: 63.9113, loss: 0.9631 2022-04-19 12:04:22,057 - mmseg - INFO - Iter [45150/80000] lr: 6.255e-07, eta: 9:27:07, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6729, decode.acc_seg: 63.2668, aux.loss_ce: 0.3029, aux.acc_seg: 61.8956, loss: 0.9758 2022-04-19 12:05:08,586 - mmseg - INFO - Iter [45200/80000] lr: 6.246e-07, eta: 9:26:16, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6709, decode.acc_seg: 64.7281, aux.loss_ce: 0.3067, aux.acc_seg: 62.8328, loss: 0.9776 2022-04-19 12:05:55,574 - mmseg - INFO - Iter [45250/80000] lr: 6.237e-07, eta: 9:25:26, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6771, decode.acc_seg: 65.7683, aux.loss_ce: 0.3045, aux.acc_seg: 64.7788, loss: 0.9816 2022-04-19 12:06:42,333 - mmseg - INFO - Iter [45300/80000] lr: 6.228e-07, eta: 9:24:36, time: 0.937, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6754, decode.acc_seg: 64.1272, aux.loss_ce: 0.3047, aux.acc_seg: 62.6185, loss: 0.9800 2022-04-19 12:07:28,797 - mmseg - INFO - Iter [45350/80000] lr: 6.219e-07, eta: 9:23:45, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6753, decode.acc_seg: 64.8283, aux.loss_ce: 0.3000, aux.acc_seg: 63.8404, loss: 0.9753 2022-04-19 12:08:15,647 - mmseg - INFO - Iter [45400/80000] lr: 6.210e-07, eta: 9:22:55, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6732, decode.acc_seg: 64.3998, aux.loss_ce: 0.3049, aux.acc_seg: 63.3199, loss: 0.9781 2022-04-19 12:09:02,060 - mmseg - INFO - Iter [45450/80000] lr: 6.201e-07, eta: 9:22:04, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6569, decode.acc_seg: 65.2966, aux.loss_ce: 0.2952, aux.acc_seg: 64.2978, loss: 0.9521 2022-04-19 12:09:48,383 - mmseg - INFO - Iter [45500/80000] lr: 6.192e-07, eta: 9:21:14, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6957, decode.acc_seg: 63.9001, aux.loss_ce: 0.3078, aux.acc_seg: 62.9518, loss: 1.0035 2022-04-19 12:10:34,831 - mmseg - INFO - Iter [45550/80000] lr: 6.183e-07, eta: 9:20:23, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6693, decode.acc_seg: 63.5685, aux.loss_ce: 0.2996, aux.acc_seg: 62.7855, loss: 0.9689 2022-04-19 12:11:21,229 - mmseg - INFO - Iter [45600/80000] lr: 6.174e-07, eta: 9:19:32, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6527, decode.acc_seg: 63.2892, aux.loss_ce: 0.2952, aux.acc_seg: 62.1703, loss: 0.9478 2022-04-19 12:12:07,640 - mmseg - INFO - Iter [45650/80000] lr: 6.165e-07, eta: 9:18:42, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6579, decode.acc_seg: 65.1034, aux.loss_ce: 0.2934, aux.acc_seg: 63.9470, loss: 0.9513 2022-04-19 12:12:54,273 - mmseg - INFO - Iter [45700/80000] lr: 6.156e-07, eta: 9:17:51, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6842, decode.acc_seg: 63.3977, aux.loss_ce: 0.3061, aux.acc_seg: 62.3223, loss: 0.9903 2022-04-19 12:13:40,887 - mmseg - INFO - Iter [45750/80000] lr: 6.147e-07, eta: 9:17:01, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6597, decode.acc_seg: 65.1983, aux.loss_ce: 0.2931, aux.acc_seg: 63.9444, loss: 0.9528 2022-04-19 12:14:27,353 - mmseg - INFO - Iter [45800/80000] lr: 6.138e-07, eta: 9:16:10, time: 0.929, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6723, decode.acc_seg: 64.2747, aux.loss_ce: 0.3050, aux.acc_seg: 63.3110, loss: 0.9773 2022-04-19 12:15:14,046 - mmseg - INFO - Iter [45850/80000] lr: 6.129e-07, eta: 9:15:20, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6557, decode.acc_seg: 64.3870, aux.loss_ce: 0.2945, aux.acc_seg: 63.2200, loss: 0.9502 2022-04-19 12:16:00,798 - mmseg - INFO - Iter [45900/80000] lr: 6.120e-07, eta: 9:14:30, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6811, decode.acc_seg: 64.7196, aux.loss_ce: 0.3054, aux.acc_seg: 63.0822, loss: 0.9865 2022-04-19 12:16:47,252 - mmseg - INFO - Iter [45950/80000] lr: 6.111e-07, eta: 9:13:39, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6582, decode.acc_seg: 63.7228, aux.loss_ce: 0.2997, aux.acc_seg: 61.9809, loss: 0.9578 2022-04-19 12:17:34,067 - mmseg - INFO - Saving checkpoint at 46000 iterations 2022-04-19 12:17:44,266 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 12:17:44,266 - mmseg - INFO - Iter [46000/80000] lr: 6.102e-07, eta: 9:12:57, time: 1.140, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6427, decode.acc_seg: 65.1207, aux.loss_ce: 0.2887, aux.acc_seg: 64.2323, loss: 0.9314 2022-04-19 12:18:31,364 - mmseg - INFO - Iter [46050/80000] lr: 6.093e-07, eta: 9:12:07, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6696, decode.acc_seg: 66.2621, aux.loss_ce: 0.3014, aux.acc_seg: 64.9253, loss: 0.9710 2022-04-19 12:19:17,905 - mmseg - INFO - Iter [46100/80000] lr: 6.084e-07, eta: 9:11:16, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6533, decode.acc_seg: 65.1009, aux.loss_ce: 0.2954, aux.acc_seg: 64.3026, loss: 0.9487 2022-04-19 12:20:04,396 - mmseg - INFO - Iter [46150/80000] lr: 6.075e-07, eta: 9:10:26, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6756, decode.acc_seg: 64.4602, aux.loss_ce: 0.3055, aux.acc_seg: 63.4453, loss: 0.9812 2022-04-19 12:20:51,005 - mmseg - INFO - Iter [46200/80000] lr: 6.066e-07, eta: 9:09:35, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6361, decode.acc_seg: 65.1307, aux.loss_ce: 0.2911, aux.acc_seg: 63.5882, loss: 0.9273 2022-04-19 12:21:37,540 - mmseg - INFO - Iter [46250/80000] lr: 6.057e-07, eta: 9:08:45, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7077, decode.acc_seg: 62.8090, aux.loss_ce: 0.3183, aux.acc_seg: 61.9149, loss: 1.0259 2022-04-19 12:22:23,893 - mmseg - INFO - Iter [46300/80000] lr: 6.048e-07, eta: 9:07:54, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6542, decode.acc_seg: 65.6716, aux.loss_ce: 0.2941, aux.acc_seg: 64.6905, loss: 0.9482 2022-04-19 12:23:10,392 - mmseg - INFO - Iter [46350/80000] lr: 6.039e-07, eta: 9:07:04, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6413, decode.acc_seg: 65.9253, aux.loss_ce: 0.2930, aux.acc_seg: 64.4132, loss: 0.9344 2022-04-19 12:23:57,492 - mmseg - INFO - Iter [46400/80000] lr: 6.031e-07, eta: 9:06:14, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6724, decode.acc_seg: 63.3525, aux.loss_ce: 0.3015, aux.acc_seg: 62.5960, loss: 0.9738 2022-04-19 12:24:44,144 - mmseg - INFO - Iter [46450/80000] lr: 6.022e-07, eta: 9:05:24, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6470, decode.acc_seg: 64.2262, aux.loss_ce: 0.2940, aux.acc_seg: 62.7935, loss: 0.9409 2022-04-19 12:25:30,623 - mmseg - INFO - Iter [46500/80000] lr: 6.013e-07, eta: 9:04:33, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6541, decode.acc_seg: 65.7111, aux.loss_ce: 0.2933, aux.acc_seg: 64.5794, loss: 0.9474 2022-04-19 12:26:17,321 - mmseg - INFO - Iter [46550/80000] lr: 6.004e-07, eta: 9:03:43, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6615, decode.acc_seg: 65.3876, aux.loss_ce: 0.2980, aux.acc_seg: 64.1923, loss: 0.9595 2022-04-19 12:27:03,830 - mmseg - INFO - Iter [46600/80000] lr: 5.995e-07, eta: 9:02:52, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6365, decode.acc_seg: 65.6347, aux.loss_ce: 0.2879, aux.acc_seg: 64.1236, loss: 0.9245 2022-04-19 12:27:50,741 - mmseg - INFO - Iter [46650/80000] lr: 5.986e-07, eta: 9:02:02, time: 0.938, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6639, decode.acc_seg: 64.0956, aux.loss_ce: 0.2969, aux.acc_seg: 63.5180, loss: 0.9607 2022-04-19 12:28:37,353 - mmseg - INFO - Iter [46700/80000] lr: 5.977e-07, eta: 9:01:12, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6795, decode.acc_seg: 64.8818, aux.loss_ce: 0.3051, aux.acc_seg: 64.0158, loss: 0.9846 2022-04-19 12:29:23,754 - mmseg - INFO - Iter [46750/80000] lr: 5.968e-07, eta: 9:00:22, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6340, decode.acc_seg: 63.9901, aux.loss_ce: 0.2856, aux.acc_seg: 62.6354, loss: 0.9196 2022-04-19 12:30:10,576 - mmseg - INFO - Iter [46800/80000] lr: 5.959e-07, eta: 8:59:31, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6443, decode.acc_seg: 63.7049, aux.loss_ce: 0.2865, aux.acc_seg: 62.9671, loss: 0.9308 2022-04-19 12:30:57,134 - mmseg - INFO - Iter [46850/80000] lr: 5.950e-07, eta: 8:58:41, time: 0.933, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6491, decode.acc_seg: 65.1942, aux.loss_ce: 0.2964, aux.acc_seg: 64.0446, loss: 0.9455 2022-04-19 12:31:44,008 - mmseg - INFO - Iter [46900/80000] lr: 5.941e-07, eta: 8:57:51, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6513, decode.acc_seg: 65.0082, aux.loss_ce: 0.2909, aux.acc_seg: 64.4976, loss: 0.9423 2022-04-19 12:32:30,476 - mmseg - INFO - Iter [46950/80000] lr: 5.932e-07, eta: 8:57:01, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6882, decode.acc_seg: 64.0035, aux.loss_ce: 0.3083, aux.acc_seg: 62.8139, loss: 0.9965 2022-04-19 12:33:17,348 - mmseg - INFO - Saving checkpoint at 47000 iterations 2022-04-19 12:33:29,064 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 12:33:29,064 - mmseg - INFO - Iter [47000/80000] lr: 5.923e-07, eta: 8:56:19, time: 1.168, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6940, decode.acc_seg: 62.8410, aux.loss_ce: 0.3070, aux.acc_seg: 61.8280, loss: 1.0009 2022-04-19 12:34:16,155 - mmseg - INFO - Iter [47050/80000] lr: 5.914e-07, eta: 8:55:29, time: 0.945, data_time: 0.009, memory: 73037, decode.loss_ce: 0.6510, decode.acc_seg: 64.9853, aux.loss_ce: 0.2909, aux.acc_seg: 64.4239, loss: 0.9418 2022-04-19 12:35:02,557 - mmseg - INFO - Iter [47100/80000] lr: 5.905e-07, eta: 8:54:39, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6644, decode.acc_seg: 64.0358, aux.loss_ce: 0.2984, aux.acc_seg: 63.0906, loss: 0.9628 2022-04-19 12:35:49,182 - mmseg - INFO - Iter [47150/80000] lr: 5.896e-07, eta: 8:53:48, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6816, decode.acc_seg: 64.6106, aux.loss_ce: 0.3089, aux.acc_seg: 63.0544, loss: 0.9905 2022-04-19 12:36:35,761 - mmseg - INFO - Iter [47200/80000] lr: 5.887e-07, eta: 8:52:58, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6527, decode.acc_seg: 65.1091, aux.loss_ce: 0.2938, aux.acc_seg: 63.7918, loss: 0.9465 2022-04-19 12:37:22,594 - mmseg - INFO - Iter [47250/80000] lr: 5.878e-07, eta: 8:52:08, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6362, decode.acc_seg: 65.7119, aux.loss_ce: 0.2839, aux.acc_seg: 64.9166, loss: 0.9201 2022-04-19 12:38:09,254 - mmseg - INFO - Iter [47300/80000] lr: 5.869e-07, eta: 8:51:18, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6685, decode.acc_seg: 64.9232, aux.loss_ce: 0.3003, aux.acc_seg: 63.7707, loss: 0.9688 2022-04-19 12:38:55,908 - mmseg - INFO - Iter [47350/80000] lr: 5.860e-07, eta: 8:50:28, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6740, decode.acc_seg: 64.3297, aux.loss_ce: 0.3013, aux.acc_seg: 63.3516, loss: 0.9753 2022-04-19 12:39:42,429 - mmseg - INFO - Iter [47400/80000] lr: 5.851e-07, eta: 8:49:37, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6320, decode.acc_seg: 65.2885, aux.loss_ce: 0.2840, aux.acc_seg: 63.9914, loss: 0.9159 2022-04-19 12:40:28,956 - mmseg - INFO - Iter [47450/80000] lr: 5.842e-07, eta: 8:48:47, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6648, decode.acc_seg: 64.6831, aux.loss_ce: 0.2979, aux.acc_seg: 63.5679, loss: 0.9627 2022-04-19 12:41:15,619 - mmseg - INFO - Iter [47500/80000] lr: 5.833e-07, eta: 8:47:57, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6456, decode.acc_seg: 65.0531, aux.loss_ce: 0.2886, aux.acc_seg: 64.3623, loss: 0.9342 2022-04-19 12:42:02,195 - mmseg - INFO - Iter [47550/80000] lr: 5.824e-07, eta: 8:47:07, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6798, decode.acc_seg: 65.2746, aux.loss_ce: 0.3022, aux.acc_seg: 64.4589, loss: 0.9820 2022-04-19 12:42:48,604 - mmseg - INFO - Iter [47600/80000] lr: 5.815e-07, eta: 8:46:17, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6632, decode.acc_seg: 64.9851, aux.loss_ce: 0.2979, aux.acc_seg: 63.9111, loss: 0.9611 2022-04-19 12:43:35,008 - mmseg - INFO - Iter [47650/80000] lr: 5.806e-07, eta: 8:45:26, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6657, decode.acc_seg: 65.0676, aux.loss_ce: 0.2982, aux.acc_seg: 63.9089, loss: 0.9639 2022-04-19 12:44:21,788 - mmseg - INFO - Iter [47700/80000] lr: 5.797e-07, eta: 8:44:36, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6761, decode.acc_seg: 64.8428, aux.loss_ce: 0.3008, aux.acc_seg: 64.1054, loss: 0.9769 2022-04-19 12:45:08,380 - mmseg - INFO - Iter [47750/80000] lr: 5.788e-07, eta: 8:43:46, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6917, decode.acc_seg: 64.4867, aux.loss_ce: 0.3125, aux.acc_seg: 63.3956, loss: 1.0042 2022-04-19 12:45:55,149 - mmseg - INFO - Iter [47800/80000] lr: 5.779e-07, eta: 8:42:56, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6718, decode.acc_seg: 64.6820, aux.loss_ce: 0.3034, aux.acc_seg: 63.0999, loss: 0.9752 2022-04-19 12:46:41,773 - mmseg - INFO - Iter [47850/80000] lr: 5.770e-07, eta: 8:42:06, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6627, decode.acc_seg: 65.8505, aux.loss_ce: 0.2961, aux.acc_seg: 64.5722, loss: 0.9588 2022-04-19 12:47:28,133 - mmseg - INFO - Iter [47900/80000] lr: 5.761e-07, eta: 8:41:16, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6489, decode.acc_seg: 64.7428, aux.loss_ce: 0.2896, aux.acc_seg: 63.9804, loss: 0.9385 2022-04-19 12:48:14,580 - mmseg - INFO - Iter [47950/80000] lr: 5.752e-07, eta: 8:40:25, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6952, decode.acc_seg: 63.3973, aux.loss_ce: 0.3116, aux.acc_seg: 62.4746, loss: 1.0068 2022-04-19 12:49:01,244 - mmseg - INFO - Saving checkpoint at 48000 iterations 2022-04-19 12:49:14,083 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 12:49:14,083 - mmseg - INFO - Iter [48000/80000] lr: 5.743e-07, eta: 8:39:44, time: 1.190, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6614, decode.acc_seg: 63.7599, aux.loss_ce: 0.2911, aux.acc_seg: 63.2030, loss: 0.9525 2022-04-19 12:53:09,240 - mmseg - INFO - per class results: 2022-04-19 12:53:09,259 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.68 | 95.73 | | bicycle | 71.27 | 88.11 | | car | 68.29 | 89.19 | | motorcycle | 85.88 | 92.86 | | airplane | 80.88 | 95.07 | | bus | 84.39 | 92.56 | | train | 82.93 | 96.96 | | truck | 66.33 | 80.87 | | boat | 66.06 | 88.94 | | traffic light | 68.34 | 87.65 | | fire hydrant | 83.88 | 98.06 | | stop sign | 91.14 | 97.94 | | parking meter | 74.72 | 89.04 | | bench | 54.95 | 78.57 | | bird | 83.18 | 91.27 | | cat | 81.24 | 89.63 | | dog | 80.75 | 89.85 | | horse | 85.89 | 95.94 | | sheep | 87.23 | 97.0 | | cow | 87.79 | 93.77 | | elephant | 91.5 | 97.77 | | bear | 92.08 | 96.32 | | zebra | 91.65 | 96.29 | | giraffe | 86.35 | 95.69 | | backpack | 40.81 | 61.43 | | umbrella | 87.0 | 94.1 | | handbag | 39.47 | 56.6 | | tie | 3.95 | 5.37 | | suitcase | 82.45 | 93.75 | | frisbee | 80.71 | 91.28 | | skis | 48.34 | 60.68 | | snowboard | 66.05 | 72.56 | | sports ball | 61.18 | 70.87 | | kite | 73.21 | 88.28 | | baseball bat | 56.09 | 74.62 | | baseball glove | 73.85 | 85.32 | | skateboard | 80.83 | 90.65 | | surfboard | 82.5 | 90.65 | | tennis racket | 84.59 | 93.22 | | bottle | 49.92 | 63.99 | | wine glass | 59.51 | 79.55 | | cup | 58.64 | 80.4 | | fork | 47.0 | 64.49 | | knife | 40.15 | 60.27 | | spoon | 41.5 | 55.82 | | bowl | 48.42 | 66.4 | | banana | 70.36 | 95.03 | | apple | 56.68 | 77.5 | | sandwich | 54.09 | 78.77 | | orange | 72.11 | 82.03 | | broccoli | 53.87 | 69.84 | | carrot | 57.98 | 75.28 | | hot dog | 58.98 | 72.7 | | pizza | 76.62 | 95.64 | | donut | 79.58 | 92.61 | | cake | 66.7 | 86.62 | | chair | 52.33 | 73.86 | | couch | 60.45 | 82.13 | | potted plant | 36.22 | 62.25 | | bed | 66.33 | 82.26 | | dining table | 46.62 | 70.9 | | toilet | 79.75 | 96.22 | | tv | 73.0 | 85.75 | | laptop | 76.69 | 95.13 | | mouse | 77.41 | 86.16 | | remote | 59.61 | 74.76 | | keyboard | 63.12 | 71.07 | | cell phone | 75.23 | 87.76 | | microwave | 71.02 | 82.42 | | oven | 57.64 | 82.58 | | toaster | 75.92 | 78.1 | | sink | 60.91 | 82.39 | | refrigerator | 77.79 | 93.44 | | book | 53.47 | 76.13 | | clock | 69.42 | 81.93 | | vase | 61.32 | 87.91 | | scissors | 75.89 | 94.62 | | teddy bear | 80.33 | 92.43 | | hair drier | 52.42 | 54.02 | | toothbrush | 51.94 | 70.24 | | banner | 33.44 | 69.13 | | blanket | 6.69 | 8.84 | | branch | 10.79 | 12.83 | | bridge | 43.68 | 63.22 | | building-other | 55.83 | 73.1 | | bush | 33.31 | 43.87 | | cabinet | 58.43 | 77.05 | | cage | 16.57 | 21.08 | | cardboard | 50.3 | 65.32 | | carpet | 52.83 | 70.0 | | ceiling-other | 67.08 | 83.54 | | ceiling-tile | 8.42 | 8.59 | | cloth | 3.46 | 3.6 | | clothes | 18.63 | 22.39 | | clouds | 52.38 | 74.47 | | counter | 27.05 | 65.8 | | cupboard | 0.0 | 0.0 | | curtain | 68.32 | 81.6 | | desk-stuff | 43.1 | 60.14 | | dirt | 44.05 | 70.46 | | door-stuff | 46.98 | 74.13 | | fence | 34.78 | 64.23 | | floor-marble | 8.96 | 10.49 | | floor-other | 24.32 | 34.26 | | floor-stone | 3.6 | 4.6 | | floor-tile | 62.31 | 76.39 | | floor-wood | 62.52 | 79.57 | | flower | 38.9 | 56.46 | | fog | 16.31 | 18.98 | | food-other | 28.59 | 39.85 | | fruit | 44.23 | 61.29 | | furniture-other | 15.17 | 17.98 | | grass | 70.82 | 83.04 | | gravel | 26.18 | 35.13 | | ground-other | 2.39 | 2.69 | | hill | 11.94 | 14.5 | | house | 30.57 | 36.86 | | leaves | 20.91 | 24.01 | | light | 42.26 | 56.58 | | mat | 0.0 | 0.0 | | metal | 30.11 | 36.86 | | mirror-stuff | 55.94 | 71.77 | | moss | 0.0 | 0.0 | | mountain | 52.96 | 68.31 | | mud | 6.4 | 8.44 | | napkin | 13.56 | 18.24 | | net | 47.3 | 64.26 | | paper | 33.2 | 50.66 | | pavement | 51.67 | 68.65 | | pillow | 14.22 | 16.0 | | plant-other | 17.85 | 26.43 | | plastic | 23.39 | 29.66 | | platform | 29.74 | 48.17 | | playingfield | 69.3 | 87.11 | | railing | 4.27 | 5.56 | | railroad | 60.42 | 84.94 | | river | 47.16 | 70.1 | | road | 65.93 | 85.6 | | rock | 44.76 | 69.02 | | roof | 23.04 | 29.21 | | rug | 37.5 | 58.6 | | salad | 0.0 | 0.0 | | sand | 66.06 | 70.34 | | sea | 84.33 | 91.73 | | shelf | 36.51 | 49.6 | | sky-other | 71.47 | 82.8 | | skyscraper | 40.66 | 52.89 | | snow | 90.01 | 96.38 | | solid-other | 0.0 | 0.0 | | stairs | 30.08 | 63.7 | | stone | 3.91 | 4.53 | | straw | 30.58 | 38.14 | | structural-other | 0.21 | 0.21 | | table | 19.06 | 24.79 | | tent | 9.35 | 12.21 | | textile-other | 15.83 | 23.39 | | towel | 34.23 | 43.49 | | tree | 72.88 | 90.51 | | vegetable | 42.41 | 54.01 | | wall-brick | 49.8 | 69.37 | | wall-concrete | 61.91 | 81.38 | | wall-other | 21.71 | 31.8 | | wall-panel | 2.45 | 2.68 | | wall-stone | 29.42 | 36.41 | | wall-tile | 68.78 | 88.46 | | wall-wood | 41.95 | 57.36 | | water-other | 23.48 | 34.02 | | waterdrops | 0.0 | 0.0 | | window-blind | 52.41 | 61.68 | | window-other | 47.8 | 73.75 | | wood | 27.37 | 38.69 | +------------------+-------+-------+ 2022-04-19 12:53:09,260 - mmseg - INFO - Summary: 2022-04-19 12:53:09,260 - mmseg - INFO - +------+-------+-------+ | aAcc | mIoU | mAcc | +------+-------+-------+ | 73.1 | 49.89 | 62.71 | +------+-------+-------+ 2022-04-19 12:53:09,276 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 12:53:09,277 - mmseg - INFO - Iter(val) [625] aAcc: 0.7310, mIoU: 0.4989, mAcc: 0.6271, IoU.person: 0.8668, IoU.bicycle: 0.7127, IoU.car: 0.6829, IoU.motorcycle: 0.8588, IoU.airplane: 0.8088, IoU.bus: 0.8439, IoU.train: 0.8293, IoU.truck: 0.6633, IoU.boat: 0.6606, IoU.traffic light: 0.6834, IoU.fire hydrant: 0.8388, IoU.stop sign: 0.9114, IoU.parking meter: 0.7472, IoU.bench: 0.5495, IoU.bird: 0.8318, IoU.cat: 0.8124, IoU.dog: 0.8075, IoU.horse: 0.8589, IoU.sheep: 0.8723, IoU.cow: 0.8779, IoU.elephant: 0.9150, IoU.bear: 0.9208, IoU.zebra: 0.9165, IoU.giraffe: 0.8635, IoU.backpack: 0.4081, IoU.umbrella: 0.8700, IoU.handbag: 0.3947, IoU.tie: 0.0395, IoU.suitcase: 0.8245, IoU.frisbee: 0.8071, IoU.skis: 0.4834, IoU.snowboard: 0.6605, IoU.sports ball: 0.6118, IoU.kite: 0.7321, IoU.baseball bat: 0.5609, IoU.baseball glove: 0.7385, IoU.skateboard: 0.8083, IoU.surfboard: 0.8250, IoU.tennis racket: 0.8459, IoU.bottle: 0.4992, IoU.wine glass: 0.5951, IoU.cup: 0.5864, IoU.fork: 0.4700, IoU.knife: 0.4015, IoU.spoon: 0.4150, IoU.bowl: 0.4842, IoU.banana: 0.7036, IoU.apple: 0.5668, IoU.sandwich: 0.5409, IoU.orange: 0.7211, IoU.broccoli: 0.5387, IoU.carrot: 0.5798, IoU.hot dog: 0.5898, IoU.pizza: 0.7662, IoU.donut: 0.7958, IoU.cake: 0.6670, IoU.chair: 0.5233, IoU.couch: 0.6045, IoU.potted plant: 0.3622, IoU.bed: 0.6633, IoU.dining table: 0.4662, IoU.toilet: 0.7975, IoU.tv: 0.7300, IoU.laptop: 0.7669, IoU.mouse: 0.7741, IoU.remote: 0.5961, IoU.keyboard: 0.6312, IoU.cell phone: 0.7523, IoU.microwave: 0.7102, IoU.oven: 0.5764, IoU.toaster: 0.7592, IoU.sink: 0.6091, IoU.refrigerator: 0.7779, IoU.book: 0.5347, IoU.clock: 0.6942, IoU.vase: 0.6132, IoU.scissors: 0.7589, IoU.teddy bear: 0.8033, IoU.hair drier: 0.5242, IoU.toothbrush: 0.5194, IoU.banner: 0.3344, IoU.blanket: 0.0669, IoU.branch: 0.1079, IoU.bridge: 0.4368, IoU.building-other: 0.5583, IoU.bush: 0.3331, IoU.cabinet: 0.5843, IoU.cage: 0.1657, IoU.cardboard: 0.5030, IoU.carpet: 0.5283, IoU.ceiling-other: 0.6708, IoU.ceiling-tile: 0.0842, IoU.cloth: 0.0346, IoU.clothes: 0.1863, IoU.clouds: 0.5238, IoU.counter: 0.2705, IoU.cupboard: 0.0000, IoU.curtain: 0.6832, IoU.desk-stuff: 0.4310, IoU.dirt: 0.4405, IoU.door-stuff: 0.4698, IoU.fence: 0.3478, IoU.floor-marble: 0.0896, IoU.floor-other: 0.2432, IoU.floor-stone: 0.0360, IoU.floor-tile: 0.6231, IoU.floor-wood: 0.6252, IoU.flower: 0.3890, IoU.fog: 0.1631, IoU.food-other: 0.2859, IoU.fruit: 0.4423, IoU.furniture-other: 0.1517, IoU.grass: 0.7082, IoU.gravel: 0.2618, IoU.ground-other: 0.0239, IoU.hill: 0.1194, IoU.house: 0.3057, IoU.leaves: 0.2091, IoU.light: 0.4226, IoU.mat: 0.0000, IoU.metal: 0.3011, IoU.mirror-stuff: 0.5594, IoU.moss: 0.0000, IoU.mountain: 0.5296, IoU.mud: 0.0640, IoU.napkin: 0.1356, IoU.net: 0.4730, IoU.paper: 0.3320, IoU.pavement: 0.5167, IoU.pillow: 0.1422, IoU.plant-other: 0.1785, IoU.plastic: 0.2339, IoU.platform: 0.2974, IoU.playingfield: 0.6930, IoU.railing: 0.0427, IoU.railroad: 0.6042, IoU.river: 0.4716, IoU.road: 0.6593, IoU.rock: 0.4476, IoU.roof: 0.2304, IoU.rug: 0.3750, IoU.salad: 0.0000, IoU.sand: 0.6606, IoU.sea: 0.8433, IoU.shelf: 0.3651, IoU.sky-other: 0.7147, IoU.skyscraper: 0.4066, IoU.snow: 0.9001, IoU.solid-other: 0.0000, IoU.stairs: 0.3008, IoU.stone: 0.0391, IoU.straw: 0.3058, IoU.structural-other: 0.0021, IoU.table: 0.1906, IoU.tent: 0.0935, IoU.textile-other: 0.1583, IoU.towel: 0.3423, IoU.tree: 0.7288, IoU.vegetable: 0.4241, IoU.wall-brick: 0.4980, IoU.wall-concrete: 0.6191, IoU.wall-other: 0.2171, IoU.wall-panel: 0.0245, IoU.wall-stone: 0.2942, IoU.wall-tile: 0.6878, IoU.wall-wood: 0.4195, IoU.water-other: 0.2348, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5241, IoU.window-other: 0.4780, IoU.wood: 0.2737, Acc.person: 0.9573, Acc.bicycle: 0.8811, Acc.car: 0.8919, Acc.motorcycle: 0.9286, Acc.airplane: 0.9507, Acc.bus: 0.9256, Acc.train: 0.9696, Acc.truck: 0.8087, Acc.boat: 0.8894, Acc.traffic light: 0.8765, Acc.fire hydrant: 0.9806, Acc.stop sign: 0.9794, Acc.parking meter: 0.8904, Acc.bench: 0.7857, Acc.bird: 0.9127, Acc.cat: 0.8963, Acc.dog: 0.8985, Acc.horse: 0.9594, Acc.sheep: 0.9700, Acc.cow: 0.9377, Acc.elephant: 0.9777, Acc.bear: 0.9632, Acc.zebra: 0.9629, Acc.giraffe: 0.9569, Acc.backpack: 0.6143, Acc.umbrella: 0.9410, Acc.handbag: 0.5660, Acc.tie: 0.0537, Acc.suitcase: 0.9375, Acc.frisbee: 0.9128, Acc.skis: 0.6068, Acc.snowboard: 0.7256, Acc.sports ball: 0.7087, Acc.kite: 0.8828, Acc.baseball bat: 0.7462, Acc.baseball glove: 0.8532, Acc.skateboard: 0.9065, Acc.surfboard: 0.9065, Acc.tennis racket: 0.9322, Acc.bottle: 0.6399, Acc.wine glass: 0.7955, Acc.cup: 0.8040, Acc.fork: 0.6449, Acc.knife: 0.6027, Acc.spoon: 0.5582, Acc.bowl: 0.6640, Acc.banana: 0.9503, Acc.apple: 0.7750, Acc.sandwich: 0.7877, Acc.orange: 0.8203, Acc.broccoli: 0.6984, Acc.carrot: 0.7528, Acc.hot dog: 0.7270, Acc.pizza: 0.9564, Acc.donut: 0.9261, Acc.cake: 0.8662, Acc.chair: 0.7386, Acc.couch: 0.8213, Acc.potted plant: 0.6225, Acc.bed: 0.8226, Acc.dining table: 0.7090, Acc.toilet: 0.9622, Acc.tv: 0.8575, Acc.laptop: 0.9513, Acc.mouse: 0.8616, Acc.remote: 0.7476, Acc.keyboard: 0.7107, Acc.cell phone: 0.8776, Acc.microwave: 0.8242, Acc.oven: 0.8258, Acc.toaster: 0.7810, Acc.sink: 0.8239, Acc.refrigerator: 0.9344, Acc.book: 0.7613, Acc.clock: 0.8193, Acc.vase: 0.8791, Acc.scissors: 0.9462, Acc.teddy bear: 0.9243, Acc.hair drier: 0.5402, Acc.toothbrush: 0.7024, Acc.banner: 0.6913, Acc.blanket: 0.0884, Acc.branch: 0.1283, Acc.bridge: 0.6322, Acc.building-other: 0.7310, Acc.bush: 0.4387, Acc.cabinet: 0.7705, Acc.cage: 0.2108, Acc.cardboard: 0.6532, Acc.carpet: 0.7000, Acc.ceiling-other: 0.8354, Acc.ceiling-tile: 0.0859, Acc.cloth: 0.0360, Acc.clothes: 0.2239, Acc.clouds: 0.7447, Acc.counter: 0.6580, Acc.cupboard: 0.0000, Acc.curtain: 0.8160, Acc.desk-stuff: 0.6014, Acc.dirt: 0.7046, Acc.door-stuff: 0.7413, Acc.fence: 0.6423, Acc.floor-marble: 0.1049, Acc.floor-other: 0.3426, Acc.floor-stone: 0.0460, Acc.floor-tile: 0.7639, Acc.floor-wood: 0.7957, Acc.flower: 0.5646, Acc.fog: 0.1898, Acc.food-other: 0.3985, Acc.fruit: 0.6129, Acc.furniture-other: 0.1798, Acc.grass: 0.8304, Acc.gravel: 0.3513, Acc.ground-other: 0.0269, Acc.hill: 0.1450, Acc.house: 0.3686, Acc.leaves: 0.2401, Acc.light: 0.5658, Acc.mat: 0.0000, Acc.metal: 0.3686, Acc.mirror-stuff: 0.7177, Acc.moss: 0.0000, Acc.mountain: 0.6831, Acc.mud: 0.0844, Acc.napkin: 0.1824, Acc.net: 0.6426, Acc.paper: 0.5066, Acc.pavement: 0.6865, Acc.pillow: 0.1600, Acc.plant-other: 0.2643, Acc.plastic: 0.2966, Acc.platform: 0.4817, Acc.playingfield: 0.8711, Acc.railing: 0.0556, Acc.railroad: 0.8494, Acc.river: 0.7010, Acc.road: 0.8560, Acc.rock: 0.6902, Acc.roof: 0.2921, Acc.rug: 0.5860, Acc.salad: 0.0000, Acc.sand: 0.7034, Acc.sea: 0.9173, Acc.shelf: 0.4960, Acc.sky-other: 0.8280, Acc.skyscraper: 0.5289, Acc.snow: 0.9638, Acc.solid-other: 0.0000, Acc.stairs: 0.6370, Acc.stone: 0.0453, Acc.straw: 0.3814, Acc.structural-other: 0.0021, Acc.table: 0.2479, Acc.tent: 0.1221, Acc.textile-other: 0.2339, Acc.towel: 0.4349, Acc.tree: 0.9051, Acc.vegetable: 0.5401, Acc.wall-brick: 0.6937, Acc.wall-concrete: 0.8138, Acc.wall-other: 0.3180, Acc.wall-panel: 0.0268, Acc.wall-stone: 0.3641, Acc.wall-tile: 0.8846, Acc.wall-wood: 0.5736, Acc.water-other: 0.3402, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6168, Acc.window-other: 0.7375, Acc.wood: 0.3869 2022-04-19 12:53:55,942 - mmseg - INFO - Iter [48050/80000] lr: 5.734e-07, eta: 8:41:30, time: 5.637, data_time: 4.709, memory: 73037, decode.loss_ce: 0.6713, decode.acc_seg: 63.8033, aux.loss_ce: 0.3004, aux.acc_seg: 62.7462, loss: 0.9717 2022-04-19 12:54:42,557 - mmseg - INFO - Iter [48100/80000] lr: 5.725e-07, eta: 8:40:39, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6801, decode.acc_seg: 63.9375, aux.loss_ce: 0.3050, aux.acc_seg: 62.4348, loss: 0.9851 2022-04-19 12:55:29,437 - mmseg - INFO - Iter [48150/80000] lr: 5.716e-07, eta: 8:39:49, time: 0.939, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6775, decode.acc_seg: 64.7947, aux.loss_ce: 0.3078, aux.acc_seg: 63.7193, loss: 0.9853 2022-04-19 12:56:16,288 - mmseg - INFO - Iter [48200/80000] lr: 5.707e-07, eta: 8:38:59, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6569, decode.acc_seg: 65.2012, aux.loss_ce: 0.2932, aux.acc_seg: 64.1862, loss: 0.9500 2022-04-19 12:57:02,625 - mmseg - INFO - Iter [48250/80000] lr: 5.698e-07, eta: 8:38:08, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6854, decode.acc_seg: 63.6101, aux.loss_ce: 0.3066, aux.acc_seg: 62.4590, loss: 0.9920 2022-04-19 12:57:49,447 - mmseg - INFO - Iter [48300/80000] lr: 5.690e-07, eta: 8:37:18, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6510, decode.acc_seg: 65.8701, aux.loss_ce: 0.2928, aux.acc_seg: 64.7295, loss: 0.9438 2022-04-19 12:58:35,947 - mmseg - INFO - Iter [48350/80000] lr: 5.681e-07, eta: 8:36:27, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6496, decode.acc_seg: 64.1670, aux.loss_ce: 0.2928, aux.acc_seg: 63.1795, loss: 0.9424 2022-04-19 12:59:22,266 - mmseg - INFO - Iter [48400/80000] lr: 5.672e-07, eta: 8:35:37, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6787, decode.acc_seg: 65.6926, aux.loss_ce: 0.3049, aux.acc_seg: 64.2163, loss: 0.9836 2022-04-19 13:00:09,029 - mmseg - INFO - Iter [48450/80000] lr: 5.663e-07, eta: 8:34:46, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6507, decode.acc_seg: 65.3186, aux.loss_ce: 0.2906, aux.acc_seg: 63.7579, loss: 0.9413 2022-04-19 13:00:55,620 - mmseg - INFO - Iter [48500/80000] lr: 5.654e-07, eta: 8:33:56, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6802, decode.acc_seg: 65.0465, aux.loss_ce: 0.3022, aux.acc_seg: 63.7596, loss: 0.9824 2022-04-19 13:01:42,100 - mmseg - INFO - Iter [48550/80000] lr: 5.645e-07, eta: 8:33:05, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6948, decode.acc_seg: 63.8233, aux.loss_ce: 0.3091, aux.acc_seg: 63.1491, loss: 1.0039 2022-04-19 13:02:28,792 - mmseg - INFO - Iter [48600/80000] lr: 5.636e-07, eta: 8:32:15, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6425, decode.acc_seg: 64.5172, aux.loss_ce: 0.2884, aux.acc_seg: 63.3577, loss: 0.9309 2022-04-19 13:03:15,452 - mmseg - INFO - Iter [48650/80000] lr: 5.627e-07, eta: 8:31:24, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6382, decode.acc_seg: 64.5487, aux.loss_ce: 0.2864, aux.acc_seg: 63.4224, loss: 0.9246 2022-04-19 13:04:02,042 - mmseg - INFO - Iter [48700/80000] lr: 5.618e-07, eta: 8:30:34, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6565, decode.acc_seg: 65.8248, aux.loss_ce: 0.2931, aux.acc_seg: 65.0238, loss: 0.9496 2022-04-19 13:04:48,832 - mmseg - INFO - Iter [48750/80000] lr: 5.609e-07, eta: 8:29:44, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6775, decode.acc_seg: 65.6263, aux.loss_ce: 0.3033, aux.acc_seg: 64.2005, loss: 0.9808 2022-04-19 13:05:35,436 - mmseg - INFO - Iter [48800/80000] lr: 5.600e-07, eta: 8:28:53, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6716, decode.acc_seg: 64.3543, aux.loss_ce: 0.3002, aux.acc_seg: 63.1981, loss: 0.9718 2022-04-19 13:06:22,149 - mmseg - INFO - Iter [48850/80000] lr: 5.591e-07, eta: 8:28:03, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6755, decode.acc_seg: 63.1521, aux.loss_ce: 0.2967, aux.acc_seg: 61.9995, loss: 0.9723 2022-04-19 13:07:08,621 - mmseg - INFO - Iter [48900/80000] lr: 5.582e-07, eta: 8:27:12, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6778, decode.acc_seg: 64.2177, aux.loss_ce: 0.3022, aux.acc_seg: 62.8073, loss: 0.9800 2022-04-19 13:07:55,217 - mmseg - INFO - Iter [48950/80000] lr: 5.573e-07, eta: 8:26:22, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6765, decode.acc_seg: 64.9940, aux.loss_ce: 0.3019, aux.acc_seg: 63.9050, loss: 0.9784 2022-04-19 13:08:42,286 - mmseg - INFO - Saving checkpoint at 49000 iterations 2022-04-19 13:08:54,091 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 13:08:54,091 - mmseg - INFO - Iter [49000/80000] lr: 5.564e-07, eta: 8:25:39, time: 1.174, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6365, decode.acc_seg: 64.9995, aux.loss_ce: 0.2865, aux.acc_seg: 63.8184, loss: 0.9230 2022-04-19 13:09:41,287 - mmseg - INFO - Iter [49050/80000] lr: 5.555e-07, eta: 8:24:49, time: 0.948, data_time: 0.009, memory: 73037, decode.loss_ce: 0.6577, decode.acc_seg: 64.7415, aux.loss_ce: 0.2946, aux.acc_seg: 63.9014, loss: 0.9523 2022-04-19 13:10:27,865 - mmseg - INFO - Iter [49100/80000] lr: 5.546e-07, eta: 8:23:59, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.7101, decode.acc_seg: 64.0603, aux.loss_ce: 0.3182, aux.acc_seg: 63.0736, loss: 1.0283 2022-04-19 13:11:14,542 - mmseg - INFO - Iter [49150/80000] lr: 5.537e-07, eta: 8:23:08, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6197, decode.acc_seg: 64.6509, aux.loss_ce: 0.2765, aux.acc_seg: 63.7035, loss: 0.8962 2022-04-19 13:12:01,262 - mmseg - INFO - Iter [49200/80000] lr: 5.528e-07, eta: 8:22:18, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6630, decode.acc_seg: 64.4389, aux.loss_ce: 0.2928, aux.acc_seg: 63.4761, loss: 0.9558 2022-04-19 13:12:47,735 - mmseg - INFO - Iter [49250/80000] lr: 5.519e-07, eta: 8:21:28, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6527, decode.acc_seg: 64.9678, aux.loss_ce: 0.2927, aux.acc_seg: 63.4825, loss: 0.9454 2022-04-19 13:13:34,816 - mmseg - INFO - Iter [49300/80000] lr: 5.510e-07, eta: 8:20:38, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6698, decode.acc_seg: 65.5250, aux.loss_ce: 0.3003, aux.acc_seg: 64.5585, loss: 0.9702 2022-04-19 13:14:21,267 - mmseg - INFO - Iter [49350/80000] lr: 5.501e-07, eta: 8:19:47, time: 0.931, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6938, decode.acc_seg: 63.4189, aux.loss_ce: 0.3071, aux.acc_seg: 62.2370, loss: 1.0009 2022-04-19 13:15:07,712 - mmseg - INFO - Iter [49400/80000] lr: 5.492e-07, eta: 8:18:57, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6716, decode.acc_seg: 65.0278, aux.loss_ce: 0.3011, aux.acc_seg: 63.6514, loss: 0.9727 2022-04-19 13:15:54,349 - mmseg - INFO - Iter [49450/80000] lr: 5.483e-07, eta: 8:18:06, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6639, decode.acc_seg: 64.5847, aux.loss_ce: 0.2991, aux.acc_seg: 63.1681, loss: 0.9630 2022-04-19 13:16:41,270 - mmseg - INFO - Iter [49500/80000] lr: 5.474e-07, eta: 8:17:16, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6669, decode.acc_seg: 63.8902, aux.loss_ce: 0.2943, aux.acc_seg: 63.3772, loss: 0.9612 2022-04-19 13:17:27,487 - mmseg - INFO - Iter [49550/80000] lr: 5.465e-07, eta: 8:16:26, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6708, decode.acc_seg: 65.0853, aux.loss_ce: 0.3006, aux.acc_seg: 63.8723, loss: 0.9714 2022-04-19 13:18:13,866 - mmseg - INFO - Iter [49600/80000] lr: 5.456e-07, eta: 8:15:35, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6323, decode.acc_seg: 64.6387, aux.loss_ce: 0.2847, aux.acc_seg: 63.7314, loss: 0.9171 2022-04-19 13:19:00,204 - mmseg - INFO - Iter [49650/80000] lr: 5.447e-07, eta: 8:14:45, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6617, decode.acc_seg: 63.8497, aux.loss_ce: 0.2980, aux.acc_seg: 62.6479, loss: 0.9597 2022-04-19 13:19:46,443 - mmseg - INFO - Iter [49700/80000] lr: 5.438e-07, eta: 8:13:54, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6706, decode.acc_seg: 65.1740, aux.loss_ce: 0.2983, aux.acc_seg: 63.9884, loss: 0.9689 2022-04-19 13:20:32,839 - mmseg - INFO - Iter [49750/80000] lr: 5.429e-07, eta: 8:13:04, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6321, decode.acc_seg: 64.7376, aux.loss_ce: 0.2803, aux.acc_seg: 63.9915, loss: 0.9124 2022-04-19 13:21:19,664 - mmseg - INFO - Iter [49800/80000] lr: 5.420e-07, eta: 8:12:14, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6724, decode.acc_seg: 64.1217, aux.loss_ce: 0.3006, aux.acc_seg: 63.0439, loss: 0.9730 2022-04-19 13:22:06,061 - mmseg - INFO - Iter [49850/80000] lr: 5.411e-07, eta: 8:11:23, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6806, decode.acc_seg: 62.5517, aux.loss_ce: 0.3069, aux.acc_seg: 61.4450, loss: 0.9876 2022-04-19 13:22:52,804 - mmseg - INFO - Iter [49900/80000] lr: 5.402e-07, eta: 8:10:33, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6194, decode.acc_seg: 64.7323, aux.loss_ce: 0.2805, aux.acc_seg: 63.7495, loss: 0.8999 2022-04-19 13:23:39,345 - mmseg - INFO - Iter [49950/80000] lr: 5.393e-07, eta: 8:09:43, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6302, decode.acc_seg: 65.4394, aux.loss_ce: 0.2841, aux.acc_seg: 64.4991, loss: 0.9143 2022-04-19 13:24:25,840 - mmseg - INFO - Saving checkpoint at 50000 iterations 2022-04-19 13:24:36,516 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 13:24:36,517 - mmseg - INFO - Iter [50000/80000] lr: 5.384e-07, eta: 8:08:59, time: 1.144, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6947, decode.acc_seg: 63.4702, aux.loss_ce: 0.3084, aux.acc_seg: 62.5916, loss: 1.0031 2022-04-19 13:25:23,347 - mmseg - INFO - Iter [50050/80000] lr: 5.375e-07, eta: 8:08:09, time: 0.937, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6567, decode.acc_seg: 64.8974, aux.loss_ce: 0.2957, aux.acc_seg: 63.4946, loss: 0.9523 2022-04-19 13:26:10,001 - mmseg - INFO - Iter [50100/80000] lr: 5.366e-07, eta: 8:07:18, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6694, decode.acc_seg: 65.0051, aux.loss_ce: 0.2963, aux.acc_seg: 64.0668, loss: 0.9657 2022-04-19 13:26:56,630 - mmseg - INFO - Iter [50150/80000] lr: 5.357e-07, eta: 8:06:28, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6491, decode.acc_seg: 66.4497, aux.loss_ce: 0.2901, aux.acc_seg: 65.1812, loss: 0.9393 2022-04-19 13:27:43,360 - mmseg - INFO - Iter [50200/80000] lr: 5.349e-07, eta: 8:05:38, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6924, decode.acc_seg: 63.8382, aux.loss_ce: 0.3088, aux.acc_seg: 62.7284, loss: 1.0012 2022-04-19 13:28:29,667 - mmseg - INFO - Iter [50250/80000] lr: 5.340e-07, eta: 8:04:48, time: 0.928, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6981, decode.acc_seg: 63.3899, aux.loss_ce: 0.3099, aux.acc_seg: 62.7142, loss: 1.0080 2022-04-19 13:29:16,091 - mmseg - INFO - Iter [50300/80000] lr: 5.331e-07, eta: 8:03:57, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6612, decode.acc_seg: 65.4232, aux.loss_ce: 0.2948, aux.acc_seg: 64.1974, loss: 0.9561 2022-04-19 13:30:02,216 - mmseg - INFO - Iter [50350/80000] lr: 5.322e-07, eta: 8:03:07, time: 0.922, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6295, decode.acc_seg: 64.9676, aux.loss_ce: 0.2837, aux.acc_seg: 63.7550, loss: 0.9132 2022-04-19 13:30:48,671 - mmseg - INFO - Iter [50400/80000] lr: 5.313e-07, eta: 8:02:16, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6629, decode.acc_seg: 63.3884, aux.loss_ce: 0.2980, aux.acc_seg: 61.9296, loss: 0.9609 2022-04-19 13:31:35,128 - mmseg - INFO - Iter [50450/80000] lr: 5.304e-07, eta: 8:01:26, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6429, decode.acc_seg: 64.7725, aux.loss_ce: 0.2872, aux.acc_seg: 63.5188, loss: 0.9301 2022-04-19 13:32:21,768 - mmseg - INFO - Iter [50500/80000] lr: 5.295e-07, eta: 8:00:36, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6781, decode.acc_seg: 64.4138, aux.loss_ce: 0.3035, aux.acc_seg: 63.2951, loss: 0.9815 2022-04-19 13:33:08,373 - mmseg - INFO - Iter [50550/80000] lr: 5.286e-07, eta: 7:59:46, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6853, decode.acc_seg: 64.2236, aux.loss_ce: 0.3056, aux.acc_seg: 63.4652, loss: 0.9910 2022-04-19 13:33:55,243 - mmseg - INFO - Iter [50600/80000] lr: 5.277e-07, eta: 7:58:56, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6959, decode.acc_seg: 65.3118, aux.loss_ce: 0.3123, aux.acc_seg: 64.0983, loss: 1.0082 2022-04-19 13:34:41,764 - mmseg - INFO - Iter [50650/80000] lr: 5.268e-07, eta: 7:58:05, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6922, decode.acc_seg: 62.8069, aux.loss_ce: 0.3139, aux.acc_seg: 61.4633, loss: 1.0061 2022-04-19 13:35:28,457 - mmseg - INFO - Iter [50700/80000] lr: 5.259e-07, eta: 7:57:15, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6554, decode.acc_seg: 64.0265, aux.loss_ce: 0.2975, aux.acc_seg: 62.7551, loss: 0.9529 2022-04-19 13:36:15,267 - mmseg - INFO - Iter [50750/80000] lr: 5.250e-07, eta: 7:56:25, time: 0.938, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6501, decode.acc_seg: 64.3652, aux.loss_ce: 0.2878, aux.acc_seg: 63.7033, loss: 0.9379 2022-04-19 13:37:01,815 - mmseg - INFO - Iter [50800/80000] lr: 5.241e-07, eta: 7:55:35, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6428, decode.acc_seg: 64.9871, aux.loss_ce: 0.2892, aux.acc_seg: 63.8663, loss: 0.9321 2022-04-19 13:37:48,577 - mmseg - INFO - Iter [50850/80000] lr: 5.232e-07, eta: 7:54:45, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6716, decode.acc_seg: 64.7640, aux.loss_ce: 0.3000, aux.acc_seg: 63.4667, loss: 0.9715 2022-04-19 13:38:34,959 - mmseg - INFO - Iter [50900/80000] lr: 5.223e-07, eta: 7:53:55, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6795, decode.acc_seg: 64.4130, aux.loss_ce: 0.3063, aux.acc_seg: 62.8347, loss: 0.9858 2022-04-19 13:39:21,427 - mmseg - INFO - Iter [50950/80000] lr: 5.214e-07, eta: 7:53:05, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6892, decode.acc_seg: 64.6380, aux.loss_ce: 0.3124, aux.acc_seg: 63.1520, loss: 1.0017 2022-04-19 13:40:08,107 - mmseg - INFO - Saving checkpoint at 51000 iterations 2022-04-19 13:40:20,187 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 13:40:20,188 - mmseg - INFO - Iter [51000/80000] lr: 5.205e-07, eta: 7:52:21, time: 1.175, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6553, decode.acc_seg: 63.4933, aux.loss_ce: 0.2908, aux.acc_seg: 62.4160, loss: 0.9462 2022-04-19 13:41:06,832 - mmseg - INFO - Iter [51050/80000] lr: 5.196e-07, eta: 7:51:31, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6846, decode.acc_seg: 64.1384, aux.loss_ce: 0.3124, aux.acc_seg: 62.8741, loss: 0.9970 2022-04-19 13:41:53,972 - mmseg - INFO - Iter [51100/80000] lr: 5.187e-07, eta: 7:50:41, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6488, decode.acc_seg: 64.5817, aux.loss_ce: 0.2920, aux.acc_seg: 63.3567, loss: 0.9408 2022-04-19 13:42:40,476 - mmseg - INFO - Iter [51150/80000] lr: 5.178e-07, eta: 7:49:51, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6293, decode.acc_seg: 64.8608, aux.loss_ce: 0.2832, aux.acc_seg: 63.7640, loss: 0.9125 2022-04-19 13:43:26,978 - mmseg - INFO - Iter [51200/80000] lr: 5.169e-07, eta: 7:49:01, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6249, decode.acc_seg: 64.9299, aux.loss_ce: 0.2820, aux.acc_seg: 63.8616, loss: 0.9069 2022-04-19 13:44:13,868 - mmseg - INFO - Iter [51250/80000] lr: 5.160e-07, eta: 7:48:11, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6690, decode.acc_seg: 64.9417, aux.loss_ce: 0.2996, aux.acc_seg: 64.0465, loss: 0.9686 2022-04-19 13:45:00,672 - mmseg - INFO - Iter [51300/80000] lr: 5.151e-07, eta: 7:47:21, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6824, decode.acc_seg: 62.9652, aux.loss_ce: 0.3073, aux.acc_seg: 61.8540, loss: 0.9897 2022-04-19 13:45:47,090 - mmseg - INFO - Iter [51350/80000] lr: 5.142e-07, eta: 7:46:31, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6117, decode.acc_seg: 65.6277, aux.loss_ce: 0.2733, aux.acc_seg: 64.6546, loss: 0.8850 2022-04-19 13:46:33,433 - mmseg - INFO - Iter [51400/80000] lr: 5.133e-07, eta: 7:45:41, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6294, decode.acc_seg: 66.3257, aux.loss_ce: 0.2818, aux.acc_seg: 64.9549, loss: 0.9113 2022-04-19 13:47:19,944 - mmseg - INFO - Iter [51450/80000] lr: 5.124e-07, eta: 7:44:50, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6594, decode.acc_seg: 65.2970, aux.loss_ce: 0.2927, aux.acc_seg: 64.0801, loss: 0.9520 2022-04-19 13:48:06,278 - mmseg - INFO - Iter [51500/80000] lr: 5.115e-07, eta: 7:44:00, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6845, decode.acc_seg: 64.8153, aux.loss_ce: 0.3066, aux.acc_seg: 63.9859, loss: 0.9911 2022-04-19 13:48:52,815 - mmseg - INFO - Iter [51550/80000] lr: 5.106e-07, eta: 7:43:10, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6910, decode.acc_seg: 64.4807, aux.loss_ce: 0.3056, aux.acc_seg: 63.6701, loss: 0.9966 2022-04-19 13:49:39,462 - mmseg - INFO - Iter [51600/80000] lr: 5.097e-07, eta: 7:42:20, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6692, decode.acc_seg: 63.6792, aux.loss_ce: 0.2991, aux.acc_seg: 62.3227, loss: 0.9682 2022-04-19 13:50:25,979 - mmseg - INFO - Iter [51650/80000] lr: 5.088e-07, eta: 7:41:30, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6613, decode.acc_seg: 63.9841, aux.loss_ce: 0.2982, aux.acc_seg: 62.9444, loss: 0.9595 2022-04-19 13:51:12,286 - mmseg - INFO - Iter [51700/80000] lr: 5.079e-07, eta: 7:40:40, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6820, decode.acc_seg: 63.8641, aux.loss_ce: 0.3053, aux.acc_seg: 62.5392, loss: 0.9873 2022-04-19 13:51:58,967 - mmseg - INFO - Iter [51750/80000] lr: 5.070e-07, eta: 7:39:50, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6641, decode.acc_seg: 64.9031, aux.loss_ce: 0.3014, aux.acc_seg: 63.5501, loss: 0.9655 2022-04-19 13:52:48,237 - mmseg - INFO - Iter [51800/80000] lr: 5.061e-07, eta: 7:39:01, time: 0.987, data_time: 0.058, memory: 73037, decode.loss_ce: 0.6596, decode.acc_seg: 65.7861, aux.loss_ce: 0.2978, aux.acc_seg: 64.5422, loss: 0.9574 2022-04-19 13:53:34,466 - mmseg - INFO - Iter [51850/80000] lr: 5.052e-07, eta: 7:38:11, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6648, decode.acc_seg: 64.2361, aux.loss_ce: 0.3024, aux.acc_seg: 62.7249, loss: 0.9672 2022-04-19 13:54:20,977 - mmseg - INFO - Iter [51900/80000] lr: 5.043e-07, eta: 7:37:21, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6597, decode.acc_seg: 65.3170, aux.loss_ce: 0.2981, aux.acc_seg: 64.1554, loss: 0.9577 2022-04-19 13:55:07,446 - mmseg - INFO - Iter [51950/80000] lr: 5.034e-07, eta: 7:36:31, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6259, decode.acc_seg: 66.0565, aux.loss_ce: 0.2853, aux.acc_seg: 64.7162, loss: 0.9112 2022-04-19 13:55:54,021 - mmseg - INFO - Saving checkpoint at 52000 iterations 2022-04-19 13:56:05,072 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 13:56:05,072 - mmseg - INFO - Iter [52000/80000] lr: 5.025e-07, eta: 7:35:47, time: 1.154, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6351, decode.acc_seg: 63.1904, aux.loss_ce: 0.2927, aux.acc_seg: 61.7617, loss: 0.9277 2022-04-19 13:56:51,858 - mmseg - INFO - Iter [52050/80000] lr: 5.016e-07, eta: 7:34:57, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6544, decode.acc_seg: 65.1017, aux.loss_ce: 0.2969, aux.acc_seg: 63.8975, loss: 0.9514 2022-04-19 13:57:38,273 - mmseg - INFO - Iter [52100/80000] lr: 5.008e-07, eta: 7:34:06, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6495, decode.acc_seg: 64.1325, aux.loss_ce: 0.2925, aux.acc_seg: 62.8613, loss: 0.9420 2022-04-19 13:58:24,629 - mmseg - INFO - Iter [52150/80000] lr: 4.999e-07, eta: 7:33:16, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6418, decode.acc_seg: 65.8371, aux.loss_ce: 0.2921, aux.acc_seg: 64.0460, loss: 0.9339 2022-04-19 13:59:11,164 - mmseg - INFO - Iter [52200/80000] lr: 4.990e-07, eta: 7:32:26, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6415, decode.acc_seg: 66.2190, aux.loss_ce: 0.2913, aux.acc_seg: 64.4232, loss: 0.9328 2022-04-19 13:59:57,754 - mmseg - INFO - Iter [52250/80000] lr: 4.981e-07, eta: 7:31:36, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6758, decode.acc_seg: 64.1638, aux.loss_ce: 0.3024, aux.acc_seg: 62.9211, loss: 0.9783 2022-04-19 14:00:44,215 - mmseg - INFO - Iter [52300/80000] lr: 4.972e-07, eta: 7:30:46, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6434, decode.acc_seg: 65.5030, aux.loss_ce: 0.2942, aux.acc_seg: 64.0155, loss: 0.9376 2022-04-19 14:01:30,633 - mmseg - INFO - Iter [52350/80000] lr: 4.963e-07, eta: 7:29:56, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6611, decode.acc_seg: 63.9467, aux.loss_ce: 0.2983, aux.acc_seg: 62.6320, loss: 0.9593 2022-04-19 14:02:17,047 - mmseg - INFO - Iter [52400/80000] lr: 4.954e-07, eta: 7:29:06, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6643, decode.acc_seg: 63.5550, aux.loss_ce: 0.2996, aux.acc_seg: 62.4717, loss: 0.9639 2022-04-19 14:03:03,533 - mmseg - INFO - Iter [52450/80000] lr: 4.945e-07, eta: 7:28:16, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6539, decode.acc_seg: 65.6082, aux.loss_ce: 0.2956, aux.acc_seg: 64.4402, loss: 0.9495 2022-04-19 14:03:50,474 - mmseg - INFO - Iter [52500/80000] lr: 4.936e-07, eta: 7:27:26, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6475, decode.acc_seg: 64.9617, aux.loss_ce: 0.2942, aux.acc_seg: 63.8637, loss: 0.9416 2022-04-19 14:04:37,286 - mmseg - INFO - Iter [52550/80000] lr: 4.927e-07, eta: 7:26:36, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6360, decode.acc_seg: 65.8474, aux.loss_ce: 0.2881, aux.acc_seg: 64.5689, loss: 0.9241 2022-04-19 14:05:23,719 - mmseg - INFO - Iter [52600/80000] lr: 4.918e-07, eta: 7:25:46, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6292, decode.acc_seg: 66.6467, aux.loss_ce: 0.2852, aux.acc_seg: 65.2121, loss: 0.9144 2022-04-19 14:06:10,270 - mmseg - INFO - Iter [52650/80000] lr: 4.909e-07, eta: 7:24:56, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6396, decode.acc_seg: 65.2320, aux.loss_ce: 0.2911, aux.acc_seg: 64.1778, loss: 0.9307 2022-04-19 14:06:56,843 - mmseg - INFO - Iter [52700/80000] lr: 4.900e-07, eta: 7:24:06, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6545, decode.acc_seg: 63.6160, aux.loss_ce: 0.2962, aux.acc_seg: 62.4529, loss: 0.9508 2022-04-19 14:07:43,338 - mmseg - INFO - Iter [52750/80000] lr: 4.891e-07, eta: 7:23:16, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6628, decode.acc_seg: 63.7494, aux.loss_ce: 0.2998, aux.acc_seg: 62.1138, loss: 0.9626 2022-04-19 14:08:29,865 - mmseg - INFO - Iter [52800/80000] lr: 4.882e-07, eta: 7:22:26, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6399, decode.acc_seg: 64.2095, aux.loss_ce: 0.2908, aux.acc_seg: 63.0058, loss: 0.9307 2022-04-19 14:09:16,120 - mmseg - INFO - Iter [52850/80000] lr: 4.873e-07, eta: 7:21:36, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6605, decode.acc_seg: 63.8863, aux.loss_ce: 0.2971, aux.acc_seg: 62.6243, loss: 0.9576 2022-04-19 14:10:02,631 - mmseg - INFO - Iter [52900/80000] lr: 4.864e-07, eta: 7:20:46, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6300, decode.acc_seg: 66.0022, aux.loss_ce: 0.2819, aux.acc_seg: 65.2357, loss: 0.9119 2022-04-19 14:10:49,340 - mmseg - INFO - Iter [52950/80000] lr: 4.855e-07, eta: 7:19:56, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6336, decode.acc_seg: 65.0639, aux.loss_ce: 0.2856, aux.acc_seg: 63.8087, loss: 0.9193 2022-04-19 14:11:36,259 - mmseg - INFO - Saving checkpoint at 53000 iterations 2022-04-19 14:11:46,351 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 14:11:46,352 - mmseg - INFO - Iter [53000/80000] lr: 4.846e-07, eta: 7:19:12, time: 1.140, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6628, decode.acc_seg: 64.4290, aux.loss_ce: 0.2962, aux.acc_seg: 63.2582, loss: 0.9590 2022-04-19 14:12:32,897 - mmseg - INFO - Iter [53050/80000] lr: 4.837e-07, eta: 7:18:22, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6375, decode.acc_seg: 65.0598, aux.loss_ce: 0.2898, aux.acc_seg: 63.6897, loss: 0.9273 2022-04-19 14:13:19,461 - mmseg - INFO - Iter [53100/80000] lr: 4.828e-07, eta: 7:17:32, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6552, decode.acc_seg: 64.8496, aux.loss_ce: 0.2960, aux.acc_seg: 63.4714, loss: 0.9512 2022-04-19 14:14:05,849 - mmseg - INFO - Iter [53150/80000] lr: 4.819e-07, eta: 7:16:42, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6220, decode.acc_seg: 66.2700, aux.loss_ce: 0.2787, aux.acc_seg: 65.2907, loss: 0.9008 2022-04-19 14:14:52,538 - mmseg - INFO - Iter [53200/80000] lr: 4.810e-07, eta: 7:15:52, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6138, decode.acc_seg: 64.6613, aux.loss_ce: 0.2826, aux.acc_seg: 63.3983, loss: 0.8965 2022-04-19 14:15:38,986 - mmseg - INFO - Iter [53250/80000] lr: 4.801e-07, eta: 7:15:02, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6708, decode.acc_seg: 65.5672, aux.loss_ce: 0.3067, aux.acc_seg: 64.2520, loss: 0.9776 2022-04-19 14:16:25,390 - mmseg - INFO - Iter [53300/80000] lr: 4.792e-07, eta: 7:14:12, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6195, decode.acc_seg: 65.9285, aux.loss_ce: 0.2811, aux.acc_seg: 64.6745, loss: 0.9006 2022-04-19 14:17:11,804 - mmseg - INFO - Iter [53350/80000] lr: 4.783e-07, eta: 7:13:22, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6650, decode.acc_seg: 65.8474, aux.loss_ce: 0.3035, aux.acc_seg: 64.2331, loss: 0.9685 2022-04-19 14:17:58,132 - mmseg - INFO - Iter [53400/80000] lr: 4.774e-07, eta: 7:12:32, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6484, decode.acc_seg: 65.6742, aux.loss_ce: 0.2906, aux.acc_seg: 64.4185, loss: 0.9390 2022-04-19 14:18:45,178 - mmseg - INFO - Iter [53450/80000] lr: 4.765e-07, eta: 7:11:42, time: 0.941, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6614, decode.acc_seg: 63.9613, aux.loss_ce: 0.2961, aux.acc_seg: 62.6628, loss: 0.9575 2022-04-19 14:19:31,841 - mmseg - INFO - Iter [53500/80000] lr: 4.756e-07, eta: 7:10:53, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6575, decode.acc_seg: 64.7987, aux.loss_ce: 0.2925, aux.acc_seg: 63.3524, loss: 0.9500 2022-04-19 14:20:18,499 - mmseg - INFO - Iter [53550/80000] lr: 4.747e-07, eta: 7:10:03, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6852, decode.acc_seg: 64.1834, aux.loss_ce: 0.3067, aux.acc_seg: 63.0554, loss: 0.9919 2022-04-19 14:21:05,400 - mmseg - INFO - Iter [53600/80000] lr: 4.738e-07, eta: 7:09:13, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6174, decode.acc_seg: 65.5594, aux.loss_ce: 0.2793, aux.acc_seg: 64.7138, loss: 0.8966 2022-04-19 14:21:52,109 - mmseg - INFO - Iter [53650/80000] lr: 4.729e-07, eta: 7:08:23, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6305, decode.acc_seg: 64.5738, aux.loss_ce: 0.2886, aux.acc_seg: 63.1085, loss: 0.9192 2022-04-19 14:22:38,549 - mmseg - INFO - Iter [53700/80000] lr: 4.720e-07, eta: 7:07:33, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6408, decode.acc_seg: 64.0960, aux.loss_ce: 0.2881, aux.acc_seg: 62.8358, loss: 0.9288 2022-04-19 14:23:24,877 - mmseg - INFO - Iter [53750/80000] lr: 4.711e-07, eta: 7:06:43, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6746, decode.acc_seg: 63.7951, aux.loss_ce: 0.3057, aux.acc_seg: 62.8079, loss: 0.9803 2022-04-19 14:24:11,235 - mmseg - INFO - Iter [53800/80000] lr: 4.702e-07, eta: 7:05:54, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6576, decode.acc_seg: 64.0046, aux.loss_ce: 0.3007, aux.acc_seg: 62.6567, loss: 0.9583 2022-04-19 14:24:57,533 - mmseg - INFO - Iter [53850/80000] lr: 4.693e-07, eta: 7:05:04, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6471, decode.acc_seg: 63.8872, aux.loss_ce: 0.2887, aux.acc_seg: 63.2196, loss: 0.9358 2022-04-19 14:25:44,033 - mmseg - INFO - Iter [53900/80000] lr: 4.684e-07, eta: 7:04:14, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6152, decode.acc_seg: 64.9722, aux.loss_ce: 0.2770, aux.acc_seg: 63.8678, loss: 0.8922 2022-04-19 14:26:30,765 - mmseg - INFO - Iter [53950/80000] lr: 4.675e-07, eta: 7:03:24, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6268, decode.acc_seg: 64.3486, aux.loss_ce: 0.2828, aux.acc_seg: 62.9339, loss: 0.9095 2022-04-19 14:27:17,451 - mmseg - INFO - Saving checkpoint at 54000 iterations 2022-04-19 14:27:27,902 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 14:27:27,902 - mmseg - INFO - Iter [54000/80000] lr: 4.667e-07, eta: 7:02:39, time: 1.142, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6589, decode.acc_seg: 63.9349, aux.loss_ce: 0.2979, aux.acc_seg: 62.4250, loss: 0.9569 2022-04-19 14:28:14,954 - mmseg - INFO - Iter [54050/80000] lr: 4.658e-07, eta: 7:01:50, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6416, decode.acc_seg: 66.5152, aux.loss_ce: 0.2943, aux.acc_seg: 64.8878, loss: 0.9359 2022-04-19 14:29:01,637 - mmseg - INFO - Iter [54100/80000] lr: 4.649e-07, eta: 7:01:00, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6613, decode.acc_seg: 64.8144, aux.loss_ce: 0.2958, aux.acc_seg: 63.7303, loss: 0.9572 2022-04-19 14:29:48,330 - mmseg - INFO - Iter [54150/80000] lr: 4.640e-07, eta: 7:00:10, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6408, decode.acc_seg: 65.9791, aux.loss_ce: 0.2891, aux.acc_seg: 64.7706, loss: 0.9299 2022-04-19 14:30:35,195 - mmseg - INFO - Iter [54200/80000] lr: 4.631e-07, eta: 6:59:20, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6037, decode.acc_seg: 65.9000, aux.loss_ce: 0.2685, aux.acc_seg: 65.1724, loss: 0.8722 2022-04-19 14:31:21,834 - mmseg - INFO - Iter [54250/80000] lr: 4.622e-07, eta: 6:58:31, time: 0.935, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6491, decode.acc_seg: 65.9526, aux.loss_ce: 0.2918, aux.acc_seg: 64.4709, loss: 0.9409 2022-04-19 14:32:08,774 - mmseg - INFO - Iter [54300/80000] lr: 4.613e-07, eta: 6:57:41, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6595, decode.acc_seg: 63.9276, aux.loss_ce: 0.2995, aux.acc_seg: 62.5794, loss: 0.9590 2022-04-19 14:32:55,166 - mmseg - INFO - Iter [54350/80000] lr: 4.604e-07, eta: 6:56:51, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6573, decode.acc_seg: 65.6586, aux.loss_ce: 0.2997, aux.acc_seg: 64.4501, loss: 0.9570 2022-04-19 14:33:41,706 - mmseg - INFO - Iter [54400/80000] lr: 4.595e-07, eta: 6:56:01, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6472, decode.acc_seg: 64.3218, aux.loss_ce: 0.2940, aux.acc_seg: 63.1059, loss: 0.9411 2022-04-19 14:34:28,142 - mmseg - INFO - Iter [54450/80000] lr: 4.586e-07, eta: 6:55:12, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6208, decode.acc_seg: 64.9339, aux.loss_ce: 0.2838, aux.acc_seg: 63.0971, loss: 0.9046 2022-04-19 14:35:14,624 - mmseg - INFO - Iter [54500/80000] lr: 4.577e-07, eta: 6:54:22, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6286, decode.acc_seg: 66.4762, aux.loss_ce: 0.2861, aux.acc_seg: 64.9683, loss: 0.9147 2022-04-19 14:36:00,995 - mmseg - INFO - Iter [54550/80000] lr: 4.568e-07, eta: 6:53:32, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6677, decode.acc_seg: 63.8912, aux.loss_ce: 0.2957, aux.acc_seg: 62.6911, loss: 0.9634 2022-04-19 14:36:47,511 - mmseg - INFO - Iter [54600/80000] lr: 4.559e-07, eta: 6:52:42, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6256, decode.acc_seg: 64.8203, aux.loss_ce: 0.2788, aux.acc_seg: 63.7674, loss: 0.9044 2022-04-19 14:37:33,933 - mmseg - INFO - Iter [54650/80000] lr: 4.550e-07, eta: 6:51:52, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6432, decode.acc_seg: 65.3677, aux.loss_ce: 0.2881, aux.acc_seg: 64.5102, loss: 0.9313 2022-04-19 14:38:20,462 - mmseg - INFO - Iter [54700/80000] lr: 4.541e-07, eta: 6:51:02, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6436, decode.acc_seg: 64.6020, aux.loss_ce: 0.2946, aux.acc_seg: 63.2328, loss: 0.9382 2022-04-19 14:39:06,904 - mmseg - INFO - Iter [54750/80000] lr: 4.532e-07, eta: 6:50:13, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6333, decode.acc_seg: 65.4005, aux.loss_ce: 0.2869, aux.acc_seg: 64.2344, loss: 0.9202 2022-04-19 14:39:53,246 - mmseg - INFO - Iter [54800/80000] lr: 4.523e-07, eta: 6:49:23, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6307, decode.acc_seg: 66.5088, aux.loss_ce: 0.2885, aux.acc_seg: 65.0032, loss: 0.9191 2022-04-19 14:40:39,659 - mmseg - INFO - Iter [54850/80000] lr: 4.514e-07, eta: 6:48:33, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6546, decode.acc_seg: 64.5651, aux.loss_ce: 0.2932, aux.acc_seg: 63.3112, loss: 0.9478 2022-04-19 14:41:26,139 - mmseg - INFO - Iter [54900/80000] lr: 4.505e-07, eta: 6:47:43, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6657, decode.acc_seg: 63.6280, aux.loss_ce: 0.3022, aux.acc_seg: 62.3224, loss: 0.9679 2022-04-19 14:42:12,503 - mmseg - INFO - Iter [54950/80000] lr: 4.496e-07, eta: 6:46:53, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6479, decode.acc_seg: 64.4241, aux.loss_ce: 0.2903, aux.acc_seg: 63.4885, loss: 0.9382 2022-04-19 14:42:58,831 - mmseg - INFO - Saving checkpoint at 55000 iterations 2022-04-19 14:43:09,110 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 14:43:09,111 - mmseg - INFO - Iter [55000/80000] lr: 4.487e-07, eta: 6:46:08, time: 1.132, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6559, decode.acc_seg: 66.0101, aux.loss_ce: 0.2957, aux.acc_seg: 64.8179, loss: 0.9516 2022-04-19 14:43:55,636 - mmseg - INFO - Iter [55050/80000] lr: 4.478e-07, eta: 6:45:19, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6363, decode.acc_seg: 64.7126, aux.loss_ce: 0.2875, aux.acc_seg: 63.3891, loss: 0.9238 2022-04-19 14:44:42,237 - mmseg - INFO - Iter [55100/80000] lr: 4.469e-07, eta: 6:44:29, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6523, decode.acc_seg: 64.8564, aux.loss_ce: 0.3004, aux.acc_seg: 63.1144, loss: 0.9527 2022-04-19 14:45:29,357 - mmseg - INFO - Iter [55150/80000] lr: 4.460e-07, eta: 6:43:39, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6747, decode.acc_seg: 64.8057, aux.loss_ce: 0.3049, aux.acc_seg: 64.0035, loss: 0.9796 2022-04-19 14:46:15,915 - mmseg - INFO - Iter [55200/80000] lr: 4.451e-07, eta: 6:42:50, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6339, decode.acc_seg: 65.6127, aux.loss_ce: 0.2876, aux.acc_seg: 64.2126, loss: 0.9215 2022-04-19 14:47:02,587 - mmseg - INFO - Iter [55250/80000] lr: 4.442e-07, eta: 6:42:00, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6169, decode.acc_seg: 65.6540, aux.loss_ce: 0.2785, aux.acc_seg: 64.5209, loss: 0.8954 2022-04-19 14:47:49,115 - mmseg - INFO - Iter [55300/80000] lr: 4.433e-07, eta: 6:41:10, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6387, decode.acc_seg: 63.9402, aux.loss_ce: 0.2823, aux.acc_seg: 63.0095, loss: 0.9210 2022-04-19 14:48:35,459 - mmseg - INFO - Iter [55350/80000] lr: 4.424e-07, eta: 6:40:21, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6815, decode.acc_seg: 64.1606, aux.loss_ce: 0.3036, aux.acc_seg: 63.3709, loss: 0.9851 2022-04-19 14:49:22,013 - mmseg - INFO - Iter [55400/80000] lr: 4.415e-07, eta: 6:39:31, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6498, decode.acc_seg: 64.9442, aux.loss_ce: 0.2911, aux.acc_seg: 63.7298, loss: 0.9409 2022-04-19 14:50:08,676 - mmseg - INFO - Iter [55450/80000] lr: 4.406e-07, eta: 6:38:41, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6187, decode.acc_seg: 66.4250, aux.loss_ce: 0.2822, aux.acc_seg: 65.4893, loss: 0.9009 2022-04-19 14:50:55,403 - mmseg - INFO - Iter [55500/80000] lr: 4.397e-07, eta: 6:37:52, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6300, decode.acc_seg: 65.3316, aux.loss_ce: 0.2838, aux.acc_seg: 64.2563, loss: 0.9138 2022-04-19 14:51:41,757 - mmseg - INFO - Iter [55550/80000] lr: 4.388e-07, eta: 6:37:02, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6613, decode.acc_seg: 63.8136, aux.loss_ce: 0.2981, aux.acc_seg: 62.8317, loss: 0.9594 2022-04-19 14:52:28,708 - mmseg - INFO - Iter [55600/80000] lr: 4.379e-07, eta: 6:36:12, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6382, decode.acc_seg: 65.6115, aux.loss_ce: 0.2895, aux.acc_seg: 64.5144, loss: 0.9277 2022-04-19 14:53:15,221 - mmseg - INFO - Iter [55650/80000] lr: 4.370e-07, eta: 6:35:23, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6766, decode.acc_seg: 64.6205, aux.loss_ce: 0.3033, aux.acc_seg: 63.5779, loss: 0.9799 2022-04-19 14:54:02,477 - mmseg - INFO - Iter [55700/80000] lr: 4.361e-07, eta: 6:34:33, time: 0.945, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6498, decode.acc_seg: 64.4110, aux.loss_ce: 0.2958, aux.acc_seg: 63.0406, loss: 0.9455 2022-04-19 14:54:48,737 - mmseg - INFO - Iter [55750/80000] lr: 4.352e-07, eta: 6:33:44, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6557, decode.acc_seg: 63.9655, aux.loss_ce: 0.2930, aux.acc_seg: 63.0255, loss: 0.9487 2022-04-19 14:55:35,270 - mmseg - INFO - Iter [55800/80000] lr: 4.343e-07, eta: 6:32:54, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6376, decode.acc_seg: 65.9125, aux.loss_ce: 0.2880, aux.acc_seg: 64.1970, loss: 0.9256 2022-04-19 14:56:21,463 - mmseg - INFO - Iter [55850/80000] lr: 4.334e-07, eta: 6:32:04, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6748, decode.acc_seg: 63.0936, aux.loss_ce: 0.3057, aux.acc_seg: 61.7776, loss: 0.9805 2022-04-19 14:57:07,963 - mmseg - INFO - Iter [55900/80000] lr: 4.326e-07, eta: 6:31:14, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6729, decode.acc_seg: 63.8959, aux.loss_ce: 0.3016, aux.acc_seg: 62.9764, loss: 0.9746 2022-04-19 14:57:54,602 - mmseg - INFO - Iter [55950/80000] lr: 4.317e-07, eta: 6:30:25, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6544, decode.acc_seg: 65.4813, aux.loss_ce: 0.2959, aux.acc_seg: 64.2056, loss: 0.9504 2022-04-19 14:58:41,272 - mmseg - INFO - Saving checkpoint at 56000 iterations 2022-04-19 14:58:52,403 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 14:58:52,403 - mmseg - INFO - Iter [56000/80000] lr: 4.308e-07, eta: 6:29:40, time: 1.155, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6404, decode.acc_seg: 66.2339, aux.loss_ce: 0.2914, aux.acc_seg: 65.0230, loss: 0.9318 2022-04-19 15:02:47,504 - mmseg - INFO - per class results: 2022-04-19 15:02:47,518 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.42 | 95.25 | | bicycle | 71.41 | 87.71 | | car | 67.52 | 86.65 | | motorcycle | 85.04 | 92.65 | | airplane | 82.08 | 94.71 | | bus | 85.23 | 92.29 | | train | 81.95 | 95.82 | | truck | 68.79 | 85.27 | | boat | 66.15 | 87.45 | | traffic light | 64.87 | 90.04 | | fire hydrant | 86.39 | 97.61 | | stop sign | 90.6 | 98.01 | | parking meter | 79.84 | 88.12 | | bench | 54.88 | 78.07 | | bird | 81.84 | 92.33 | | cat | 81.64 | 89.64 | | dog | 78.47 | 87.71 | | horse | 86.73 | 95.46 | | sheep | 87.47 | 96.62 | | cow | 88.1 | 93.57 | | elephant | 92.09 | 97.43 | | bear | 92.69 | 96.82 | | zebra | 91.83 | 97.27 | | giraffe | 85.64 | 96.51 | | backpack | 40.43 | 65.5 | | umbrella | 87.09 | 94.86 | | handbag | 39.63 | 56.46 | | tie | 4.54 | 5.94 | | suitcase | 81.2 | 94.35 | | frisbee | 81.89 | 91.29 | | skis | 47.65 | 61.64 | | snowboard | 65.7 | 78.46 | | sports ball | 61.78 | 73.29 | | kite | 72.66 | 90.74 | | baseball bat | 56.55 | 78.45 | | baseball glove | 72.16 | 88.95 | | skateboard | 80.9 | 90.7 | | surfboard | 82.43 | 90.8 | | tennis racket | 85.02 | 93.82 | | bottle | 52.43 | 68.25 | | wine glass | 59.85 | 83.07 | | cup | 56.74 | 82.66 | | fork | 48.22 | 67.32 | | knife | 40.44 | 62.26 | | spoon | 43.7 | 60.29 | | bowl | 50.2 | 72.54 | | banana | 69.96 | 93.6 | | apple | 55.54 | 79.25 | | sandwich | 51.25 | 73.84 | | orange | 71.4 | 82.6 | | broccoli | 50.92 | 65.85 | | carrot | 58.89 | 71.87 | | hot dog | 58.16 | 71.92 | | pizza | 76.36 | 93.81 | | donut | 76.88 | 92.31 | | cake | 65.41 | 86.25 | | chair | 51.29 | 76.21 | | couch | 58.1 | 79.25 | | potted plant | 34.22 | 54.61 | | bed | 65.48 | 82.32 | | dining table | 47.45 | 71.5 | | toilet | 80.41 | 96.62 | | tv | 73.11 | 89.71 | | laptop | 77.62 | 94.92 | | mouse | 76.43 | 88.92 | | remote | 59.42 | 76.63 | | keyboard | 62.01 | 69.95 | | cell phone | 74.67 | 89.88 | | microwave | 68.09 | 83.56 | | oven | 60.08 | 82.72 | | toaster | 78.57 | 86.29 | | sink | 60.43 | 87.07 | | refrigerator | 76.77 | 93.68 | | book | 53.12 | 73.68 | | clock | 68.82 | 84.17 | | vase | 62.14 | 88.83 | | scissors | 69.36 | 96.64 | | teddy bear | 79.48 | 93.83 | | hair drier | 53.1 | 56.23 | | toothbrush | 49.69 | 74.72 | | banner | 32.85 | 73.18 | | blanket | 8.73 | 10.87 | | branch | 10.76 | 13.35 | | bridge | 38.54 | 54.12 | | building-other | 55.37 | 72.38 | | bush | 32.9 | 41.7 | | cabinet | 58.84 | 76.67 | | cage | 29.1 | 43.67 | | cardboard | 51.24 | 63.85 | | carpet | 54.38 | 78.09 | | ceiling-other | 65.33 | 87.3 | | ceiling-tile | 4.88 | 4.88 | | cloth | 3.4 | 4.57 | | clothes | 16.58 | 19.52 | | clouds | 50.34 | 65.01 | | counter | 29.56 | 55.07 | | cupboard | 0.0 | 0.0 | | curtain | 68.47 | 82.25 | | desk-stuff | 47.79 | 71.75 | | dirt | 42.56 | 60.46 | | door-stuff | 46.45 | 76.31 | | fence | 33.58 | 53.55 | | floor-marble | 8.05 | 10.17 | | floor-other | 22.33 | 29.51 | | floor-stone | 3.87 | 5.05 | | floor-tile | 61.36 | 76.33 | | floor-wood | 64.29 | 80.76 | | flower | 39.18 | 62.0 | | fog | 15.45 | 16.72 | | food-other | 28.91 | 34.83 | | fruit | 45.61 | 63.73 | | furniture-other | 16.34 | 19.89 | | grass | 70.99 | 85.2 | | gravel | 25.5 | 34.23 | | ground-other | 7.22 | 8.8 | | hill | 15.5 | 19.88 | | house | 27.73 | 34.69 | | leaves | 29.0 | 34.82 | | light | 41.02 | 55.95 | | mat | 0.0 | 0.0 | | metal | 33.36 | 44.33 | | mirror-stuff | 57.19 | 77.08 | | moss | 0.0 | 0.0 | | mountain | 54.99 | 71.82 | | mud | 6.48 | 10.9 | | napkin | 8.92 | 11.25 | | net | 48.93 | 68.17 | | paper | 33.69 | 47.88 | | pavement | 51.66 | 66.56 | | pillow | 11.73 | 14.96 | | plant-other | 16.23 | 23.21 | | plastic | 22.54 | 27.66 | | platform | 30.09 | 58.4 | | playingfield | 69.84 | 92.12 | | railing | 8.3 | 14.1 | | railroad | 60.25 | 85.83 | | river | 47.51 | 70.85 | | road | 67.02 | 86.54 | | rock | 46.17 | 72.85 | | roof | 20.88 | 25.45 | | rug | 38.18 | 58.44 | | salad | 0.02 | 0.02 | | sand | 66.42 | 71.49 | | sea | 84.83 | 92.6 | | shelf | 36.27 | 52.27 | | sky-other | 73.05 | 88.75 | | skyscraper | 40.36 | 53.95 | | snow | 90.86 | 94.97 | | solid-other | 0.0 | 0.0 | | stairs | 27.75 | 53.52 | | stone | 3.2 | 3.53 | | straw | 30.07 | 38.65 | | structural-other | 0.29 | 0.29 | | table | 23.13 | 30.79 | | tent | 9.18 | 12.3 | | textile-other | 15.47 | 22.03 | | towel | 33.37 | 43.96 | | tree | 73.29 | 88.62 | | vegetable | 42.54 | 57.22 | | wall-brick | 49.16 | 68.43 | | wall-concrete | 61.52 | 78.76 | | wall-other | 21.66 | 30.41 | | wall-panel | 4.24 | 4.72 | | wall-stone | 29.37 | 37.35 | | wall-tile | 68.48 | 88.83 | | wall-wood | 42.26 | 57.04 | | water-other | 26.52 | 37.01 | | waterdrops | 0.0 | 0.0 | | window-blind | 52.06 | 66.36 | | window-other | 48.44 | 74.13 | | wood | 28.6 | 44.05 | +------------------+-------+-------+ 2022-04-19 15:02:47,518 - mmseg - INFO - Summary: 2022-04-19 15:02:47,518 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 73.38 | 49.96 | 63.45 | +-------+-------+-------+ 2022-04-19 15:02:47,533 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 15:02:47,534 - mmseg - INFO - Iter(val) [625] aAcc: 0.7338, mIoU: 0.4996, mAcc: 0.6345, IoU.person: 0.8642, IoU.bicycle: 0.7141, IoU.car: 0.6752, IoU.motorcycle: 0.8504, IoU.airplane: 0.8208, IoU.bus: 0.8523, IoU.train: 0.8195, IoU.truck: 0.6879, IoU.boat: 0.6615, IoU.traffic light: 0.6487, IoU.fire hydrant: 0.8639, IoU.stop sign: 0.9060, IoU.parking meter: 0.7984, IoU.bench: 0.5488, IoU.bird: 0.8184, IoU.cat: 0.8164, IoU.dog: 0.7847, IoU.horse: 0.8673, IoU.sheep: 0.8747, IoU.cow: 0.8810, IoU.elephant: 0.9209, IoU.bear: 0.9269, IoU.zebra: 0.9183, IoU.giraffe: 0.8564, IoU.backpack: 0.4043, IoU.umbrella: 0.8709, IoU.handbag: 0.3963, IoU.tie: 0.0454, IoU.suitcase: 0.8120, IoU.frisbee: 0.8189, IoU.skis: 0.4765, IoU.snowboard: 0.6570, IoU.sports ball: 0.6178, IoU.kite: 0.7266, IoU.baseball bat: 0.5655, IoU.baseball glove: 0.7216, IoU.skateboard: 0.8090, IoU.surfboard: 0.8243, IoU.tennis racket: 0.8502, IoU.bottle: 0.5243, IoU.wine glass: 0.5985, IoU.cup: 0.5674, IoU.fork: 0.4822, IoU.knife: 0.4044, IoU.spoon: 0.4370, IoU.bowl: 0.5020, IoU.banana: 0.6996, IoU.apple: 0.5554, IoU.sandwich: 0.5125, IoU.orange: 0.7140, IoU.broccoli: 0.5092, IoU.carrot: 0.5889, IoU.hot dog: 0.5816, IoU.pizza: 0.7636, IoU.donut: 0.7688, IoU.cake: 0.6541, IoU.chair: 0.5129, IoU.couch: 0.5810, IoU.potted plant: 0.3422, IoU.bed: 0.6548, IoU.dining table: 0.4745, IoU.toilet: 0.8041, IoU.tv: 0.7311, IoU.laptop: 0.7762, IoU.mouse: 0.7643, IoU.remote: 0.5942, IoU.keyboard: 0.6201, IoU.cell phone: 0.7467, IoU.microwave: 0.6809, IoU.oven: 0.6008, IoU.toaster: 0.7857, IoU.sink: 0.6043, IoU.refrigerator: 0.7677, IoU.book: 0.5312, IoU.clock: 0.6882, IoU.vase: 0.6214, IoU.scissors: 0.6936, IoU.teddy bear: 0.7948, IoU.hair drier: 0.5310, IoU.toothbrush: 0.4969, IoU.banner: 0.3285, IoU.blanket: 0.0873, IoU.branch: 0.1076, IoU.bridge: 0.3854, IoU.building-other: 0.5537, IoU.bush: 0.3290, IoU.cabinet: 0.5884, IoU.cage: 0.2910, IoU.cardboard: 0.5124, IoU.carpet: 0.5438, IoU.ceiling-other: 0.6533, IoU.ceiling-tile: 0.0488, IoU.cloth: 0.0340, IoU.clothes: 0.1658, IoU.clouds: 0.5034, IoU.counter: 0.2956, IoU.cupboard: 0.0000, IoU.curtain: 0.6847, IoU.desk-stuff: 0.4779, IoU.dirt: 0.4256, IoU.door-stuff: 0.4645, IoU.fence: 0.3358, IoU.floor-marble: 0.0805, IoU.floor-other: 0.2233, IoU.floor-stone: 0.0387, IoU.floor-tile: 0.6136, IoU.floor-wood: 0.6429, IoU.flower: 0.3918, IoU.fog: 0.1545, IoU.food-other: 0.2891, IoU.fruit: 0.4561, IoU.furniture-other: 0.1634, IoU.grass: 0.7099, IoU.gravel: 0.2550, IoU.ground-other: 0.0722, IoU.hill: 0.1550, IoU.house: 0.2773, IoU.leaves: 0.2900, IoU.light: 0.4102, IoU.mat: 0.0000, IoU.metal: 0.3336, IoU.mirror-stuff: 0.5719, IoU.moss: 0.0000, IoU.mountain: 0.5499, IoU.mud: 0.0648, IoU.napkin: 0.0892, IoU.net: 0.4893, IoU.paper: 0.3369, IoU.pavement: 0.5166, IoU.pillow: 0.1173, IoU.plant-other: 0.1623, IoU.plastic: 0.2254, IoU.platform: 0.3009, IoU.playingfield: 0.6984, IoU.railing: 0.0830, IoU.railroad: 0.6025, IoU.river: 0.4751, IoU.road: 0.6702, IoU.rock: 0.4617, IoU.roof: 0.2088, IoU.rug: 0.3818, IoU.salad: 0.0002, IoU.sand: 0.6642, IoU.sea: 0.8483, IoU.shelf: 0.3627, IoU.sky-other: 0.7305, IoU.skyscraper: 0.4036, IoU.snow: 0.9086, IoU.solid-other: 0.0000, IoU.stairs: 0.2775, IoU.stone: 0.0320, IoU.straw: 0.3007, IoU.structural-other: 0.0029, IoU.table: 0.2313, IoU.tent: 0.0918, IoU.textile-other: 0.1547, IoU.towel: 0.3337, IoU.tree: 0.7329, IoU.vegetable: 0.4254, IoU.wall-brick: 0.4916, IoU.wall-concrete: 0.6152, IoU.wall-other: 0.2166, IoU.wall-panel: 0.0424, IoU.wall-stone: 0.2937, IoU.wall-tile: 0.6848, IoU.wall-wood: 0.4226, IoU.water-other: 0.2652, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5206, IoU.window-other: 0.4844, IoU.wood: 0.2860, Acc.person: 0.9525, Acc.bicycle: 0.8771, Acc.car: 0.8665, Acc.motorcycle: 0.9265, Acc.airplane: 0.9471, Acc.bus: 0.9229, Acc.train: 0.9582, Acc.truck: 0.8527, Acc.boat: 0.8745, Acc.traffic light: 0.9004, Acc.fire hydrant: 0.9761, Acc.stop sign: 0.9801, Acc.parking meter: 0.8812, Acc.bench: 0.7807, Acc.bird: 0.9233, Acc.cat: 0.8964, Acc.dog: 0.8771, Acc.horse: 0.9546, Acc.sheep: 0.9662, Acc.cow: 0.9357, Acc.elephant: 0.9743, Acc.bear: 0.9682, Acc.zebra: 0.9727, Acc.giraffe: 0.9651, Acc.backpack: 0.6550, Acc.umbrella: 0.9486, Acc.handbag: 0.5646, Acc.tie: 0.0594, Acc.suitcase: 0.9435, Acc.frisbee: 0.9129, Acc.skis: 0.6164, Acc.snowboard: 0.7846, Acc.sports ball: 0.7329, Acc.kite: 0.9074, Acc.baseball bat: 0.7845, Acc.baseball glove: 0.8895, Acc.skateboard: 0.9070, Acc.surfboard: 0.9080, Acc.tennis racket: 0.9382, Acc.bottle: 0.6825, Acc.wine glass: 0.8307, Acc.cup: 0.8266, Acc.fork: 0.6732, Acc.knife: 0.6226, Acc.spoon: 0.6029, Acc.bowl: 0.7254, Acc.banana: 0.9360, Acc.apple: 0.7925, Acc.sandwich: 0.7384, Acc.orange: 0.8260, Acc.broccoli: 0.6585, Acc.carrot: 0.7187, Acc.hot dog: 0.7192, Acc.pizza: 0.9381, Acc.donut: 0.9231, Acc.cake: 0.8625, Acc.chair: 0.7621, Acc.couch: 0.7925, Acc.potted plant: 0.5461, Acc.bed: 0.8232, Acc.dining table: 0.7150, Acc.toilet: 0.9662, Acc.tv: 0.8971, Acc.laptop: 0.9492, Acc.mouse: 0.8892, Acc.remote: 0.7663, Acc.keyboard: 0.6995, Acc.cell phone: 0.8988, Acc.microwave: 0.8356, Acc.oven: 0.8272, Acc.toaster: 0.8629, Acc.sink: 0.8707, Acc.refrigerator: 0.9368, Acc.book: 0.7368, Acc.clock: 0.8417, Acc.vase: 0.8883, Acc.scissors: 0.9664, Acc.teddy bear: 0.9383, Acc.hair drier: 0.5623, Acc.toothbrush: 0.7472, Acc.banner: 0.7318, Acc.blanket: 0.1087, Acc.branch: 0.1335, Acc.bridge: 0.5412, Acc.building-other: 0.7238, Acc.bush: 0.4170, Acc.cabinet: 0.7667, Acc.cage: 0.4367, Acc.cardboard: 0.6385, Acc.carpet: 0.7809, Acc.ceiling-other: 0.8730, Acc.ceiling-tile: 0.0488, Acc.cloth: 0.0457, Acc.clothes: 0.1952, Acc.clouds: 0.6501, Acc.counter: 0.5507, Acc.cupboard: 0.0000, Acc.curtain: 0.8225, Acc.desk-stuff: 0.7175, Acc.dirt: 0.6046, Acc.door-stuff: 0.7631, Acc.fence: 0.5355, Acc.floor-marble: 0.1017, Acc.floor-other: 0.2951, Acc.floor-stone: 0.0505, Acc.floor-tile: 0.7633, Acc.floor-wood: 0.8076, Acc.flower: 0.6200, Acc.fog: 0.1672, Acc.food-other: 0.3483, Acc.fruit: 0.6373, Acc.furniture-other: 0.1989, Acc.grass: 0.8520, Acc.gravel: 0.3423, Acc.ground-other: 0.0880, Acc.hill: 0.1988, Acc.house: 0.3469, Acc.leaves: 0.3482, Acc.light: 0.5595, Acc.mat: 0.0000, Acc.metal: 0.4433, Acc.mirror-stuff: 0.7708, Acc.moss: 0.0000, Acc.mountain: 0.7182, Acc.mud: 0.1090, Acc.napkin: 0.1125, Acc.net: 0.6817, Acc.paper: 0.4788, Acc.pavement: 0.6656, Acc.pillow: 0.1496, Acc.plant-other: 0.2321, Acc.plastic: 0.2766, Acc.platform: 0.5840, Acc.playingfield: 0.9212, Acc.railing: 0.1410, Acc.railroad: 0.8583, Acc.river: 0.7085, Acc.road: 0.8654, Acc.rock: 0.7285, Acc.roof: 0.2545, Acc.rug: 0.5844, Acc.salad: 0.0002, Acc.sand: 0.7149, Acc.sea: 0.9260, Acc.shelf: 0.5227, Acc.sky-other: 0.8875, Acc.skyscraper: 0.5395, Acc.snow: 0.9497, Acc.solid-other: 0.0000, Acc.stairs: 0.5352, Acc.stone: 0.0353, Acc.straw: 0.3865, Acc.structural-other: 0.0029, Acc.table: 0.3079, Acc.tent: 0.1230, Acc.textile-other: 0.2203, Acc.towel: 0.4396, Acc.tree: 0.8862, Acc.vegetable: 0.5722, Acc.wall-brick: 0.6843, Acc.wall-concrete: 0.7876, Acc.wall-other: 0.3041, Acc.wall-panel: 0.0472, Acc.wall-stone: 0.3735, Acc.wall-tile: 0.8883, Acc.wall-wood: 0.5704, Acc.water-other: 0.3701, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6636, Acc.window-other: 0.7413, Acc.wood: 0.4405 2022-04-19 15:03:34,397 - mmseg - INFO - Iter [56050/80000] lr: 4.299e-07, eta: 6:30:31, time: 5.641, data_time: 4.709, memory: 73037, decode.loss_ce: 0.6441, decode.acc_seg: 66.0845, aux.loss_ce: 0.2895, aux.acc_seg: 64.7720, loss: 0.9336 2022-04-19 15:04:20,585 - mmseg - INFO - Iter [56100/80000] lr: 4.290e-07, eta: 6:29:41, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6633, decode.acc_seg: 63.8468, aux.loss_ce: 0.2989, aux.acc_seg: 62.8003, loss: 0.9622 2022-04-19 15:05:07,312 - mmseg - INFO - Iter [56150/80000] lr: 4.281e-07, eta: 6:28:51, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6606, decode.acc_seg: 64.4547, aux.loss_ce: 0.2944, aux.acc_seg: 63.2803, loss: 0.9550 2022-04-19 15:05:53,703 - mmseg - INFO - Iter [56200/80000] lr: 4.272e-07, eta: 6:28:01, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5972, decode.acc_seg: 65.9963, aux.loss_ce: 0.2664, aux.acc_seg: 65.0047, loss: 0.8636 2022-04-19 15:06:40,125 - mmseg - INFO - Iter [56250/80000] lr: 4.263e-07, eta: 6:27:11, time: 0.930, data_time: 0.009, memory: 73037, decode.loss_ce: 0.6438, decode.acc_seg: 66.1951, aux.loss_ce: 0.2900, aux.acc_seg: 64.8508, loss: 0.9338 2022-04-19 15:07:26,549 - mmseg - INFO - Iter [56300/80000] lr: 4.254e-07, eta: 6:26:21, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6452, decode.acc_seg: 65.9661, aux.loss_ce: 0.2894, aux.acc_seg: 64.9778, loss: 0.9346 2022-04-19 15:08:12,915 - mmseg - INFO - Iter [56350/80000] lr: 4.245e-07, eta: 6:25:31, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6119, decode.acc_seg: 66.5282, aux.loss_ce: 0.2780, aux.acc_seg: 65.3486, loss: 0.8899 2022-04-19 15:08:59,201 - mmseg - INFO - Iter [56400/80000] lr: 4.236e-07, eta: 6:24:41, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6276, decode.acc_seg: 65.7348, aux.loss_ce: 0.2845, aux.acc_seg: 64.4504, loss: 0.9121 2022-04-19 15:09:45,539 - mmseg - INFO - Iter [56450/80000] lr: 4.227e-07, eta: 6:23:51, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6813, decode.acc_seg: 63.5771, aux.loss_ce: 0.3035, aux.acc_seg: 62.6749, loss: 0.9848 2022-04-19 15:10:31,965 - mmseg - INFO - Iter [56500/80000] lr: 4.218e-07, eta: 6:23:01, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6615, decode.acc_seg: 65.2973, aux.loss_ce: 0.2943, aux.acc_seg: 64.2849, loss: 0.9557 2022-04-19 15:11:19,009 - mmseg - INFO - Iter [56550/80000] lr: 4.209e-07, eta: 6:22:12, time: 0.941, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6829, decode.acc_seg: 63.5783, aux.loss_ce: 0.3076, aux.acc_seg: 62.4660, loss: 0.9905 2022-04-19 15:12:05,491 - mmseg - INFO - Iter [56600/80000] lr: 4.200e-07, eta: 6:21:22, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6436, decode.acc_seg: 65.6196, aux.loss_ce: 0.2926, aux.acc_seg: 64.3957, loss: 0.9362 2022-04-19 15:12:51,991 - mmseg - INFO - Iter [56650/80000] lr: 4.191e-07, eta: 6:20:32, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6303, decode.acc_seg: 65.7724, aux.loss_ce: 0.2878, aux.acc_seg: 64.2524, loss: 0.9181 2022-04-19 15:13:38,399 - mmseg - INFO - Iter [56700/80000] lr: 4.182e-07, eta: 6:19:42, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6856, decode.acc_seg: 65.2978, aux.loss_ce: 0.3132, aux.acc_seg: 64.2176, loss: 0.9988 2022-04-19 15:14:24,848 - mmseg - INFO - Iter [56750/80000] lr: 4.173e-07, eta: 6:18:52, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6792, decode.acc_seg: 63.1007, aux.loss_ce: 0.3102, aux.acc_seg: 61.8992, loss: 0.9894 2022-04-19 15:15:11,531 - mmseg - INFO - Iter [56800/80000] lr: 4.164e-07, eta: 6:18:02, time: 0.935, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6596, decode.acc_seg: 65.1480, aux.loss_ce: 0.3001, aux.acc_seg: 63.8824, loss: 0.9597 2022-04-19 15:15:57,865 - mmseg - INFO - Iter [56850/80000] lr: 4.155e-07, eta: 6:17:12, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6585, decode.acc_seg: 65.0846, aux.loss_ce: 0.2999, aux.acc_seg: 63.3311, loss: 0.9584 2022-04-19 15:16:44,186 - mmseg - INFO - Iter [56900/80000] lr: 4.146e-07, eta: 6:16:22, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6522, decode.acc_seg: 64.3054, aux.loss_ce: 0.2882, aux.acc_seg: 63.1168, loss: 0.9403 2022-04-19 15:17:30,642 - mmseg - INFO - Iter [56950/80000] lr: 4.137e-07, eta: 6:15:33, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6377, decode.acc_seg: 64.9944, aux.loss_ce: 0.2884, aux.acc_seg: 63.8991, loss: 0.9261 2022-04-19 15:18:16,770 - mmseg - INFO - Saving checkpoint at 57000 iterations 2022-04-19 15:18:28,416 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 15:18:28,416 - mmseg - INFO - Iter [57000/80000] lr: 4.128e-07, eta: 6:14:47, time: 1.155, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6593, decode.acc_seg: 65.1456, aux.loss_ce: 0.2983, aux.acc_seg: 63.8735, loss: 0.9576 2022-04-19 15:19:15,079 - mmseg - INFO - Iter [57050/80000] lr: 4.119e-07, eta: 6:13:58, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6321, decode.acc_seg: 65.1263, aux.loss_ce: 0.2892, aux.acc_seg: 63.5515, loss: 0.9213 2022-04-19 15:20:01,446 - mmseg - INFO - Iter [57100/80000] lr: 4.110e-07, eta: 6:13:08, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6354, decode.acc_seg: 64.3480, aux.loss_ce: 0.2916, aux.acc_seg: 63.0045, loss: 0.9270 2022-04-19 15:20:47,850 - mmseg - INFO - Iter [57150/80000] lr: 4.101e-07, eta: 6:12:18, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6235, decode.acc_seg: 65.7163, aux.loss_ce: 0.2811, aux.acc_seg: 64.6064, loss: 0.9046 2022-04-19 15:21:34,532 - mmseg - INFO - Iter [57200/80000] lr: 4.092e-07, eta: 6:11:28, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6335, decode.acc_seg: 64.4566, aux.loss_ce: 0.2873, aux.acc_seg: 63.1182, loss: 0.9208 2022-04-19 15:22:20,930 - mmseg - INFO - Iter [57250/80000] lr: 4.083e-07, eta: 6:10:38, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6476, decode.acc_seg: 65.2150, aux.loss_ce: 0.2898, aux.acc_seg: 64.0676, loss: 0.9374 2022-04-19 15:23:07,488 - mmseg - INFO - Iter [57300/80000] lr: 4.074e-07, eta: 6:09:48, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6622, decode.acc_seg: 65.2807, aux.loss_ce: 0.2985, aux.acc_seg: 63.8930, loss: 0.9607 2022-04-19 15:23:54,361 - mmseg - INFO - Iter [57350/80000] lr: 4.065e-07, eta: 6:08:59, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6376, decode.acc_seg: 64.5457, aux.loss_ce: 0.2841, aux.acc_seg: 63.6937, loss: 0.9217 2022-04-19 15:24:40,715 - mmseg - INFO - Iter [57400/80000] lr: 4.056e-07, eta: 6:08:09, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6291, decode.acc_seg: 64.5996, aux.loss_ce: 0.2801, aux.acc_seg: 63.4723, loss: 0.9092 2022-04-19 15:25:27,148 - mmseg - INFO - Iter [57450/80000] lr: 4.047e-07, eta: 6:07:19, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6548, decode.acc_seg: 64.3715, aux.loss_ce: 0.2972, aux.acc_seg: 63.1060, loss: 0.9520 2022-04-19 15:26:13,498 - mmseg - INFO - Iter [57500/80000] lr: 4.038e-07, eta: 6:06:29, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6590, decode.acc_seg: 65.3688, aux.loss_ce: 0.2935, aux.acc_seg: 64.2262, loss: 0.9525 2022-04-19 15:26:59,867 - mmseg - INFO - Iter [57550/80000] lr: 4.029e-07, eta: 6:05:39, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6153, decode.acc_seg: 65.9247, aux.loss_ce: 0.2781, aux.acc_seg: 64.2500, loss: 0.8934 2022-04-19 15:27:46,437 - mmseg - INFO - Iter [57600/80000] lr: 4.020e-07, eta: 6:04:50, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6634, decode.acc_seg: 64.9231, aux.loss_ce: 0.2988, aux.acc_seg: 63.3134, loss: 0.9622 2022-04-19 15:28:32,673 - mmseg - INFO - Iter [57650/80000] lr: 4.011e-07, eta: 6:04:00, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6752, decode.acc_seg: 64.0680, aux.loss_ce: 0.3053, aux.acc_seg: 63.1275, loss: 0.9805 2022-04-19 15:29:18,924 - mmseg - INFO - Iter [57700/80000] lr: 4.002e-07, eta: 6:03:10, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6717, decode.acc_seg: 65.3851, aux.loss_ce: 0.3002, aux.acc_seg: 64.0212, loss: 0.9719 2022-04-19 15:30:05,345 - mmseg - INFO - Iter [57750/80000] lr: 3.993e-07, eta: 6:02:20, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6383, decode.acc_seg: 65.8701, aux.loss_ce: 0.2897, aux.acc_seg: 64.2705, loss: 0.9280 2022-04-19 15:30:51,775 - mmseg - INFO - Iter [57800/80000] lr: 3.985e-07, eta: 6:01:30, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6476, decode.acc_seg: 64.3902, aux.loss_ce: 0.2899, aux.acc_seg: 63.2972, loss: 0.9376 2022-04-19 15:31:38,237 - mmseg - INFO - Iter [57850/80000] lr: 3.976e-07, eta: 6:00:40, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6699, decode.acc_seg: 64.3855, aux.loss_ce: 0.3035, aux.acc_seg: 63.1057, loss: 0.9734 2022-04-19 15:32:24,733 - mmseg - INFO - Iter [57900/80000] lr: 3.967e-07, eta: 5:59:51, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6233, decode.acc_seg: 66.3933, aux.loss_ce: 0.2832, aux.acc_seg: 65.3059, loss: 0.9065 2022-04-19 15:33:11,040 - mmseg - INFO - Iter [57950/80000] lr: 3.958e-07, eta: 5:59:01, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6493, decode.acc_seg: 64.0885, aux.loss_ce: 0.2948, aux.acc_seg: 62.5166, loss: 0.9441 2022-04-19 15:33:57,471 - mmseg - INFO - Saving checkpoint at 58000 iterations 2022-04-19 15:34:08,550 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 15:34:08,551 - mmseg - INFO - Iter [58000/80000] lr: 3.949e-07, eta: 5:58:15, time: 1.150, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6628, decode.acc_seg: 64.0717, aux.loss_ce: 0.3007, aux.acc_seg: 62.6879, loss: 0.9635 2022-04-19 15:34:55,276 - mmseg - INFO - Iter [58050/80000] lr: 3.940e-07, eta: 5:57:26, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6185, decode.acc_seg: 66.4603, aux.loss_ce: 0.2800, aux.acc_seg: 65.1543, loss: 0.8985 2022-04-19 15:35:41,944 - mmseg - INFO - Iter [58100/80000] lr: 3.931e-07, eta: 5:56:36, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6587, decode.acc_seg: 63.9764, aux.loss_ce: 0.2937, aux.acc_seg: 63.0477, loss: 0.9523 2022-04-19 15:36:28,475 - mmseg - INFO - Iter [58150/80000] lr: 3.922e-07, eta: 5:55:46, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6442, decode.acc_seg: 64.6967, aux.loss_ce: 0.2916, aux.acc_seg: 63.5295, loss: 0.9358 2022-04-19 15:37:15,029 - mmseg - INFO - Iter [58200/80000] lr: 3.913e-07, eta: 5:54:57, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6421, decode.acc_seg: 66.1154, aux.loss_ce: 0.2869, aux.acc_seg: 65.1041, loss: 0.9290 2022-04-19 15:38:01,940 - mmseg - INFO - Iter [58250/80000] lr: 3.904e-07, eta: 5:54:07, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6368, decode.acc_seg: 64.4528, aux.loss_ce: 0.2906, aux.acc_seg: 63.0029, loss: 0.9274 2022-04-19 15:38:48,449 - mmseg - INFO - Iter [58300/80000] lr: 3.895e-07, eta: 5:53:17, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6374, decode.acc_seg: 65.2608, aux.loss_ce: 0.2868, aux.acc_seg: 63.8488, loss: 0.9242 2022-04-19 15:39:35,377 - mmseg - INFO - Iter [58350/80000] lr: 3.886e-07, eta: 5:52:28, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6193, decode.acc_seg: 65.7704, aux.loss_ce: 0.2822, aux.acc_seg: 64.6524, loss: 0.9015 2022-04-19 15:40:21,737 - mmseg - INFO - Iter [58400/80000] lr: 3.877e-07, eta: 5:51:38, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6276, decode.acc_seg: 65.0051, aux.loss_ce: 0.2852, aux.acc_seg: 63.8830, loss: 0.9128 2022-04-19 15:41:08,238 - mmseg - INFO - Iter [58450/80000] lr: 3.868e-07, eta: 5:50:48, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6547, decode.acc_seg: 65.0441, aux.loss_ce: 0.2956, aux.acc_seg: 63.5442, loss: 0.9502 2022-04-19 15:41:54,821 - mmseg - INFO - Iter [58500/80000] lr: 3.859e-07, eta: 5:49:59, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6783, decode.acc_seg: 64.1598, aux.loss_ce: 0.3069, aux.acc_seg: 62.6497, loss: 0.9852 2022-04-19 15:42:41,430 - mmseg - INFO - Iter [58550/80000] lr: 3.850e-07, eta: 5:49:09, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6514, decode.acc_seg: 64.4097, aux.loss_ce: 0.2927, aux.acc_seg: 63.3716, loss: 0.9441 2022-04-19 15:43:28,208 - mmseg - INFO - Iter [58600/80000] lr: 3.841e-07, eta: 5:48:19, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6545, decode.acc_seg: 64.7837, aux.loss_ce: 0.2948, aux.acc_seg: 63.7747, loss: 0.9493 2022-04-19 15:44:14,534 - mmseg - INFO - Iter [58650/80000] lr: 3.832e-07, eta: 5:47:30, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6597, decode.acc_seg: 64.2766, aux.loss_ce: 0.2979, aux.acc_seg: 62.6957, loss: 0.9576 2022-04-19 15:45:00,924 - mmseg - INFO - Iter [58700/80000] lr: 3.823e-07, eta: 5:46:40, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6461, decode.acc_seg: 65.2771, aux.loss_ce: 0.2852, aux.acc_seg: 64.2799, loss: 0.9313 2022-04-19 15:45:47,362 - mmseg - INFO - Iter [58750/80000] lr: 3.814e-07, eta: 5:45:50, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6516, decode.acc_seg: 63.1020, aux.loss_ce: 0.2972, aux.acc_seg: 62.0467, loss: 0.9488 2022-04-19 15:46:33,870 - mmseg - INFO - Iter [58800/80000] lr: 3.805e-07, eta: 5:45:01, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6587, decode.acc_seg: 65.0466, aux.loss_ce: 0.2944, aux.acc_seg: 64.1057, loss: 0.9531 2022-04-19 15:47:20,299 - mmseg - INFO - Iter [58850/80000] lr: 3.796e-07, eta: 5:44:11, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6484, decode.acc_seg: 64.7696, aux.loss_ce: 0.2947, aux.acc_seg: 63.3854, loss: 0.9431 2022-04-19 15:48:07,020 - mmseg - INFO - Iter [58900/80000] lr: 3.787e-07, eta: 5:43:21, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6463, decode.acc_seg: 66.2852, aux.loss_ce: 0.2911, aux.acc_seg: 64.9199, loss: 0.9374 2022-04-19 15:48:53,646 - mmseg - INFO - Iter [58950/80000] lr: 3.778e-07, eta: 5:42:32, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6432, decode.acc_seg: 64.6699, aux.loss_ce: 0.2901, aux.acc_seg: 63.2539, loss: 0.9333 2022-04-19 15:49:40,051 - mmseg - INFO - Saving checkpoint at 59000 iterations 2022-04-19 15:49:50,223 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 15:49:50,223 - mmseg - INFO - Iter [59000/80000] lr: 3.769e-07, eta: 5:41:46, time: 1.132, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6300, decode.acc_seg: 63.6446, aux.loss_ce: 0.2832, aux.acc_seg: 62.5542, loss: 0.9132 2022-04-19 15:50:36,951 - mmseg - INFO - Iter [59050/80000] lr: 3.760e-07, eta: 5:40:56, time: 0.934, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6469, decode.acc_seg: 64.6180, aux.loss_ce: 0.2889, aux.acc_seg: 63.5647, loss: 0.9358 2022-04-19 15:51:23,461 - mmseg - INFO - Iter [59100/80000] lr: 3.751e-07, eta: 5:40:06, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6282, decode.acc_seg: 65.1007, aux.loss_ce: 0.2800, aux.acc_seg: 64.0588, loss: 0.9081 2022-04-19 15:52:12,769 - mmseg - INFO - Iter [59150/80000] lr: 3.742e-07, eta: 5:39:18, time: 0.986, data_time: 0.056, memory: 73037, decode.loss_ce: 0.6238, decode.acc_seg: 64.1321, aux.loss_ce: 0.2846, aux.acc_seg: 62.9951, loss: 0.9085 2022-04-19 15:52:59,581 - mmseg - INFO - Iter [59200/80000] lr: 3.733e-07, eta: 5:38:28, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6055, decode.acc_seg: 65.8943, aux.loss_ce: 0.2764, aux.acc_seg: 64.4542, loss: 0.8819 2022-04-19 15:53:46,113 - mmseg - INFO - Iter [59250/80000] lr: 3.724e-07, eta: 5:37:39, time: 0.932, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6551, decode.acc_seg: 64.5724, aux.loss_ce: 0.2979, aux.acc_seg: 63.3011, loss: 0.9530 2022-04-19 15:54:33,030 - mmseg - INFO - Iter [59300/80000] lr: 3.715e-07, eta: 5:36:49, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6398, decode.acc_seg: 65.5490, aux.loss_ce: 0.2924, aux.acc_seg: 64.0241, loss: 0.9323 2022-04-19 15:55:19,455 - mmseg - INFO - Iter [59350/80000] lr: 3.706e-07, eta: 5:35:59, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6118, decode.acc_seg: 65.7595, aux.loss_ce: 0.2808, aux.acc_seg: 64.4439, loss: 0.8925 2022-04-19 15:56:06,363 - mmseg - INFO - Iter [59400/80000] lr: 3.697e-07, eta: 5:35:10, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6499, decode.acc_seg: 64.3751, aux.loss_ce: 0.2951, aux.acc_seg: 62.8104, loss: 0.9450 2022-04-19 15:56:52,881 - mmseg - INFO - Iter [59450/80000] lr: 3.688e-07, eta: 5:34:20, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6500, decode.acc_seg: 64.1585, aux.loss_ce: 0.2993, aux.acc_seg: 62.3847, loss: 0.9493 2022-04-19 15:57:39,383 - mmseg - INFO - Iter [59500/80000] lr: 3.679e-07, eta: 5:33:31, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6424, decode.acc_seg: 64.7751, aux.loss_ce: 0.2896, aux.acc_seg: 63.6363, loss: 0.9321 2022-04-19 15:58:25,696 - mmseg - INFO - Iter [59550/80000] lr: 3.670e-07, eta: 5:32:41, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6378, decode.acc_seg: 65.8339, aux.loss_ce: 0.2921, aux.acc_seg: 64.2983, loss: 0.9299 2022-04-19 15:59:11,914 - mmseg - INFO - Iter [59600/80000] lr: 3.661e-07, eta: 5:31:51, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6220, decode.acc_seg: 65.4492, aux.loss_ce: 0.2860, aux.acc_seg: 64.0896, loss: 0.9080 2022-04-19 15:59:58,337 - mmseg - INFO - Iter [59650/80000] lr: 3.652e-07, eta: 5:31:02, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6292, decode.acc_seg: 64.9719, aux.loss_ce: 0.2919, aux.acc_seg: 62.9049, loss: 0.9211 2022-04-19 16:00:44,979 - mmseg - INFO - Iter [59700/80000] lr: 3.644e-07, eta: 5:30:12, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6427, decode.acc_seg: 64.4499, aux.loss_ce: 0.2943, aux.acc_seg: 62.9375, loss: 0.9370 2022-04-19 16:01:31,791 - mmseg - INFO - Iter [59750/80000] lr: 3.635e-07, eta: 5:29:23, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6312, decode.acc_seg: 66.2122, aux.loss_ce: 0.2870, aux.acc_seg: 64.8330, loss: 0.9182 2022-04-19 16:02:18,211 - mmseg - INFO - Iter [59800/80000] lr: 3.626e-07, eta: 5:28:33, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6544, decode.acc_seg: 64.3080, aux.loss_ce: 0.2946, aux.acc_seg: 63.1014, loss: 0.9490 2022-04-19 16:03:04,649 - mmseg - INFO - Iter [59850/80000] lr: 3.617e-07, eta: 5:27:44, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6608, decode.acc_seg: 64.2164, aux.loss_ce: 0.2969, aux.acc_seg: 62.9364, loss: 0.9576 2022-04-19 16:03:51,257 - mmseg - INFO - Iter [59900/80000] lr: 3.608e-07, eta: 5:26:54, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6660, decode.acc_seg: 64.1415, aux.loss_ce: 0.3006, aux.acc_seg: 62.9366, loss: 0.9666 2022-04-19 16:04:37,594 - mmseg - INFO - Iter [59950/80000] lr: 3.599e-07, eta: 5:26:04, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5897, decode.acc_seg: 66.7941, aux.loss_ce: 0.2683, aux.acc_seg: 65.3820, loss: 0.8579 2022-04-19 16:05:24,166 - mmseg - INFO - Saving checkpoint at 60000 iterations 2022-04-19 16:05:38,020 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 16:05:38,036 - mmseg - INFO - Iter [60000/80000] lr: 3.590e-07, eta: 5:25:20, time: 1.206, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6731, decode.acc_seg: 64.2410, aux.loss_ce: 0.3041, aux.acc_seg: 62.8555, loss: 0.9772 2022-04-19 16:06:24,706 - mmseg - INFO - Iter [60050/80000] lr: 3.581e-07, eta: 5:24:30, time: 0.936, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6368, decode.acc_seg: 64.5363, aux.loss_ce: 0.2896, aux.acc_seg: 63.2914, loss: 0.9263 2022-04-19 16:07:11,266 - mmseg - INFO - Iter [60100/80000] lr: 3.572e-07, eta: 5:23:41, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6279, decode.acc_seg: 65.1405, aux.loss_ce: 0.2840, aux.acc_seg: 63.5829, loss: 0.9119 2022-04-19 16:07:57,664 - mmseg - INFO - Iter [60150/80000] lr: 3.563e-07, eta: 5:22:51, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6389, decode.acc_seg: 65.9725, aux.loss_ce: 0.2892, aux.acc_seg: 64.4868, loss: 0.9281 2022-04-19 16:08:44,000 - mmseg - INFO - Iter [60200/80000] lr: 3.554e-07, eta: 5:22:01, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6003, decode.acc_seg: 66.4692, aux.loss_ce: 0.2747, aux.acc_seg: 65.0188, loss: 0.8750 2022-04-19 16:09:30,324 - mmseg - INFO - Iter [60250/80000] lr: 3.545e-07, eta: 5:21:12, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6294, decode.acc_seg: 65.0034, aux.loss_ce: 0.2876, aux.acc_seg: 63.6340, loss: 0.9170 2022-04-19 16:10:17,034 - mmseg - INFO - Iter [60300/80000] lr: 3.536e-07, eta: 5:20:22, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6404, decode.acc_seg: 65.5126, aux.loss_ce: 0.2878, aux.acc_seg: 64.5161, loss: 0.9283 2022-04-19 16:11:03,241 - mmseg - INFO - Iter [60350/80000] lr: 3.527e-07, eta: 5:19:33, time: 0.924, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6702, decode.acc_seg: 64.8734, aux.loss_ce: 0.3028, aux.acc_seg: 63.4839, loss: 0.9730 2022-04-19 16:11:49,911 - mmseg - INFO - Iter [60400/80000] lr: 3.518e-07, eta: 5:18:43, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6487, decode.acc_seg: 64.2705, aux.loss_ce: 0.2940, aux.acc_seg: 62.8197, loss: 0.9427 2022-04-19 16:12:36,206 - mmseg - INFO - Iter [60450/80000] lr: 3.509e-07, eta: 5:17:54, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6081, decode.acc_seg: 65.6383, aux.loss_ce: 0.2778, aux.acc_seg: 64.1477, loss: 0.8858 2022-04-19 16:13:22,917 - mmseg - INFO - Iter [60500/80000] lr: 3.500e-07, eta: 5:17:04, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6219, decode.acc_seg: 65.7068, aux.loss_ce: 0.2848, aux.acc_seg: 63.9930, loss: 0.9067 2022-04-19 16:14:09,230 - mmseg - INFO - Iter [60550/80000] lr: 3.491e-07, eta: 5:16:15, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6341, decode.acc_seg: 66.3386, aux.loss_ce: 0.2860, aux.acc_seg: 65.0438, loss: 0.9201 2022-04-19 16:14:55,532 - mmseg - INFO - Iter [60600/80000] lr: 3.482e-07, eta: 5:15:25, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6296, decode.acc_seg: 66.4721, aux.loss_ce: 0.2880, aux.acc_seg: 65.0471, loss: 0.9176 2022-04-19 16:15:42,100 - mmseg - INFO - Iter [60650/80000] lr: 3.473e-07, eta: 5:14:35, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6658, decode.acc_seg: 64.8593, aux.loss_ce: 0.3043, aux.acc_seg: 63.3974, loss: 0.9701 2022-04-19 16:16:28,885 - mmseg - INFO - Iter [60700/80000] lr: 3.464e-07, eta: 5:13:46, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6132, decode.acc_seg: 66.0306, aux.loss_ce: 0.2822, aux.acc_seg: 64.2946, loss: 0.8953 2022-04-19 16:17:15,496 - mmseg - INFO - Iter [60750/80000] lr: 3.455e-07, eta: 5:12:57, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6225, decode.acc_seg: 64.7816, aux.loss_ce: 0.2863, aux.acc_seg: 63.2475, loss: 0.9088 2022-04-19 16:18:01,949 - mmseg - INFO - Iter [60800/80000] lr: 3.446e-07, eta: 5:12:07, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6436, decode.acc_seg: 64.6241, aux.loss_ce: 0.2936, aux.acc_seg: 63.1186, loss: 0.9373 2022-04-19 16:18:48,321 - mmseg - INFO - Iter [60850/80000] lr: 3.437e-07, eta: 5:11:18, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6308, decode.acc_seg: 65.0837, aux.loss_ce: 0.2888, aux.acc_seg: 63.4696, loss: 0.9196 2022-04-19 16:19:35,024 - mmseg - INFO - Iter [60900/80000] lr: 3.428e-07, eta: 5:10:28, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6216, decode.acc_seg: 66.3829, aux.loss_ce: 0.2828, aux.acc_seg: 65.2179, loss: 0.9045 2022-04-19 16:20:21,777 - mmseg - INFO - Iter [60950/80000] lr: 3.419e-07, eta: 5:09:39, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6168, decode.acc_seg: 65.2939, aux.loss_ce: 0.2819, aux.acc_seg: 63.5944, loss: 0.8987 2022-04-19 16:21:08,225 - mmseg - INFO - Saving checkpoint at 61000 iterations 2022-04-19 16:21:18,550 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 16:21:18,550 - mmseg - INFO - Iter [61000/80000] lr: 3.410e-07, eta: 5:08:53, time: 1.135, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6486, decode.acc_seg: 64.6343, aux.loss_ce: 0.2968, aux.acc_seg: 63.3520, loss: 0.9454 2022-04-19 16:22:04,997 - mmseg - INFO - Iter [61050/80000] lr: 3.401e-07, eta: 5:08:03, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6249, decode.acc_seg: 65.5694, aux.loss_ce: 0.2860, aux.acc_seg: 64.1696, loss: 0.9109 2022-04-19 16:22:51,598 - mmseg - INFO - Iter [61100/80000] lr: 3.392e-07, eta: 5:07:14, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6140, decode.acc_seg: 65.3721, aux.loss_ce: 0.2788, aux.acc_seg: 64.2952, loss: 0.8928 2022-04-19 16:23:37,936 - mmseg - INFO - Iter [61150/80000] lr: 3.383e-07, eta: 5:06:24, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6212, decode.acc_seg: 65.5873, aux.loss_ce: 0.2832, aux.acc_seg: 64.0575, loss: 0.9044 2022-04-19 16:24:24,522 - mmseg - INFO - Iter [61200/80000] lr: 3.374e-07, eta: 5:05:35, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6196, decode.acc_seg: 66.0688, aux.loss_ce: 0.2780, aux.acc_seg: 64.9103, loss: 0.8976 2022-04-19 16:25:10,998 - mmseg - INFO - Iter [61250/80000] lr: 3.365e-07, eta: 5:04:45, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6524, decode.acc_seg: 64.2288, aux.loss_ce: 0.2940, aux.acc_seg: 62.6181, loss: 0.9464 2022-04-19 16:25:57,647 - mmseg - INFO - Iter [61300/80000] lr: 3.356e-07, eta: 5:03:56, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6336, decode.acc_seg: 65.5800, aux.loss_ce: 0.2917, aux.acc_seg: 63.8010, loss: 0.9253 2022-04-19 16:26:44,021 - mmseg - INFO - Iter [61350/80000] lr: 3.347e-07, eta: 5:03:06, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6515, decode.acc_seg: 65.2136, aux.loss_ce: 0.2936, aux.acc_seg: 63.8549, loss: 0.9451 2022-04-19 16:27:30,323 - mmseg - INFO - Iter [61400/80000] lr: 3.338e-07, eta: 5:02:17, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6474, decode.acc_seg: 66.1066, aux.loss_ce: 0.2956, aux.acc_seg: 64.4804, loss: 0.9430 2022-04-19 16:28:16,415 - mmseg - INFO - Iter [61450/80000] lr: 3.329e-07, eta: 5:01:27, time: 0.922, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6327, decode.acc_seg: 65.6649, aux.loss_ce: 0.2846, aux.acc_seg: 64.4197, loss: 0.9173 2022-04-19 16:29:03,051 - mmseg - INFO - Iter [61500/80000] lr: 3.320e-07, eta: 5:00:38, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6319, decode.acc_seg: 65.8058, aux.loss_ce: 0.2860, aux.acc_seg: 64.6355, loss: 0.9179 2022-04-19 16:29:49,936 - mmseg - INFO - Iter [61550/80000] lr: 3.311e-07, eta: 4:59:48, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6391, decode.acc_seg: 65.4545, aux.loss_ce: 0.2893, aux.acc_seg: 64.2916, loss: 0.9284 2022-04-19 16:30:36,387 - mmseg - INFO - Iter [61600/80000] lr: 3.303e-07, eta: 4:58:59, time: 0.931, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6309, decode.acc_seg: 64.8058, aux.loss_ce: 0.2859, aux.acc_seg: 64.0333, loss: 0.9169 2022-04-19 16:31:22,961 - mmseg - INFO - Iter [61650/80000] lr: 3.294e-07, eta: 4:58:10, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6305, decode.acc_seg: 65.4747, aux.loss_ce: 0.2869, aux.acc_seg: 63.8781, loss: 0.9175 2022-04-19 16:32:09,431 - mmseg - INFO - Iter [61700/80000] lr: 3.285e-07, eta: 4:57:20, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6112, decode.acc_seg: 65.5517, aux.loss_ce: 0.2778, aux.acc_seg: 63.8594, loss: 0.8890 2022-04-19 16:32:55,895 - mmseg - INFO - Iter [61750/80000] lr: 3.276e-07, eta: 4:56:31, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6294, decode.acc_seg: 64.6314, aux.loss_ce: 0.2846, aux.acc_seg: 63.5164, loss: 0.9140 2022-04-19 16:33:42,167 - mmseg - INFO - Iter [61800/80000] lr: 3.267e-07, eta: 4:55:41, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5932, decode.acc_seg: 66.0038, aux.loss_ce: 0.2703, aux.acc_seg: 64.7811, loss: 0.8635 2022-04-19 16:34:28,365 - mmseg - INFO - Iter [61850/80000] lr: 3.258e-07, eta: 4:54:52, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6472, decode.acc_seg: 65.3033, aux.loss_ce: 0.2978, aux.acc_seg: 63.6223, loss: 0.9450 2022-04-19 16:35:14,906 - mmseg - INFO - Iter [61900/80000] lr: 3.249e-07, eta: 4:54:02, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6332, decode.acc_seg: 65.8147, aux.loss_ce: 0.2866, aux.acc_seg: 64.5382, loss: 0.9198 2022-04-19 16:36:01,464 - mmseg - INFO - Iter [61950/80000] lr: 3.240e-07, eta: 4:53:13, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6066, decode.acc_seg: 66.0234, aux.loss_ce: 0.2755, aux.acc_seg: 64.9466, loss: 0.8821 2022-04-19 16:36:47,556 - mmseg - INFO - Saving checkpoint at 62000 iterations 2022-04-19 16:36:59,301 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 16:36:59,324 - mmseg - INFO - Iter [62000/80000] lr: 3.231e-07, eta: 4:52:27, time: 1.157, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6509, decode.acc_seg: 64.8323, aux.loss_ce: 0.2962, aux.acc_seg: 63.2041, loss: 0.9471 2022-04-19 16:37:46,410 - mmseg - INFO - Iter [62050/80000] lr: 3.222e-07, eta: 4:51:38, time: 0.943, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6474, decode.acc_seg: 64.5552, aux.loss_ce: 0.2901, aux.acc_seg: 63.4681, loss: 0.9375 2022-04-19 16:38:33,378 - mmseg - INFO - Iter [62100/80000] lr: 3.213e-07, eta: 4:50:49, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5955, decode.acc_seg: 66.7888, aux.loss_ce: 0.2698, aux.acc_seg: 65.6257, loss: 0.8653 2022-04-19 16:39:19,519 - mmseg - INFO - Iter [62150/80000] lr: 3.204e-07, eta: 4:49:59, time: 0.923, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6212, decode.acc_seg: 65.9397, aux.loss_ce: 0.2838, aux.acc_seg: 64.6435, loss: 0.9049 2022-04-19 16:40:06,009 - mmseg - INFO - Iter [62200/80000] lr: 3.195e-07, eta: 4:49:10, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6282, decode.acc_seg: 65.8660, aux.loss_ce: 0.2862, aux.acc_seg: 64.4464, loss: 0.9145 2022-04-19 16:40:52,419 - mmseg - INFO - Iter [62250/80000] lr: 3.186e-07, eta: 4:48:20, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6158, decode.acc_seg: 65.9604, aux.loss_ce: 0.2798, aux.acc_seg: 64.4775, loss: 0.8956 2022-04-19 16:41:38,905 - mmseg - INFO - Iter [62300/80000] lr: 3.177e-07, eta: 4:47:31, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6402, decode.acc_seg: 65.2931, aux.loss_ce: 0.2910, aux.acc_seg: 64.0270, loss: 0.9312 2022-04-19 16:42:25,321 - mmseg - INFO - Iter [62350/80000] lr: 3.168e-07, eta: 4:46:42, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6070, decode.acc_seg: 65.8844, aux.loss_ce: 0.2766, aux.acc_seg: 64.2178, loss: 0.8835 2022-04-19 16:43:12,030 - mmseg - INFO - Iter [62400/80000] lr: 3.159e-07, eta: 4:45:52, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6187, decode.acc_seg: 64.3603, aux.loss_ce: 0.2831, aux.acc_seg: 63.0061, loss: 0.9018 2022-04-19 16:43:58,364 - mmseg - INFO - Iter [62450/80000] lr: 3.150e-07, eta: 4:45:03, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6214, decode.acc_seg: 66.1347, aux.loss_ce: 0.2862, aux.acc_seg: 65.1849, loss: 0.9076 2022-04-19 16:44:45,086 - mmseg - INFO - Iter [62500/80000] lr: 3.141e-07, eta: 4:44:14, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6287, decode.acc_seg: 65.4694, aux.loss_ce: 0.2859, aux.acc_seg: 64.2068, loss: 0.9145 2022-04-19 16:45:31,557 - mmseg - INFO - Iter [62550/80000] lr: 3.132e-07, eta: 4:43:24, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6144, decode.acc_seg: 65.5527, aux.loss_ce: 0.2831, aux.acc_seg: 64.2137, loss: 0.8975 2022-04-19 16:46:18,219 - mmseg - INFO - Iter [62600/80000] lr: 3.123e-07, eta: 4:42:35, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6487, decode.acc_seg: 67.0680, aux.loss_ce: 0.2969, aux.acc_seg: 65.4153, loss: 0.9456 2022-04-19 16:47:04,890 - mmseg - INFO - Iter [62650/80000] lr: 3.114e-07, eta: 4:41:46, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6525, decode.acc_seg: 65.1358, aux.loss_ce: 0.2938, aux.acc_seg: 63.8986, loss: 0.9463 2022-04-19 16:47:51,566 - mmseg - INFO - Iter [62700/80000] lr: 3.105e-07, eta: 4:40:56, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6202, decode.acc_seg: 66.3912, aux.loss_ce: 0.2806, aux.acc_seg: 65.2979, loss: 0.9008 2022-04-19 16:48:38,250 - mmseg - INFO - Iter [62750/80000] lr: 3.096e-07, eta: 4:40:07, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6097, decode.acc_seg: 65.5321, aux.loss_ce: 0.2812, aux.acc_seg: 63.8758, loss: 0.8909 2022-04-19 16:49:24,718 - mmseg - INFO - Iter [62800/80000] lr: 3.087e-07, eta: 4:39:18, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6094, decode.acc_seg: 66.2158, aux.loss_ce: 0.2791, aux.acc_seg: 65.1220, loss: 0.8885 2022-04-19 16:50:11,548 - mmseg - INFO - Iter [62850/80000] lr: 3.078e-07, eta: 4:38:28, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6289, decode.acc_seg: 66.7221, aux.loss_ce: 0.2862, aux.acc_seg: 65.5419, loss: 0.9151 2022-04-19 16:50:57,937 - mmseg - INFO - Iter [62900/80000] lr: 3.069e-07, eta: 4:37:39, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6322, decode.acc_seg: 64.4617, aux.loss_ce: 0.2903, aux.acc_seg: 63.0198, loss: 0.9225 2022-04-19 16:51:44,780 - mmseg - INFO - Iter [62950/80000] lr: 3.060e-07, eta: 4:36:50, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6396, decode.acc_seg: 64.5148, aux.loss_ce: 0.2907, aux.acc_seg: 63.3298, loss: 0.9303 2022-04-19 16:52:31,096 - mmseg - INFO - Saving checkpoint at 63000 iterations 2022-04-19 16:52:43,871 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 16:52:43,872 - mmseg - INFO - Iter [63000/80000] lr: 3.051e-07, eta: 4:36:04, time: 1.181, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6381, decode.acc_seg: 65.8184, aux.loss_ce: 0.2897, aux.acc_seg: 64.5573, loss: 0.9278 2022-04-19 16:53:30,460 - mmseg - INFO - Iter [63050/80000] lr: 3.042e-07, eta: 4:35:15, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6376, decode.acc_seg: 65.4369, aux.loss_ce: 0.2886, aux.acc_seg: 64.4455, loss: 0.9261 2022-04-19 16:54:16,888 - mmseg - INFO - Iter [63100/80000] lr: 3.033e-07, eta: 4:34:25, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6535, decode.acc_seg: 63.8743, aux.loss_ce: 0.2919, aux.acc_seg: 62.8689, loss: 0.9454 2022-04-19 16:55:03,354 - mmseg - INFO - Iter [63150/80000] lr: 3.024e-07, eta: 4:33:36, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6013, decode.acc_seg: 65.8497, aux.loss_ce: 0.2738, aux.acc_seg: 64.5559, loss: 0.8751 2022-04-19 16:55:49,674 - mmseg - INFO - Iter [63200/80000] lr: 3.015e-07, eta: 4:32:47, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6146, decode.acc_seg: 65.8455, aux.loss_ce: 0.2804, aux.acc_seg: 64.5242, loss: 0.8950 2022-04-19 16:56:36,168 - mmseg - INFO - Iter [63250/80000] lr: 3.006e-07, eta: 4:31:57, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6455, decode.acc_seg: 66.4838, aux.loss_ce: 0.2932, aux.acc_seg: 65.2502, loss: 0.9387 2022-04-19 16:57:22,453 - mmseg - INFO - Iter [63300/80000] lr: 2.997e-07, eta: 4:31:08, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6085, decode.acc_seg: 65.7133, aux.loss_ce: 0.2788, aux.acc_seg: 64.2845, loss: 0.8873 2022-04-19 16:58:08,750 - mmseg - INFO - Iter [63350/80000] lr: 2.988e-07, eta: 4:30:19, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6715, decode.acc_seg: 64.3987, aux.loss_ce: 0.3042, aux.acc_seg: 63.0480, loss: 0.9757 2022-04-19 16:58:55,056 - mmseg - INFO - Iter [63400/80000] lr: 2.979e-07, eta: 4:29:29, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5998, decode.acc_seg: 66.1845, aux.loss_ce: 0.2750, aux.acc_seg: 64.7237, loss: 0.8748 2022-04-19 16:59:41,542 - mmseg - INFO - Iter [63450/80000] lr: 2.970e-07, eta: 4:28:40, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6320, decode.acc_seg: 65.0093, aux.loss_ce: 0.2901, aux.acc_seg: 63.9527, loss: 0.9221 2022-04-19 17:00:27,873 - mmseg - INFO - Iter [63500/80000] lr: 2.962e-07, eta: 4:27:51, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6007, decode.acc_seg: 67.1475, aux.loss_ce: 0.2740, aux.acc_seg: 65.6952, loss: 0.8747 2022-04-19 17:01:14,529 - mmseg - INFO - Iter [63550/80000] lr: 2.953e-07, eta: 4:27:02, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6106, decode.acc_seg: 66.6887, aux.loss_ce: 0.2786, aux.acc_seg: 65.1189, loss: 0.8892 2022-04-19 17:02:00,789 - mmseg - INFO - Iter [63600/80000] lr: 2.944e-07, eta: 4:26:12, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6336, decode.acc_seg: 64.3066, aux.loss_ce: 0.2893, aux.acc_seg: 62.8978, loss: 0.9228 2022-04-19 17:02:47,063 - mmseg - INFO - Iter [63650/80000] lr: 2.935e-07, eta: 4:25:23, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6167, decode.acc_seg: 65.3637, aux.loss_ce: 0.2759, aux.acc_seg: 64.2208, loss: 0.8926 2022-04-19 17:03:33,342 - mmseg - INFO - Iter [63700/80000] lr: 2.926e-07, eta: 4:24:34, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6080, decode.acc_seg: 66.6931, aux.loss_ce: 0.2748, aux.acc_seg: 65.2695, loss: 0.8828 2022-04-19 17:04:19,599 - mmseg - INFO - Iter [63750/80000] lr: 2.917e-07, eta: 4:23:44, time: 0.927, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6317, decode.acc_seg: 64.5605, aux.loss_ce: 0.2858, aux.acc_seg: 63.3675, loss: 0.9175 2022-04-19 17:05:05,973 - mmseg - INFO - Iter [63800/80000] lr: 2.908e-07, eta: 4:22:55, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6470, decode.acc_seg: 65.3566, aux.loss_ce: 0.2942, aux.acc_seg: 63.7099, loss: 0.9412 2022-04-19 17:05:52,726 - mmseg - INFO - Iter [63850/80000] lr: 2.899e-07, eta: 4:22:06, time: 0.937, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6179, decode.acc_seg: 66.0893, aux.loss_ce: 0.2830, aux.acc_seg: 64.4485, loss: 0.9009 2022-04-19 17:06:39,175 - mmseg - INFO - Iter [63900/80000] lr: 2.890e-07, eta: 4:21:17, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6190, decode.acc_seg: 65.1182, aux.loss_ce: 0.2832, aux.acc_seg: 63.6191, loss: 0.9023 2022-04-19 17:07:25,813 - mmseg - INFO - Iter [63950/80000] lr: 2.881e-07, eta: 4:20:27, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6415, decode.acc_seg: 65.5295, aux.loss_ce: 0.2948, aux.acc_seg: 64.2993, loss: 0.9364 2022-04-19 17:08:12,372 - mmseg - INFO - Saving checkpoint at 64000 iterations 2022-04-19 17:08:23,797 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 17:08:23,797 - mmseg - INFO - Iter [64000/80000] lr: 2.872e-07, eta: 4:19:41, time: 1.160, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6518, decode.acc_seg: 64.0785, aux.loss_ce: 0.2917, aux.acc_seg: 62.9400, loss: 0.9434 2022-04-19 17:12:18,122 - mmseg - INFO - per class results: 2022-04-19 17:12:18,149 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.81 | 95.56 | | bicycle | 71.89 | 86.22 | | car | 67.36 | 86.91 | | motorcycle | 84.97 | 92.97 | | airplane | 79.3 | 93.35 | | bus | 85.79 | 93.48 | | train | 87.16 | 95.64 | | truck | 68.48 | 84.9 | | boat | 67.82 | 84.8 | | traffic light | 68.07 | 87.62 | | fire hydrant | 88.03 | 97.38 | | stop sign | 89.54 | 98.56 | | parking meter | 79.88 | 87.75 | | bench | 56.78 | 75.76 | | bird | 81.55 | 92.87 | | cat | 81.53 | 89.82 | | dog | 78.78 | 87.57 | | horse | 86.86 | 95.84 | | sheep | 87.22 | 97.02 | | cow | 88.03 | 93.44 | | elephant | 91.76 | 97.8 | | bear | 91.88 | 97.21 | | zebra | 91.98 | 97.47 | | giraffe | 86.28 | 95.97 | | backpack | 41.12 | 66.61 | | umbrella | 86.84 | 95.44 | | handbag | 39.95 | 58.37 | | tie | 5.77 | 7.48 | | suitcase | 82.19 | 94.32 | | frisbee | 81.07 | 90.3 | | skis | 48.37 | 60.38 | | snowboard | 66.65 | 77.51 | | sports ball | 61.41 | 72.05 | | kite | 72.28 | 90.2 | | baseball bat | 56.79 | 77.33 | | baseball glove | 73.58 | 88.8 | | skateboard | 81.61 | 89.64 | | surfboard | 82.76 | 90.35 | | tennis racket | 85.41 | 93.3 | | bottle | 52.33 | 68.68 | | wine glass | 59.84 | 82.15 | | cup | 56.06 | 78.26 | | fork | 46.76 | 61.38 | | knife | 40.49 | 55.4 | | spoon | 41.02 | 58.17 | | bowl | 48.2 | 63.26 | | banana | 72.17 | 93.65 | | apple | 56.27 | 77.02 | | sandwich | 51.26 | 71.3 | | orange | 72.07 | 84.4 | | broccoli | 57.78 | 82.24 | | carrot | 57.52 | 79.5 | | hot dog | 54.35 | 65.42 | | pizza | 76.25 | 93.89 | | donut | 78.75 | 93.18 | | cake | 66.64 | 82.24 | | chair | 52.38 | 73.9 | | couch | 57.86 | 83.58 | | potted plant | 33.45 | 55.63 | | bed | 67.22 | 81.82 | | dining table | 46.84 | 69.89 | | toilet | 81.14 | 95.52 | | tv | 75.99 | 88.49 | | laptop | 78.21 | 94.29 | | mouse | 77.15 | 88.33 | | remote | 58.8 | 76.53 | | keyboard | 63.73 | 75.25 | | cell phone | 74.71 | 87.41 | | microwave | 68.09 | 83.07 | | oven | 58.32 | 86.26 | | toaster | 80.96 | 84.31 | | sink | 65.56 | 82.85 | | refrigerator | 77.22 | 93.15 | | book | 53.7 | 76.18 | | clock | 68.61 | 82.68 | | vase | 62.38 | 87.6 | | scissors | 73.42 | 95.64 | | teddy bear | 80.18 | 93.42 | | hair drier | 54.84 | 57.3 | | toothbrush | 50.78 | 69.76 | | banner | 31.89 | 68.1 | | blanket | 8.72 | 10.9 | | branch | 11.46 | 16.25 | | bridge | 43.57 | 64.39 | | building-other | 55.24 | 69.8 | | bush | 34.6 | 45.81 | | cabinet | 57.39 | 78.78 | | cage | 28.81 | 44.77 | | cardboard | 51.76 | 65.86 | | carpet | 54.68 | 76.36 | | ceiling-other | 66.02 | 85.43 | | ceiling-tile | 8.27 | 8.77 | | cloth | 3.48 | 3.92 | | clothes | 17.77 | 21.27 | | clouds | 51.14 | 69.64 | | counter | 31.09 | 55.22 | | cupboard | 0.0 | 0.0 | | curtain | 66.86 | 83.2 | | desk-stuff | 44.06 | 61.42 | | dirt | 42.77 | 67.29 | | door-stuff | 46.29 | 72.75 | | fence | 33.72 | 53.75 | | floor-marble | 7.33 | 8.24 | | floor-other | 23.99 | 32.22 | | floor-stone | 3.65 | 4.74 | | floor-tile | 61.85 | 75.79 | | floor-wood | 67.19 | 81.82 | | flower | 39.53 | 60.2 | | fog | 17.92 | 20.76 | | food-other | 31.31 | 42.11 | | fruit | 45.17 | 58.9 | | furniture-other | 16.22 | 19.75 | | grass | 71.36 | 84.91 | | gravel | 25.15 | 33.13 | | ground-other | 4.76 | 5.78 | | hill | 12.14 | 15.38 | | house | 28.21 | 34.24 | | leaves | 27.81 | 37.47 | | light | 42.17 | 56.63 | | mat | 0.0 | 0.0 | | metal | 31.85 | 42.19 | | mirror-stuff | 56.92 | 81.17 | | moss | 0.0 | 0.0 | | mountain | 54.42 | 77.14 | | mud | 5.9 | 8.82 | | napkin | 15.44 | 22.69 | | net | 51.82 | 67.29 | | paper | 33.0 | 46.16 | | pavement | 51.41 | 65.26 | | pillow | 10.47 | 14.04 | | plant-other | 17.45 | 26.48 | | plastic | 25.65 | 33.66 | | platform | 28.41 | 51.51 | | playingfield | 68.48 | 86.84 | | railing | 6.78 | 9.44 | | railroad | 59.39 | 85.73 | | river | 46.44 | 68.66 | | road | 66.26 | 86.89 | | rock | 44.13 | 70.38 | | roof | 22.78 | 29.29 | | rug | 37.32 | 58.34 | | salad | 2.65 | 2.85 | | sand | 66.44 | 72.77 | | sea | 84.51 | 92.32 | | shelf | 36.68 | 54.31 | | sky-other | 72.66 | 85.79 | | skyscraper | 40.95 | 54.6 | | snow | 90.6 | 95.47 | | solid-other | 0.0 | 0.0 | | stairs | 29.3 | 57.08 | | stone | 3.89 | 4.4 | | straw | 34.16 | 45.21 | | structural-other | 0.29 | 0.29 | | table | 23.46 | 32.17 | | tent | 9.09 | 11.77 | | textile-other | 15.75 | 25.01 | | towel | 33.65 | 43.58 | | tree | 73.36 | 88.46 | | vegetable | 43.36 | 59.43 | | wall-brick | 47.6 | 69.82 | | wall-concrete | 61.38 | 79.63 | | wall-other | 21.66 | 32.11 | | wall-panel | 4.59 | 5.24 | | wall-stone | 27.1 | 34.85 | | wall-tile | 68.86 | 88.08 | | wall-wood | 43.01 | 57.99 | | water-other | 24.12 | 33.11 | | waterdrops | 0.0 | 0.0 | | window-blind | 53.48 | 64.71 | | window-other | 48.82 | 74.96 | | wood | 28.26 | 42.75 | +------------------+-------+-------+ 2022-04-19 17:12:18,149 - mmseg - INFO - Summary: 2022-04-19 17:12:18,149 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 73.27 | 50.31 | 63.44 | +-------+-------+-------+ 2022-04-19 17:12:18,165 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 17:12:18,166 - mmseg - INFO - Iter(val) [625] aAcc: 0.7327, mIoU: 0.5031, mAcc: 0.6344, IoU.person: 0.8681, IoU.bicycle: 0.7189, IoU.car: 0.6736, IoU.motorcycle: 0.8497, IoU.airplane: 0.7930, IoU.bus: 0.8579, IoU.train: 0.8716, IoU.truck: 0.6848, IoU.boat: 0.6782, IoU.traffic light: 0.6807, IoU.fire hydrant: 0.8803, IoU.stop sign: 0.8954, IoU.parking meter: 0.7988, IoU.bench: 0.5678, IoU.bird: 0.8155, IoU.cat: 0.8153, IoU.dog: 0.7878, IoU.horse: 0.8686, IoU.sheep: 0.8722, IoU.cow: 0.8803, IoU.elephant: 0.9176, IoU.bear: 0.9188, IoU.zebra: 0.9198, IoU.giraffe: 0.8628, IoU.backpack: 0.4112, IoU.umbrella: 0.8684, IoU.handbag: 0.3995, IoU.tie: 0.0577, IoU.suitcase: 0.8219, IoU.frisbee: 0.8107, IoU.skis: 0.4837, IoU.snowboard: 0.6665, IoU.sports ball: 0.6141, IoU.kite: 0.7228, IoU.baseball bat: 0.5679, IoU.baseball glove: 0.7358, IoU.skateboard: 0.8161, IoU.surfboard: 0.8276, IoU.tennis racket: 0.8541, IoU.bottle: 0.5233, IoU.wine glass: 0.5984, IoU.cup: 0.5606, IoU.fork: 0.4676, IoU.knife: 0.4049, IoU.spoon: 0.4102, IoU.bowl: 0.4820, IoU.banana: 0.7217, IoU.apple: 0.5627, IoU.sandwich: 0.5126, IoU.orange: 0.7207, IoU.broccoli: 0.5778, IoU.carrot: 0.5752, IoU.hot dog: 0.5435, IoU.pizza: 0.7625, IoU.donut: 0.7875, IoU.cake: 0.6664, IoU.chair: 0.5238, IoU.couch: 0.5786, IoU.potted plant: 0.3345, IoU.bed: 0.6722, IoU.dining table: 0.4684, IoU.toilet: 0.8114, IoU.tv: 0.7599, IoU.laptop: 0.7821, IoU.mouse: 0.7715, IoU.remote: 0.5880, IoU.keyboard: 0.6373, IoU.cell phone: 0.7471, IoU.microwave: 0.6809, IoU.oven: 0.5832, IoU.toaster: 0.8096, IoU.sink: 0.6556, IoU.refrigerator: 0.7722, IoU.book: 0.5370, IoU.clock: 0.6861, IoU.vase: 0.6238, IoU.scissors: 0.7342, IoU.teddy bear: 0.8018, IoU.hair drier: 0.5484, IoU.toothbrush: 0.5078, IoU.banner: 0.3189, IoU.blanket: 0.0872, IoU.branch: 0.1146, IoU.bridge: 0.4357, IoU.building-other: 0.5524, IoU.bush: 0.3460, IoU.cabinet: 0.5739, IoU.cage: 0.2881, IoU.cardboard: 0.5176, IoU.carpet: 0.5468, IoU.ceiling-other: 0.6602, IoU.ceiling-tile: 0.0827, IoU.cloth: 0.0348, IoU.clothes: 0.1777, IoU.clouds: 0.5114, IoU.counter: 0.3109, IoU.cupboard: 0.0000, IoU.curtain: 0.6686, IoU.desk-stuff: 0.4406, IoU.dirt: 0.4277, IoU.door-stuff: 0.4629, IoU.fence: 0.3372, IoU.floor-marble: 0.0733, IoU.floor-other: 0.2399, IoU.floor-stone: 0.0365, IoU.floor-tile: 0.6185, IoU.floor-wood: 0.6719, IoU.flower: 0.3953, IoU.fog: 0.1792, IoU.food-other: 0.3131, IoU.fruit: 0.4517, IoU.furniture-other: 0.1622, IoU.grass: 0.7136, IoU.gravel: 0.2515, IoU.ground-other: 0.0476, IoU.hill: 0.1214, IoU.house: 0.2821, IoU.leaves: 0.2781, IoU.light: 0.4217, IoU.mat: 0.0000, IoU.metal: 0.3185, IoU.mirror-stuff: 0.5692, IoU.moss: 0.0000, IoU.mountain: 0.5442, IoU.mud: 0.0590, IoU.napkin: 0.1544, IoU.net: 0.5182, IoU.paper: 0.3300, IoU.pavement: 0.5141, IoU.pillow: 0.1047, IoU.plant-other: 0.1745, IoU.plastic: 0.2565, IoU.platform: 0.2841, IoU.playingfield: 0.6848, IoU.railing: 0.0678, IoU.railroad: 0.5939, IoU.river: 0.4644, IoU.road: 0.6626, IoU.rock: 0.4413, IoU.roof: 0.2278, IoU.rug: 0.3732, IoU.salad: 0.0265, IoU.sand: 0.6644, IoU.sea: 0.8451, IoU.shelf: 0.3668, IoU.sky-other: 0.7266, IoU.skyscraper: 0.4095, IoU.snow: 0.9060, IoU.solid-other: 0.0000, IoU.stairs: 0.2930, IoU.stone: 0.0389, IoU.straw: 0.3416, IoU.structural-other: 0.0029, IoU.table: 0.2346, IoU.tent: 0.0909, IoU.textile-other: 0.1575, IoU.towel: 0.3365, IoU.tree: 0.7336, IoU.vegetable: 0.4336, IoU.wall-brick: 0.4760, IoU.wall-concrete: 0.6138, IoU.wall-other: 0.2166, IoU.wall-panel: 0.0459, IoU.wall-stone: 0.2710, IoU.wall-tile: 0.6886, IoU.wall-wood: 0.4301, IoU.water-other: 0.2412, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5348, IoU.window-other: 0.4882, IoU.wood: 0.2826, Acc.person: 0.9556, Acc.bicycle: 0.8622, Acc.car: 0.8691, Acc.motorcycle: 0.9297, Acc.airplane: 0.9335, Acc.bus: 0.9348, Acc.train: 0.9564, Acc.truck: 0.8490, Acc.boat: 0.8480, Acc.traffic light: 0.8762, Acc.fire hydrant: 0.9738, Acc.stop sign: 0.9856, Acc.parking meter: 0.8775, Acc.bench: 0.7576, Acc.bird: 0.9287, Acc.cat: 0.8982, Acc.dog: 0.8757, Acc.horse: 0.9584, Acc.sheep: 0.9702, Acc.cow: 0.9344, Acc.elephant: 0.9780, Acc.bear: 0.9721, Acc.zebra: 0.9747, Acc.giraffe: 0.9597, Acc.backpack: 0.6661, Acc.umbrella: 0.9544, Acc.handbag: 0.5837, Acc.tie: 0.0748, Acc.suitcase: 0.9432, Acc.frisbee: 0.9030, Acc.skis: 0.6038, Acc.snowboard: 0.7751, Acc.sports ball: 0.7205, Acc.kite: 0.9020, Acc.baseball bat: 0.7733, Acc.baseball glove: 0.8880, Acc.skateboard: 0.8964, Acc.surfboard: 0.9035, Acc.tennis racket: 0.9330, Acc.bottle: 0.6868, Acc.wine glass: 0.8215, Acc.cup: 0.7826, Acc.fork: 0.6138, Acc.knife: 0.5540, Acc.spoon: 0.5817, Acc.bowl: 0.6326, Acc.banana: 0.9365, Acc.apple: 0.7702, Acc.sandwich: 0.7130, Acc.orange: 0.8440, Acc.broccoli: 0.8224, Acc.carrot: 0.7950, Acc.hot dog: 0.6542, Acc.pizza: 0.9389, Acc.donut: 0.9318, Acc.cake: 0.8224, Acc.chair: 0.7390, Acc.couch: 0.8358, Acc.potted plant: 0.5563, Acc.bed: 0.8182, Acc.dining table: 0.6989, Acc.toilet: 0.9552, Acc.tv: 0.8849, Acc.laptop: 0.9429, Acc.mouse: 0.8833, Acc.remote: 0.7653, Acc.keyboard: 0.7525, Acc.cell phone: 0.8741, Acc.microwave: 0.8307, Acc.oven: 0.8626, Acc.toaster: 0.8431, Acc.sink: 0.8285, Acc.refrigerator: 0.9315, Acc.book: 0.7618, Acc.clock: 0.8268, Acc.vase: 0.8760, Acc.scissors: 0.9564, Acc.teddy bear: 0.9342, Acc.hair drier: 0.5730, Acc.toothbrush: 0.6976, Acc.banner: 0.6810, Acc.blanket: 0.1090, Acc.branch: 0.1625, Acc.bridge: 0.6439, Acc.building-other: 0.6980, Acc.bush: 0.4581, Acc.cabinet: 0.7878, Acc.cage: 0.4477, Acc.cardboard: 0.6586, Acc.carpet: 0.7636, Acc.ceiling-other: 0.8543, Acc.ceiling-tile: 0.0877, Acc.cloth: 0.0392, Acc.clothes: 0.2127, Acc.clouds: 0.6964, Acc.counter: 0.5522, Acc.cupboard: 0.0000, Acc.curtain: 0.8320, Acc.desk-stuff: 0.6142, Acc.dirt: 0.6729, Acc.door-stuff: 0.7275, Acc.fence: 0.5375, Acc.floor-marble: 0.0824, Acc.floor-other: 0.3222, Acc.floor-stone: 0.0474, Acc.floor-tile: 0.7579, Acc.floor-wood: 0.8182, Acc.flower: 0.6020, Acc.fog: 0.2076, Acc.food-other: 0.4211, Acc.fruit: 0.5890, Acc.furniture-other: 0.1975, Acc.grass: 0.8491, Acc.gravel: 0.3313, Acc.ground-other: 0.0578, Acc.hill: 0.1538, Acc.house: 0.3424, Acc.leaves: 0.3747, Acc.light: 0.5663, Acc.mat: 0.0000, Acc.metal: 0.4219, Acc.mirror-stuff: 0.8117, Acc.moss: 0.0000, Acc.mountain: 0.7714, Acc.mud: 0.0882, Acc.napkin: 0.2269, Acc.net: 0.6729, Acc.paper: 0.4616, Acc.pavement: 0.6526, Acc.pillow: 0.1404, Acc.plant-other: 0.2648, Acc.plastic: 0.3366, Acc.platform: 0.5151, Acc.playingfield: 0.8684, Acc.railing: 0.0944, Acc.railroad: 0.8573, Acc.river: 0.6866, Acc.road: 0.8689, Acc.rock: 0.7038, Acc.roof: 0.2929, Acc.rug: 0.5834, Acc.salad: 0.0285, Acc.sand: 0.7277, Acc.sea: 0.9232, Acc.shelf: 0.5431, Acc.sky-other: 0.8579, Acc.skyscraper: 0.5460, Acc.snow: 0.9547, Acc.solid-other: 0.0000, Acc.stairs: 0.5708, Acc.stone: 0.0440, Acc.straw: 0.4521, Acc.structural-other: 0.0029, Acc.table: 0.3217, Acc.tent: 0.1177, Acc.textile-other: 0.2501, Acc.towel: 0.4358, Acc.tree: 0.8846, Acc.vegetable: 0.5943, Acc.wall-brick: 0.6982, Acc.wall-concrete: 0.7963, Acc.wall-other: 0.3211, Acc.wall-panel: 0.0524, Acc.wall-stone: 0.3485, Acc.wall-tile: 0.8808, Acc.wall-wood: 0.5799, Acc.water-other: 0.3311, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6471, Acc.window-other: 0.7496, Acc.wood: 0.4275 2022-04-19 17:13:04,984 - mmseg - INFO - Iter [64050/80000] lr: 2.863e-07, eta: 4:19:50, time: 5.624, data_time: 4.692, memory: 73037, decode.loss_ce: 0.6289, decode.acc_seg: 63.7702, aux.loss_ce: 0.2892, aux.acc_seg: 62.3126, loss: 0.9181 2022-04-19 17:13:51,649 - mmseg - INFO - Iter [64100/80000] lr: 2.854e-07, eta: 4:19:01, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6263, decode.acc_seg: 65.8770, aux.loss_ce: 0.2850, aux.acc_seg: 64.5817, loss: 0.9113 2022-04-19 17:14:37,701 - mmseg - INFO - Iter [64150/80000] lr: 2.845e-07, eta: 4:18:11, time: 0.922, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6131, decode.acc_seg: 65.7269, aux.loss_ce: 0.2839, aux.acc_seg: 63.9990, loss: 0.8971 2022-04-19 17:15:24,133 - mmseg - INFO - Iter [64200/80000] lr: 2.836e-07, eta: 4:17:22, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6477, decode.acc_seg: 64.9502, aux.loss_ce: 0.3015, aux.acc_seg: 63.2883, loss: 0.9492 2022-04-19 17:16:10,780 - mmseg - INFO - Iter [64250/80000] lr: 2.827e-07, eta: 4:16:32, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6282, decode.acc_seg: 66.0043, aux.loss_ce: 0.2866, aux.acc_seg: 64.8141, loss: 0.9148 2022-04-19 17:16:57,764 - mmseg - INFO - Iter [64300/80000] lr: 2.818e-07, eta: 4:15:43, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6496, decode.acc_seg: 65.5998, aux.loss_ce: 0.2967, aux.acc_seg: 64.1048, loss: 0.9463 2022-04-19 17:17:44,304 - mmseg - INFO - Iter [64350/80000] lr: 2.809e-07, eta: 4:14:54, time: 0.933, data_time: 0.008, memory: 73037, decode.loss_ce: 0.5951, decode.acc_seg: 65.2830, aux.loss_ce: 0.2759, aux.acc_seg: 64.0060, loss: 0.8710 2022-04-19 17:18:30,677 - mmseg - INFO - Iter [64400/80000] lr: 2.800e-07, eta: 4:14:04, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6309, decode.acc_seg: 65.9300, aux.loss_ce: 0.2889, aux.acc_seg: 64.4785, loss: 0.9198 2022-04-19 17:19:16,892 - mmseg - INFO - Iter [64450/80000] lr: 2.791e-07, eta: 4:13:15, time: 0.926, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6409, decode.acc_seg: 66.2619, aux.loss_ce: 0.2905, aux.acc_seg: 65.0117, loss: 0.9315 2022-04-19 17:20:04,279 - mmseg - INFO - Iter [64500/80000] lr: 2.782e-07, eta: 4:12:25, time: 0.948, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6465, decode.acc_seg: 64.1171, aux.loss_ce: 0.2926, aux.acc_seg: 62.9452, loss: 0.9391 2022-04-19 17:20:50,781 - mmseg - INFO - Iter [64550/80000] lr: 2.773e-07, eta: 4:11:36, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6380, decode.acc_seg: 64.7215, aux.loss_ce: 0.2895, aux.acc_seg: 63.2486, loss: 0.9275 2022-04-19 17:21:37,562 - mmseg - INFO - Iter [64600/80000] lr: 2.764e-07, eta: 4:10:47, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6399, decode.acc_seg: 64.5823, aux.loss_ce: 0.2925, aux.acc_seg: 63.0938, loss: 0.9324 2022-04-19 17:22:24,116 - mmseg - INFO - Iter [64650/80000] lr: 2.755e-07, eta: 4:09:57, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6369, decode.acc_seg: 64.9555, aux.loss_ce: 0.2867, aux.acc_seg: 63.6370, loss: 0.9236 2022-04-19 17:23:10,342 - mmseg - INFO - Iter [64700/80000] lr: 2.746e-07, eta: 4:09:08, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6187, decode.acc_seg: 64.6325, aux.loss_ce: 0.2848, aux.acc_seg: 63.0819, loss: 0.9034 2022-04-19 17:23:56,791 - mmseg - INFO - Iter [64750/80000] lr: 2.737e-07, eta: 4:08:18, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6246, decode.acc_seg: 65.5923, aux.loss_ce: 0.2845, aux.acc_seg: 64.1327, loss: 0.9091 2022-04-19 17:24:43,340 - mmseg - INFO - Iter [64800/80000] lr: 2.728e-07, eta: 4:07:29, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6433, decode.acc_seg: 65.3927, aux.loss_ce: 0.2886, aux.acc_seg: 64.5151, loss: 0.9319 2022-04-19 17:25:29,828 - mmseg - INFO - Iter [64850/80000] lr: 2.719e-07, eta: 4:06:40, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6373, decode.acc_seg: 65.8865, aux.loss_ce: 0.2859, aux.acc_seg: 64.8927, loss: 0.9232 2022-04-19 17:26:16,353 - mmseg - INFO - Iter [64900/80000] lr: 2.710e-07, eta: 4:05:50, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6358, decode.acc_seg: 65.4947, aux.loss_ce: 0.2927, aux.acc_seg: 64.0456, loss: 0.9285 2022-04-19 17:27:03,183 - mmseg - INFO - Iter [64950/80000] lr: 2.701e-07, eta: 4:05:01, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6147, decode.acc_seg: 64.6467, aux.loss_ce: 0.2774, aux.acc_seg: 63.4485, loss: 0.8921 2022-04-19 17:27:49,586 - mmseg - INFO - Saving checkpoint at 65000 iterations 2022-04-19 17:28:00,735 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 17:28:00,736 - mmseg - INFO - Iter [65000/80000] lr: 2.692e-07, eta: 4:04:14, time: 1.151, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6330, decode.acc_seg: 65.2885, aux.loss_ce: 0.2853, aux.acc_seg: 64.2062, loss: 0.9183 2022-04-19 17:28:47,307 - mmseg - INFO - Iter [65050/80000] lr: 2.683e-07, eta: 4:03:25, time: 0.931, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6169, decode.acc_seg: 66.0192, aux.loss_ce: 0.2816, aux.acc_seg: 64.6103, loss: 0.8984 2022-04-19 17:29:33,725 - mmseg - INFO - Iter [65100/80000] lr: 2.674e-07, eta: 4:02:35, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5991, decode.acc_seg: 65.3076, aux.loss_ce: 0.2767, aux.acc_seg: 63.8351, loss: 0.8758 2022-04-19 17:30:20,197 - mmseg - INFO - Iter [65150/80000] lr: 2.665e-07, eta: 4:01:46, time: 0.932, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6074, decode.acc_seg: 65.9690, aux.loss_ce: 0.2752, aux.acc_seg: 64.6548, loss: 0.8826 2022-04-19 17:31:06,440 - mmseg - INFO - Iter [65200/80000] lr: 2.656e-07, eta: 4:00:56, time: 0.923, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6312, decode.acc_seg: 64.6912, aux.loss_ce: 0.2860, aux.acc_seg: 63.6407, loss: 0.9172 2022-04-19 17:31:52,533 - mmseg - INFO - Iter [65250/80000] lr: 2.647e-07, eta: 4:00:07, time: 0.924, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6375, decode.acc_seg: 65.1083, aux.loss_ce: 0.2887, aux.acc_seg: 64.1160, loss: 0.9262 2022-04-19 17:32:38,967 - mmseg - INFO - Iter [65300/80000] lr: 2.638e-07, eta: 3:59:18, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6322, decode.acc_seg: 63.8963, aux.loss_ce: 0.2875, aux.acc_seg: 62.7004, loss: 0.9198 2022-04-19 17:33:25,418 - mmseg - INFO - Iter [65350/80000] lr: 2.629e-07, eta: 3:58:28, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6228, decode.acc_seg: 65.8355, aux.loss_ce: 0.2825, aux.acc_seg: 64.6486, loss: 0.9053 2022-04-19 17:34:11,983 - mmseg - INFO - Iter [65400/80000] lr: 2.621e-07, eta: 3:57:39, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6107, decode.acc_seg: 65.7415, aux.loss_ce: 0.2723, aux.acc_seg: 64.5951, loss: 0.8830 2022-04-19 17:34:58,355 - mmseg - INFO - Iter [65450/80000] lr: 2.612e-07, eta: 3:56:49, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6493, decode.acc_seg: 65.8388, aux.loss_ce: 0.2933, aux.acc_seg: 64.6153, loss: 0.9426 2022-04-19 17:35:44,760 - mmseg - INFO - Iter [65500/80000] lr: 2.603e-07, eta: 3:56:00, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6249, decode.acc_seg: 66.2201, aux.loss_ce: 0.2833, aux.acc_seg: 64.9475, loss: 0.9081 2022-04-19 17:36:31,096 - mmseg - INFO - Iter [65550/80000] lr: 2.594e-07, eta: 3:55:11, time: 0.928, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6645, decode.acc_seg: 64.9701, aux.loss_ce: 0.2968, aux.acc_seg: 63.9740, loss: 0.9613 2022-04-19 17:37:17,628 - mmseg - INFO - Iter [65600/80000] lr: 2.585e-07, eta: 3:54:21, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6223, decode.acc_seg: 66.1610, aux.loss_ce: 0.2819, aux.acc_seg: 64.8569, loss: 0.9043 2022-04-19 17:38:04,162 - mmseg - INFO - Iter [65650/80000] lr: 2.576e-07, eta: 3:53:32, time: 0.932, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6365, decode.acc_seg: 64.8943, aux.loss_ce: 0.2873, aux.acc_seg: 63.4567, loss: 0.9238 2022-04-19 17:38:50,716 - mmseg - INFO - Iter [65700/80000] lr: 2.567e-07, eta: 3:52:43, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5950, decode.acc_seg: 65.9001, aux.loss_ce: 0.2738, aux.acc_seg: 64.0192, loss: 0.8688 2022-04-19 17:39:37,033 - mmseg - INFO - Iter [65750/80000] lr: 2.558e-07, eta: 3:51:53, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6012, decode.acc_seg: 65.6083, aux.loss_ce: 0.2743, aux.acc_seg: 64.4891, loss: 0.8755 2022-04-19 17:40:23,467 - mmseg - INFO - Iter [65800/80000] lr: 2.549e-07, eta: 3:51:04, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6112, decode.acc_seg: 65.0608, aux.loss_ce: 0.2749, aux.acc_seg: 63.5974, loss: 0.8861 2022-04-19 17:41:10,064 - mmseg - INFO - Iter [65850/80000] lr: 2.540e-07, eta: 3:50:15, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6152, decode.acc_seg: 65.2261, aux.loss_ce: 0.2792, aux.acc_seg: 64.1179, loss: 0.8944 2022-04-19 17:41:56,881 - mmseg - INFO - Iter [65900/80000] lr: 2.531e-07, eta: 3:49:26, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6424, decode.acc_seg: 65.4106, aux.loss_ce: 0.2915, aux.acc_seg: 63.9734, loss: 0.9339 2022-04-19 17:42:43,425 - mmseg - INFO - Iter [65950/80000] lr: 2.522e-07, eta: 3:48:36, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6404, decode.acc_seg: 65.3492, aux.loss_ce: 0.2935, aux.acc_seg: 63.9816, loss: 0.9339 2022-04-19 17:43:29,646 - mmseg - INFO - Saving checkpoint at 66000 iterations 2022-04-19 17:43:40,019 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 17:43:40,020 - mmseg - INFO - Iter [66000/80000] lr: 2.513e-07, eta: 3:47:49, time: 1.132, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6703, decode.acc_seg: 65.5109, aux.loss_ce: 0.3041, aux.acc_seg: 64.1928, loss: 0.9744 2022-04-19 17:44:26,756 - mmseg - INFO - Iter [66050/80000] lr: 2.504e-07, eta: 3:47:00, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6272, decode.acc_seg: 64.2983, aux.loss_ce: 0.2900, aux.acc_seg: 62.5481, loss: 0.9172 2022-04-19 17:45:13,504 - mmseg - INFO - Iter [66100/80000] lr: 2.495e-07, eta: 3:46:11, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6659, decode.acc_seg: 64.3978, aux.loss_ce: 0.3051, aux.acc_seg: 62.8675, loss: 0.9711 2022-04-19 17:46:00,107 - mmseg - INFO - Iter [66150/80000] lr: 2.486e-07, eta: 3:45:21, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6609, decode.acc_seg: 65.4464, aux.loss_ce: 0.2984, aux.acc_seg: 64.1292, loss: 0.9592 2022-04-19 17:46:46,619 - mmseg - INFO - Iter [66200/80000] lr: 2.477e-07, eta: 3:44:32, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6345, decode.acc_seg: 65.7038, aux.loss_ce: 0.2871, aux.acc_seg: 64.6115, loss: 0.9216 2022-04-19 17:47:33,562 - mmseg - INFO - Iter [66250/80000] lr: 2.468e-07, eta: 3:43:43, time: 0.939, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6096, decode.acc_seg: 65.8105, aux.loss_ce: 0.2751, aux.acc_seg: 64.7234, loss: 0.8847 2022-04-19 17:48:19,943 - mmseg - INFO - Iter [66300/80000] lr: 2.459e-07, eta: 3:42:53, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6263, decode.acc_seg: 66.2829, aux.loss_ce: 0.2835, aux.acc_seg: 64.8975, loss: 0.9098 2022-04-19 17:49:06,205 - mmseg - INFO - Iter [66350/80000] lr: 2.450e-07, eta: 3:42:04, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6361, decode.acc_seg: 66.2118, aux.loss_ce: 0.2893, aux.acc_seg: 64.7319, loss: 0.9255 2022-04-19 17:49:52,339 - mmseg - INFO - Iter [66400/80000] lr: 2.441e-07, eta: 3:41:15, time: 0.923, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6418, decode.acc_seg: 66.0393, aux.loss_ce: 0.2945, aux.acc_seg: 64.5297, loss: 0.9363 2022-04-19 17:50:38,528 - mmseg - INFO - Iter [66450/80000] lr: 2.432e-07, eta: 3:40:25, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6219, decode.acc_seg: 65.5352, aux.loss_ce: 0.2840, aux.acc_seg: 64.1302, loss: 0.9059 2022-04-19 17:51:25,367 - mmseg - INFO - Iter [66500/80000] lr: 2.423e-07, eta: 3:39:36, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6362, decode.acc_seg: 66.1241, aux.loss_ce: 0.2961, aux.acc_seg: 64.1390, loss: 0.9323 2022-04-19 17:52:14,560 - mmseg - INFO - Iter [66550/80000] lr: 2.414e-07, eta: 3:38:47, time: 0.986, data_time: 0.056, memory: 73037, decode.loss_ce: 0.6268, decode.acc_seg: 65.3122, aux.loss_ce: 0.2874, aux.acc_seg: 63.7058, loss: 0.9142 2022-04-19 17:53:01,116 - mmseg - INFO - Iter [66600/80000] lr: 2.405e-07, eta: 3:37:58, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5922, decode.acc_seg: 65.2013, aux.loss_ce: 0.2721, aux.acc_seg: 63.6216, loss: 0.8643 2022-04-19 17:53:47,438 - mmseg - INFO - Iter [66650/80000] lr: 2.396e-07, eta: 3:37:09, time: 0.926, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6071, decode.acc_seg: 66.0877, aux.loss_ce: 0.2776, aux.acc_seg: 64.6983, loss: 0.8847 2022-04-19 17:54:33,995 - mmseg - INFO - Iter [66700/80000] lr: 2.387e-07, eta: 3:36:20, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6102, decode.acc_seg: 64.8972, aux.loss_ce: 0.2826, aux.acc_seg: 63.3634, loss: 0.8928 2022-04-19 17:55:20,810 - mmseg - INFO - Iter [66750/80000] lr: 2.378e-07, eta: 3:35:30, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6420, decode.acc_seg: 66.1095, aux.loss_ce: 0.2951, aux.acc_seg: 64.0042, loss: 0.9372 2022-04-19 17:56:07,521 - mmseg - INFO - Iter [66800/80000] lr: 2.369e-07, eta: 3:34:41, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5985, decode.acc_seg: 66.5841, aux.loss_ce: 0.2734, aux.acc_seg: 65.1866, loss: 0.8719 2022-04-19 17:56:54,316 - mmseg - INFO - Iter [66850/80000] lr: 2.360e-07, eta: 3:33:52, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6139, decode.acc_seg: 65.4987, aux.loss_ce: 0.2834, aux.acc_seg: 63.9872, loss: 0.8974 2022-04-19 17:57:40,535 - mmseg - INFO - Iter [66900/80000] lr: 2.351e-07, eta: 3:33:03, time: 0.926, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5909, decode.acc_seg: 65.5366, aux.loss_ce: 0.2756, aux.acc_seg: 63.7979, loss: 0.8665 2022-04-19 17:58:26,754 - mmseg - INFO - Iter [66950/80000] lr: 2.342e-07, eta: 3:32:14, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6181, decode.acc_seg: 63.9079, aux.loss_ce: 0.2853, aux.acc_seg: 62.3387, loss: 0.9034 2022-04-19 17:59:13,216 - mmseg - INFO - Saving checkpoint at 67000 iterations 2022-04-19 17:59:24,871 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 17:59:24,871 - mmseg - INFO - Iter [67000/80000] lr: 2.333e-07, eta: 3:31:27, time: 1.162, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6207, decode.acc_seg: 64.7552, aux.loss_ce: 0.2865, aux.acc_seg: 63.1370, loss: 0.9072 2022-04-19 18:00:13,086 - mmseg - INFO - Iter [67050/80000] lr: 2.324e-07, eta: 3:30:38, time: 0.964, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6312, decode.acc_seg: 64.3195, aux.loss_ce: 0.2887, aux.acc_seg: 62.9223, loss: 0.9199 2022-04-19 18:00:59,748 - mmseg - INFO - Iter [67100/80000] lr: 2.315e-07, eta: 3:29:48, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6121, decode.acc_seg: 65.0034, aux.loss_ce: 0.2788, aux.acc_seg: 63.4486, loss: 0.8909 2022-04-19 18:01:46,364 - mmseg - INFO - Iter [67150/80000] lr: 2.306e-07, eta: 3:28:59, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6481, decode.acc_seg: 65.6066, aux.loss_ce: 0.2933, aux.acc_seg: 64.0113, loss: 0.9414 2022-04-19 18:02:32,916 - mmseg - INFO - Iter [67200/80000] lr: 2.297e-07, eta: 3:28:10, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6209, decode.acc_seg: 64.8709, aux.loss_ce: 0.2826, aux.acc_seg: 63.4955, loss: 0.9035 2022-04-19 18:03:19,283 - mmseg - INFO - Iter [67250/80000] lr: 2.288e-07, eta: 3:27:21, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6286, decode.acc_seg: 64.6204, aux.loss_ce: 0.2886, aux.acc_seg: 62.8647, loss: 0.9172 2022-04-19 18:04:05,661 - mmseg - INFO - Iter [67300/80000] lr: 2.280e-07, eta: 3:26:31, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6114, decode.acc_seg: 66.7004, aux.loss_ce: 0.2820, aux.acc_seg: 65.4042, loss: 0.8934 2022-04-19 18:04:52,279 - mmseg - INFO - Iter [67350/80000] lr: 2.271e-07, eta: 3:25:42, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6264, decode.acc_seg: 65.6610, aux.loss_ce: 0.2879, aux.acc_seg: 64.3758, loss: 0.9143 2022-04-19 18:05:38,782 - mmseg - INFO - Iter [67400/80000] lr: 2.262e-07, eta: 3:24:53, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5999, decode.acc_seg: 66.8272, aux.loss_ce: 0.2746, aux.acc_seg: 65.5860, loss: 0.8746 2022-04-19 18:06:25,065 - mmseg - INFO - Iter [67450/80000] lr: 2.253e-07, eta: 3:24:04, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6209, decode.acc_seg: 65.1665, aux.loss_ce: 0.2839, aux.acc_seg: 64.1698, loss: 0.9048 2022-04-19 18:07:11,319 - mmseg - INFO - Iter [67500/80000] lr: 2.244e-07, eta: 3:23:15, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6404, decode.acc_seg: 65.3560, aux.loss_ce: 0.2943, aux.acc_seg: 63.6856, loss: 0.9347 2022-04-19 18:07:57,787 - mmseg - INFO - Iter [67550/80000] lr: 2.235e-07, eta: 3:22:25, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6199, decode.acc_seg: 65.4388, aux.loss_ce: 0.2857, aux.acc_seg: 63.7023, loss: 0.9056 2022-04-19 18:08:44,469 - mmseg - INFO - Iter [67600/80000] lr: 2.226e-07, eta: 3:21:36, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6237, decode.acc_seg: 65.9424, aux.loss_ce: 0.2875, aux.acc_seg: 64.2319, loss: 0.9113 2022-04-19 18:09:31,373 - mmseg - INFO - Iter [67650/80000] lr: 2.217e-07, eta: 3:20:47, time: 0.940, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6335, decode.acc_seg: 65.5374, aux.loss_ce: 0.2910, aux.acc_seg: 63.4024, loss: 0.9245 2022-04-19 18:10:18,134 - mmseg - INFO - Iter [67700/80000] lr: 2.208e-07, eta: 3:19:58, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6224, decode.acc_seg: 66.6457, aux.loss_ce: 0.2878, aux.acc_seg: 64.9637, loss: 0.9102 2022-04-19 18:11:04,529 - mmseg - INFO - Iter [67750/80000] lr: 2.199e-07, eta: 3:19:09, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6209, decode.acc_seg: 65.5320, aux.loss_ce: 0.2849, aux.acc_seg: 63.9889, loss: 0.9058 2022-04-19 18:11:51,130 - mmseg - INFO - Iter [67800/80000] lr: 2.190e-07, eta: 3:18:20, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6125, decode.acc_seg: 65.8083, aux.loss_ce: 0.2816, aux.acc_seg: 64.4355, loss: 0.8941 2022-04-19 18:12:37,367 - mmseg - INFO - Iter [67850/80000] lr: 2.181e-07, eta: 3:17:30, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6301, decode.acc_seg: 65.2222, aux.loss_ce: 0.2888, aux.acc_seg: 64.0440, loss: 0.9189 2022-04-19 18:13:23,796 - mmseg - INFO - Iter [67900/80000] lr: 2.172e-07, eta: 3:16:41, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6304, decode.acc_seg: 64.7943, aux.loss_ce: 0.2907, aux.acc_seg: 62.9910, loss: 0.9210 2022-04-19 18:14:10,638 - mmseg - INFO - Iter [67950/80000] lr: 2.163e-07, eta: 3:15:52, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6279, decode.acc_seg: 65.2753, aux.loss_ce: 0.2847, aux.acc_seg: 64.0441, loss: 0.9126 2022-04-19 18:14:57,232 - mmseg - INFO - Saving checkpoint at 68000 iterations 2022-04-19 18:15:10,890 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 18:15:10,905 - mmseg - INFO - Iter [68000/80000] lr: 2.154e-07, eta: 3:15:05, time: 1.200, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6225, decode.acc_seg: 64.9202, aux.loss_ce: 0.2894, aux.acc_seg: 63.2524, loss: 0.9118 2022-04-19 18:15:57,961 - mmseg - INFO - Iter [68050/80000] lr: 2.145e-07, eta: 3:14:16, time: 0.946, data_time: 0.012, memory: 73037, decode.loss_ce: 0.5973, decode.acc_seg: 65.0074, aux.loss_ce: 0.2748, aux.acc_seg: 63.1688, loss: 0.8721 2022-04-19 18:16:44,176 - mmseg - INFO - Iter [68100/80000] lr: 2.136e-07, eta: 3:13:27, time: 0.923, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6100, decode.acc_seg: 64.1727, aux.loss_ce: 0.2766, aux.acc_seg: 63.0747, loss: 0.8866 2022-04-19 18:17:30,305 - mmseg - INFO - Iter [68150/80000] lr: 2.127e-07, eta: 3:12:38, time: 0.924, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5974, decode.acc_seg: 66.2301, aux.loss_ce: 0.2780, aux.acc_seg: 64.7895, loss: 0.8754 2022-04-19 18:18:16,733 - mmseg - INFO - Iter [68200/80000] lr: 2.118e-07, eta: 3:11:49, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6302, decode.acc_seg: 66.9811, aux.loss_ce: 0.2877, aux.acc_seg: 65.4868, loss: 0.9179 2022-04-19 18:19:03,008 - mmseg - INFO - Iter [68250/80000] lr: 2.109e-07, eta: 3:10:59, time: 0.927, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6161, decode.acc_seg: 63.8698, aux.loss_ce: 0.2845, aux.acc_seg: 61.8864, loss: 0.9006 2022-04-19 18:19:49,630 - mmseg - INFO - Iter [68300/80000] lr: 2.100e-07, eta: 3:10:10, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5988, decode.acc_seg: 66.0066, aux.loss_ce: 0.2772, aux.acc_seg: 63.9877, loss: 0.8761 2022-04-19 18:20:35,941 - mmseg - INFO - Iter [68350/80000] lr: 2.091e-07, eta: 3:09:21, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6401, decode.acc_seg: 65.5134, aux.loss_ce: 0.2922, aux.acc_seg: 64.0376, loss: 0.9324 2022-04-19 18:21:22,927 - mmseg - INFO - Iter [68400/80000] lr: 2.082e-07, eta: 3:08:32, time: 0.940, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5931, decode.acc_seg: 66.0855, aux.loss_ce: 0.2708, aux.acc_seg: 64.6792, loss: 0.8638 2022-04-19 18:22:09,154 - mmseg - INFO - Iter [68450/80000] lr: 2.073e-07, eta: 3:07:43, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5845, decode.acc_seg: 66.6398, aux.loss_ce: 0.2719, aux.acc_seg: 64.7812, loss: 0.8564 2022-04-19 18:22:55,863 - mmseg - INFO - Iter [68500/80000] lr: 2.064e-07, eta: 3:06:54, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6290, decode.acc_seg: 65.7898, aux.loss_ce: 0.2866, aux.acc_seg: 64.2300, loss: 0.9156 2022-04-19 18:23:42,373 - mmseg - INFO - Iter [68550/80000] lr: 2.055e-07, eta: 3:06:05, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6408, decode.acc_seg: 65.6762, aux.loss_ce: 0.2937, aux.acc_seg: 64.2026, loss: 0.9345 2022-04-19 18:24:28,937 - mmseg - INFO - Iter [68600/80000] lr: 2.046e-07, eta: 3:05:16, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6234, decode.acc_seg: 65.2873, aux.loss_ce: 0.2866, aux.acc_seg: 63.6659, loss: 0.9100 2022-04-19 18:25:15,111 - mmseg - INFO - Iter [68650/80000] lr: 2.037e-07, eta: 3:04:26, time: 0.923, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6506, decode.acc_seg: 64.2253, aux.loss_ce: 0.3023, aux.acc_seg: 62.6904, loss: 0.9528 2022-04-19 18:26:01,251 - mmseg - INFO - Iter [68700/80000] lr: 2.028e-07, eta: 3:03:37, time: 0.923, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6229, decode.acc_seg: 64.9949, aux.loss_ce: 0.2826, aux.acc_seg: 64.1014, loss: 0.9056 2022-04-19 18:26:47,590 - mmseg - INFO - Iter [68750/80000] lr: 2.019e-07, eta: 3:02:48, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6083, decode.acc_seg: 67.0672, aux.loss_ce: 0.2831, aux.acc_seg: 65.8447, loss: 0.8914 2022-04-19 18:27:34,020 - mmseg - INFO - Iter [68800/80000] lr: 2.010e-07, eta: 3:01:59, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6273, decode.acc_seg: 66.2050, aux.loss_ce: 0.2833, aux.acc_seg: 64.8623, loss: 0.9106 2022-04-19 18:28:20,651 - mmseg - INFO - Iter [68850/80000] lr: 2.001e-07, eta: 3:01:10, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5981, decode.acc_seg: 66.6794, aux.loss_ce: 0.2757, aux.acc_seg: 65.0092, loss: 0.8738 2022-04-19 18:29:07,215 - mmseg - INFO - Iter [68900/80000] lr: 1.992e-07, eta: 3:00:21, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6448, decode.acc_seg: 64.9353, aux.loss_ce: 0.2944, aux.acc_seg: 63.1310, loss: 0.9392 2022-04-19 18:29:53,584 - mmseg - INFO - Iter [68950/80000] lr: 1.983e-07, eta: 2:59:32, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6663, decode.acc_seg: 64.4097, aux.loss_ce: 0.3034, aux.acc_seg: 63.1528, loss: 0.9697 2022-04-19 18:30:39,967 - mmseg - INFO - Saving checkpoint at 69000 iterations 2022-04-19 18:30:51,607 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 18:30:51,608 - mmseg - INFO - Iter [69000/80000] lr: 1.974e-07, eta: 2:58:44, time: 1.159, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6461, decode.acc_seg: 65.9732, aux.loss_ce: 0.2942, aux.acc_seg: 64.5657, loss: 0.9403 2022-04-19 18:31:38,065 - mmseg - INFO - Iter [69050/80000] lr: 1.965e-07, eta: 2:57:55, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6355, decode.acc_seg: 65.9340, aux.loss_ce: 0.2924, aux.acc_seg: 64.2650, loss: 0.9279 2022-04-19 18:32:24,414 - mmseg - INFO - Iter [69100/80000] lr: 1.956e-07, eta: 2:57:06, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6214, decode.acc_seg: 65.5947, aux.loss_ce: 0.2880, aux.acc_seg: 63.7278, loss: 0.9093 2022-04-19 18:33:10,739 - mmseg - INFO - Iter [69150/80000] lr: 1.947e-07, eta: 2:56:17, time: 0.928, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6509, decode.acc_seg: 64.4598, aux.loss_ce: 0.2969, aux.acc_seg: 63.1052, loss: 0.9477 2022-04-19 18:33:57,271 - mmseg - INFO - Iter [69200/80000] lr: 1.939e-07, eta: 2:55:28, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6141, decode.acc_seg: 66.8155, aux.loss_ce: 0.2844, aux.acc_seg: 65.4774, loss: 0.8985 2022-04-19 18:34:43,751 - mmseg - INFO - Iter [69250/80000] lr: 1.930e-07, eta: 2:54:39, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6440, decode.acc_seg: 65.2894, aux.loss_ce: 0.2913, aux.acc_seg: 64.1736, loss: 0.9353 2022-04-19 18:35:30,150 - mmseg - INFO - Iter [69300/80000] lr: 1.921e-07, eta: 2:53:50, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6154, decode.acc_seg: 66.2931, aux.loss_ce: 0.2787, aux.acc_seg: 64.8105, loss: 0.8941 2022-04-19 18:36:16,695 - mmseg - INFO - Iter [69350/80000] lr: 1.912e-07, eta: 2:53:01, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6324, decode.acc_seg: 65.6242, aux.loss_ce: 0.2888, aux.acc_seg: 63.6884, loss: 0.9212 2022-04-19 18:37:03,022 - mmseg - INFO - Iter [69400/80000] lr: 1.903e-07, eta: 2:52:11, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6061, decode.acc_seg: 66.5640, aux.loss_ce: 0.2767, aux.acc_seg: 65.0124, loss: 0.8828 2022-04-19 18:37:49,392 - mmseg - INFO - Iter [69450/80000] lr: 1.894e-07, eta: 2:51:22, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6240, decode.acc_seg: 66.5563, aux.loss_ce: 0.2858, aux.acc_seg: 64.7453, loss: 0.9098 2022-04-19 18:38:36,222 - mmseg - INFO - Iter [69500/80000] lr: 1.885e-07, eta: 2:50:33, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6360, decode.acc_seg: 65.1029, aux.loss_ce: 0.2915, aux.acc_seg: 63.2787, loss: 0.9275 2022-04-19 18:39:22,519 - mmseg - INFO - Iter [69550/80000] lr: 1.876e-07, eta: 2:49:44, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6312, decode.acc_seg: 64.8846, aux.loss_ce: 0.2932, aux.acc_seg: 63.1515, loss: 0.9244 2022-04-19 18:40:09,042 - mmseg - INFO - Iter [69600/80000] lr: 1.867e-07, eta: 2:48:55, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6133, decode.acc_seg: 66.2338, aux.loss_ce: 0.2812, aux.acc_seg: 64.4586, loss: 0.8945 2022-04-19 18:40:55,190 - mmseg - INFO - Iter [69650/80000] lr: 1.858e-07, eta: 2:48:06, time: 0.923, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6218, decode.acc_seg: 65.4438, aux.loss_ce: 0.2845, aux.acc_seg: 63.9278, loss: 0.9063 2022-04-19 18:41:41,806 - mmseg - INFO - Iter [69700/80000] lr: 1.849e-07, eta: 2:47:17, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6602, decode.acc_seg: 63.9148, aux.loss_ce: 0.3005, aux.acc_seg: 62.6226, loss: 0.9607 2022-04-19 18:42:28,449 - mmseg - INFO - Iter [69750/80000] lr: 1.840e-07, eta: 2:46:28, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5938, decode.acc_seg: 67.0695, aux.loss_ce: 0.2771, aux.acc_seg: 65.5538, loss: 0.8709 2022-04-19 18:43:14,721 - mmseg - INFO - Iter [69800/80000] lr: 1.831e-07, eta: 2:45:39, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6250, decode.acc_seg: 65.5280, aux.loss_ce: 0.2889, aux.acc_seg: 64.0285, loss: 0.9139 2022-04-19 18:44:01,036 - mmseg - INFO - Iter [69850/80000] lr: 1.822e-07, eta: 2:44:50, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6263, decode.acc_seg: 64.5163, aux.loss_ce: 0.2868, aux.acc_seg: 62.9309, loss: 0.9131 2022-04-19 18:44:47,400 - mmseg - INFO - Iter [69900/80000] lr: 1.813e-07, eta: 2:44:01, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6357, decode.acc_seg: 65.2590, aux.loss_ce: 0.2926, aux.acc_seg: 63.9027, loss: 0.9283 2022-04-19 18:45:33,905 - mmseg - INFO - Iter [69950/80000] lr: 1.804e-07, eta: 2:43:12, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5954, decode.acc_seg: 66.6022, aux.loss_ce: 0.2721, aux.acc_seg: 65.2292, loss: 0.8674 2022-04-19 18:46:20,539 - mmseg - INFO - Saving checkpoint at 70000 iterations 2022-04-19 18:46:32,925 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 18:46:32,957 - mmseg - INFO - Iter [70000/80000] lr: 1.795e-07, eta: 2:42:24, time: 1.179, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6195, decode.acc_seg: 66.2504, aux.loss_ce: 0.2812, aux.acc_seg: 65.3505, loss: 0.9007 2022-04-19 18:47:19,659 - mmseg - INFO - Iter [70050/80000] lr: 1.786e-07, eta: 2:41:35, time: 0.936, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6118, decode.acc_seg: 66.4043, aux.loss_ce: 0.2807, aux.acc_seg: 65.0228, loss: 0.8925 2022-04-19 18:48:06,004 - mmseg - INFO - Iter [70100/80000] lr: 1.777e-07, eta: 2:40:46, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6009, decode.acc_seg: 66.2169, aux.loss_ce: 0.2749, aux.acc_seg: 64.8034, loss: 0.8758 2022-04-19 18:48:52,562 - mmseg - INFO - Iter [70150/80000] lr: 1.768e-07, eta: 2:39:57, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6042, decode.acc_seg: 66.3233, aux.loss_ce: 0.2759, aux.acc_seg: 64.9665, loss: 0.8802 2022-04-19 18:49:38,903 - mmseg - INFO - Iter [70200/80000] lr: 1.759e-07, eta: 2:39:08, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6415, decode.acc_seg: 65.9405, aux.loss_ce: 0.2998, aux.acc_seg: 64.0164, loss: 0.9414 2022-04-19 18:50:25,431 - mmseg - INFO - Iter [70250/80000] lr: 1.750e-07, eta: 2:38:19, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6274, decode.acc_seg: 65.9770, aux.loss_ce: 0.2854, aux.acc_seg: 64.6311, loss: 0.9129 2022-04-19 18:51:11,683 - mmseg - INFO - Iter [70300/80000] lr: 1.741e-07, eta: 2:37:30, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6496, decode.acc_seg: 66.0155, aux.loss_ce: 0.2954, aux.acc_seg: 64.4924, loss: 0.9450 2022-04-19 18:51:58,047 - mmseg - INFO - Iter [70350/80000] lr: 1.732e-07, eta: 2:36:41, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6275, decode.acc_seg: 65.9554, aux.loss_ce: 0.2868, aux.acc_seg: 64.4969, loss: 0.9143 2022-04-19 18:52:44,434 - mmseg - INFO - Iter [70400/80000] lr: 1.723e-07, eta: 2:35:52, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6064, decode.acc_seg: 64.7043, aux.loss_ce: 0.2766, aux.acc_seg: 62.9933, loss: 0.8830 2022-04-19 18:53:31,328 - mmseg - INFO - Iter [70450/80000] lr: 1.714e-07, eta: 2:35:03, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6129, decode.acc_seg: 64.7283, aux.loss_ce: 0.2809, aux.acc_seg: 63.5381, loss: 0.8938 2022-04-19 18:54:17,637 - mmseg - INFO - Iter [70500/80000] lr: 1.705e-07, eta: 2:34:14, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6158, decode.acc_seg: 65.2316, aux.loss_ce: 0.2811, aux.acc_seg: 63.9056, loss: 0.8969 2022-04-19 18:55:04,107 - mmseg - INFO - Iter [70550/80000] lr: 1.696e-07, eta: 2:33:25, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6198, decode.acc_seg: 65.8016, aux.loss_ce: 0.2816, aux.acc_seg: 64.2721, loss: 0.9014 2022-04-19 18:55:50,772 - mmseg - INFO - Iter [70600/80000] lr: 1.687e-07, eta: 2:32:36, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5903, decode.acc_seg: 66.1781, aux.loss_ce: 0.2680, aux.acc_seg: 64.6555, loss: 0.8582 2022-04-19 18:56:37,455 - mmseg - INFO - Iter [70650/80000] lr: 1.678e-07, eta: 2:31:47, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6279, decode.acc_seg: 65.1981, aux.loss_ce: 0.2879, aux.acc_seg: 63.7107, loss: 0.9159 2022-04-19 18:57:23,950 - mmseg - INFO - Iter [70700/80000] lr: 1.669e-07, eta: 2:30:58, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6092, decode.acc_seg: 65.5086, aux.loss_ce: 0.2782, aux.acc_seg: 63.6512, loss: 0.8874 2022-04-19 18:58:10,388 - mmseg - INFO - Iter [70750/80000] lr: 1.660e-07, eta: 2:30:09, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6076, decode.acc_seg: 65.9859, aux.loss_ce: 0.2758, aux.acc_seg: 64.7508, loss: 0.8834 2022-04-19 18:58:56,869 - mmseg - INFO - Iter [70800/80000] lr: 1.651e-07, eta: 2:29:20, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6301, decode.acc_seg: 64.5221, aux.loss_ce: 0.2880, aux.acc_seg: 62.8729, loss: 0.9181 2022-04-19 18:59:43,569 - mmseg - INFO - Iter [70850/80000] lr: 1.642e-07, eta: 2:28:31, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5983, decode.acc_seg: 67.3909, aux.loss_ce: 0.2755, aux.acc_seg: 66.0100, loss: 0.8738 2022-04-19 19:00:29,961 - mmseg - INFO - Iter [70900/80000] lr: 1.633e-07, eta: 2:27:42, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6196, decode.acc_seg: 65.2337, aux.loss_ce: 0.2866, aux.acc_seg: 63.4917, loss: 0.9062 2022-04-19 19:01:16,522 - mmseg - INFO - Iter [70950/80000] lr: 1.624e-07, eta: 2:26:53, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6121, decode.acc_seg: 66.2403, aux.loss_ce: 0.2833, aux.acc_seg: 64.8336, loss: 0.8954 2022-04-19 19:02:03,014 - mmseg - INFO - Saving checkpoint at 71000 iterations 2022-04-19 19:02:20,198 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 19:02:20,198 - mmseg - INFO - Iter [71000/80000] lr: 1.615e-07, eta: 2:26:07, time: 1.273, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5894, decode.acc_seg: 66.3625, aux.loss_ce: 0.2715, aux.acc_seg: 64.9030, loss: 0.8609 2022-04-19 19:03:07,303 - mmseg - INFO - Iter [71050/80000] lr: 1.606e-07, eta: 2:25:18, time: 0.943, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6411, decode.acc_seg: 64.9906, aux.loss_ce: 0.2928, aux.acc_seg: 63.3418, loss: 0.9340 2022-04-19 19:03:53,876 - mmseg - INFO - Iter [71100/80000] lr: 1.598e-07, eta: 2:24:29, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6440, decode.acc_seg: 64.2221, aux.loss_ce: 0.2883, aux.acc_seg: 63.4424, loss: 0.9323 2022-04-19 19:04:40,290 - mmseg - INFO - Iter [71150/80000] lr: 1.589e-07, eta: 2:23:40, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5993, decode.acc_seg: 66.0041, aux.loss_ce: 0.2755, aux.acc_seg: 64.6260, loss: 0.8747 2022-04-19 19:05:26,794 - mmseg - INFO - Iter [71200/80000] lr: 1.580e-07, eta: 2:22:51, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5891, decode.acc_seg: 67.1342, aux.loss_ce: 0.2675, aux.acc_seg: 66.0914, loss: 0.8566 2022-04-19 19:06:13,428 - mmseg - INFO - Iter [71250/80000] lr: 1.571e-07, eta: 2:22:02, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6010, decode.acc_seg: 66.3723, aux.loss_ce: 0.2771, aux.acc_seg: 64.6324, loss: 0.8781 2022-04-19 19:06:59,807 - mmseg - INFO - Iter [71300/80000] lr: 1.562e-07, eta: 2:21:13, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6026, decode.acc_seg: 66.4583, aux.loss_ce: 0.2777, aux.acc_seg: 64.4533, loss: 0.8803 2022-04-19 19:07:46,278 - mmseg - INFO - Iter [71350/80000] lr: 1.553e-07, eta: 2:20:24, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6067, decode.acc_seg: 65.9610, aux.loss_ce: 0.2764, aux.acc_seg: 64.7918, loss: 0.8830 2022-04-19 19:08:32,546 - mmseg - INFO - Iter [71400/80000] lr: 1.544e-07, eta: 2:19:35, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6247, decode.acc_seg: 66.1353, aux.loss_ce: 0.2849, aux.acc_seg: 64.7093, loss: 0.9096 2022-04-19 19:09:18,819 - mmseg - INFO - Iter [71450/80000] lr: 1.535e-07, eta: 2:18:46, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6041, decode.acc_seg: 65.7673, aux.loss_ce: 0.2773, aux.acc_seg: 64.2323, loss: 0.8814 2022-04-19 19:10:05,163 - mmseg - INFO - Iter [71500/80000] lr: 1.526e-07, eta: 2:17:57, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6131, decode.acc_seg: 65.9969, aux.loss_ce: 0.2837, aux.acc_seg: 64.4036, loss: 0.8968 2022-04-19 19:10:51,437 - mmseg - INFO - Iter [71550/80000] lr: 1.517e-07, eta: 2:17:08, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5942, decode.acc_seg: 65.9559, aux.loss_ce: 0.2745, aux.acc_seg: 64.4812, loss: 0.8687 2022-04-19 19:11:37,831 - mmseg - INFO - Iter [71600/80000] lr: 1.508e-07, eta: 2:16:19, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6170, decode.acc_seg: 67.5544, aux.loss_ce: 0.2821, aux.acc_seg: 66.0367, loss: 0.8991 2022-04-19 19:12:24,036 - mmseg - INFO - Iter [71650/80000] lr: 1.499e-07, eta: 2:15:30, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5953, decode.acc_seg: 67.2223, aux.loss_ce: 0.2727, aux.acc_seg: 65.7003, loss: 0.8680 2022-04-19 19:13:10,282 - mmseg - INFO - Iter [71700/80000] lr: 1.490e-07, eta: 2:14:41, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5899, decode.acc_seg: 65.9180, aux.loss_ce: 0.2683, aux.acc_seg: 64.5174, loss: 0.8582 2022-04-19 19:13:56,928 - mmseg - INFO - Iter [71750/80000] lr: 1.481e-07, eta: 2:13:52, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6259, decode.acc_seg: 64.5653, aux.loss_ce: 0.2877, aux.acc_seg: 62.9189, loss: 0.9136 2022-04-19 19:14:43,372 - mmseg - INFO - Iter [71800/80000] lr: 1.472e-07, eta: 2:13:03, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6463, decode.acc_seg: 65.2598, aux.loss_ce: 0.2938, aux.acc_seg: 63.8673, loss: 0.9401 2022-04-19 19:15:30,261 - mmseg - INFO - Iter [71850/80000] lr: 1.463e-07, eta: 2:12:14, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6339, decode.acc_seg: 65.3305, aux.loss_ce: 0.2900, aux.acc_seg: 63.5094, loss: 0.9239 2022-04-19 19:16:16,579 - mmseg - INFO - Iter [71900/80000] lr: 1.454e-07, eta: 2:11:25, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6268, decode.acc_seg: 65.2669, aux.loss_ce: 0.2901, aux.acc_seg: 63.7717, loss: 0.9169 2022-04-19 19:17:03,226 - mmseg - INFO - Iter [71950/80000] lr: 1.445e-07, eta: 2:10:36, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5984, decode.acc_seg: 66.5786, aux.loss_ce: 0.2733, aux.acc_seg: 65.0307, loss: 0.8717 2022-04-19 19:17:49,578 - mmseg - INFO - Saving checkpoint at 72000 iterations 2022-04-19 19:18:00,335 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 19:18:00,336 - mmseg - INFO - Iter [72000/80000] lr: 1.436e-07, eta: 2:09:49, time: 1.142, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6163, decode.acc_seg: 66.6191, aux.loss_ce: 0.2876, aux.acc_seg: 64.9321, loss: 0.9038 2022-04-19 19:22:00,917 - mmseg - INFO - per class results: 2022-04-19 19:22:00,927 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.63 | 95.8 | | bicycle | 71.92 | 86.54 | | car | 68.1 | 87.13 | | motorcycle | 85.39 | 93.05 | | airplane | 79.96 | 95.3 | | bus | 85.66 | 93.34 | | train | 84.77 | 96.53 | | truck | 68.43 | 84.8 | | boat | 67.45 | 86.05 | | traffic light | 67.6 | 87.7 | | fire hydrant | 86.0 | 97.36 | | stop sign | 90.71 | 98.1 | | parking meter | 79.59 | 87.96 | | bench | 56.57 | 77.13 | | bird | 82.47 | 92.18 | | cat | 82.53 | 90.88 | | dog | 78.84 | 87.3 | | horse | 86.73 | 95.97 | | sheep | 87.6 | 96.73 | | cow | 87.92 | 93.54 | | elephant | 91.74 | 97.91 | | bear | 92.25 | 96.77 | | zebra | 92.15 | 97.19 | | giraffe | 86.34 | 96.06 | | backpack | 41.32 | 67.62 | | umbrella | 86.92 | 95.09 | | handbag | 39.68 | 58.12 | | tie | 5.53 | 8.19 | | suitcase | 81.87 | 94.48 | | frisbee | 81.52 | 91.23 | | skis | 48.31 | 61.19 | | snowboard | 66.86 | 76.28 | | sports ball | 62.0 | 73.11 | | kite | 72.8 | 90.14 | | baseball bat | 56.77 | 78.31 | | baseball glove | 73.81 | 87.75 | | skateboard | 81.27 | 90.41 | | surfboard | 82.77 | 90.67 | | tennis racket | 85.39 | 93.41 | | bottle | 52.08 | 70.63 | | wine glass | 59.65 | 82.86 | | cup | 56.59 | 78.81 | | fork | 48.29 | 63.89 | | knife | 41.62 | 61.85 | | spoon | 42.53 | 58.26 | | bowl | 49.56 | 67.01 | | banana | 70.04 | 95.36 | | apple | 56.07 | 79.69 | | sandwich | 52.39 | 75.89 | | orange | 70.58 | 82.07 | | broccoli | 57.28 | 78.1 | | carrot | 58.63 | 82.17 | | hot dog | 56.07 | 68.31 | | pizza | 75.49 | 93.09 | | donut | 78.6 | 92.0 | | cake | 66.06 | 85.66 | | chair | 52.07 | 75.39 | | couch | 57.46 | 79.72 | | potted plant | 35.04 | 55.69 | | bed | 65.93 | 81.09 | | dining table | 47.09 | 69.24 | | toilet | 82.03 | 95.27 | | tv | 74.22 | 88.08 | | laptop | 77.81 | 95.23 | | mouse | 77.17 | 89.14 | | remote | 62.03 | 81.13 | | keyboard | 63.37 | 72.2 | | cell phone | 75.52 | 88.21 | | microwave | 68.1 | 83.13 | | oven | 58.93 | 84.1 | | toaster | 81.11 | 87.62 | | sink | 64.21 | 84.99 | | refrigerator | 77.65 | 93.21 | | book | 53.11 | 76.56 | | clock | 68.64 | 85.44 | | vase | 63.49 | 88.37 | | scissors | 72.3 | 96.27 | | teddy bear | 80.47 | 93.62 | | hair drier | 53.53 | 56.38 | | toothbrush | 47.17 | 73.33 | | banner | 31.81 | 70.53 | | blanket | 8.31 | 9.81 | | branch | 11.39 | 14.34 | | bridge | 42.45 | 63.1 | | building-other | 54.73 | 69.93 | | bush | 34.12 | 45.14 | | cabinet | 58.01 | 78.18 | | cage | 26.49 | 38.64 | | cardboard | 53.1 | 66.97 | | carpet | 54.79 | 75.35 | | ceiling-other | 65.87 | 84.36 | | ceiling-tile | 16.89 | 18.92 | | cloth | 3.2 | 3.93 | | clothes | 17.37 | 20.56 | | clouds | 51.23 | 67.9 | | counter | 29.58 | 59.22 | | cupboard | 0.0 | 0.0 | | curtain | 68.68 | 81.94 | | desk-stuff | 45.19 | 64.03 | | dirt | 42.27 | 63.07 | | door-stuff | 47.29 | 72.63 | | fence | 34.28 | 57.95 | | floor-marble | 9.37 | 11.64 | | floor-other | 23.31 | 31.47 | | floor-stone | 3.4 | 4.32 | | floor-tile | 62.05 | 76.15 | | floor-wood | 64.36 | 81.49 | | flower | 41.1 | 65.29 | | fog | 13.92 | 14.9 | | food-other | 27.28 | 34.06 | | fruit | 46.61 | 60.5 | | furniture-other | 16.63 | 20.17 | | grass | 71.28 | 84.23 | | gravel | 28.15 | 39.7 | | ground-other | 4.92 | 5.91 | | hill | 13.0 | 15.94 | | house | 30.24 | 38.28 | | leaves | 30.86 | 39.51 | | light | 41.79 | 56.88 | | mat | 0.0 | 0.0 | | metal | 31.37 | 39.55 | | mirror-stuff | 59.72 | 76.86 | | moss | 0.0 | 0.0 | | mountain | 54.47 | 70.58 | | mud | 6.69 | 10.59 | | napkin | 16.19 | 23.32 | | net | 51.7 | 67.28 | | paper | 32.55 | 45.6 | | pavement | 51.24 | 66.78 | | pillow | 16.08 | 21.12 | | plant-other | 17.46 | 25.17 | | plastic | 25.08 | 31.65 | | platform | 27.73 | 52.85 | | playingfield | 69.8 | 90.07 | | railing | 7.09 | 10.57 | | railroad | 60.43 | 84.97 | | river | 49.08 | 70.99 | | road | 66.55 | 86.82 | | rock | 44.04 | 69.03 | | roof | 20.78 | 25.54 | | rug | 37.7 | 55.64 | | salad | 2.48 | 2.69 | | sand | 66.61 | 73.15 | | sea | 84.98 | 92.57 | | shelf | 36.63 | 53.87 | | sky-other | 72.73 | 87.49 | | skyscraper | 40.26 | 60.13 | | snow | 90.8 | 96.49 | | solid-other | 0.0 | 0.0 | | stairs | 30.03 | 58.99 | | stone | 4.89 | 5.73 | | straw | 29.41 | 36.89 | | structural-other | 0.82 | 0.85 | | table | 24.78 | 34.53 | | tent | 9.25 | 12.34 | | textile-other | 15.9 | 24.25 | | towel | 33.46 | 44.0 | | tree | 73.61 | 89.33 | | vegetable | 42.72 | 58.88 | | wall-brick | 49.47 | 68.96 | | wall-concrete | 61.66 | 81.35 | | wall-other | 21.62 | 30.11 | | wall-panel | 4.24 | 4.76 | | wall-stone | 28.45 | 35.77 | | wall-tile | 68.71 | 89.09 | | wall-wood | 43.44 | 58.79 | | water-other | 23.68 | 34.08 | | waterdrops | 0.0 | 0.0 | | window-blind | 52.08 | 65.21 | | window-other | 48.63 | 71.29 | | wood | 28.58 | 43.3 | +------------------+-------+-------+ 2022-04-19 19:22:00,927 - mmseg - INFO - Summary: 2022-04-19 19:22:00,927 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 73.44 | 50.44 | 63.76 | +-------+-------+-------+ 2022-04-19 19:22:00,942 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 19:22:00,942 - mmseg - INFO - Iter(val) [625] aAcc: 0.7344, mIoU: 0.5044, mAcc: 0.6376, IoU.person: 0.8663, IoU.bicycle: 0.7192, IoU.car: 0.6810, IoU.motorcycle: 0.8539, IoU.airplane: 0.7996, IoU.bus: 0.8566, IoU.train: 0.8477, IoU.truck: 0.6843, IoU.boat: 0.6745, IoU.traffic light: 0.6760, IoU.fire hydrant: 0.8600, IoU.stop sign: 0.9071, IoU.parking meter: 0.7959, IoU.bench: 0.5657, IoU.bird: 0.8247, IoU.cat: 0.8253, IoU.dog: 0.7884, IoU.horse: 0.8673, IoU.sheep: 0.8760, IoU.cow: 0.8792, IoU.elephant: 0.9174, IoU.bear: 0.9225, IoU.zebra: 0.9215, IoU.giraffe: 0.8634, IoU.backpack: 0.4132, IoU.umbrella: 0.8692, IoU.handbag: 0.3968, IoU.tie: 0.0553, IoU.suitcase: 0.8187, IoU.frisbee: 0.8152, IoU.skis: 0.4831, IoU.snowboard: 0.6686, IoU.sports ball: 0.6200, IoU.kite: 0.7280, IoU.baseball bat: 0.5677, IoU.baseball glove: 0.7381, IoU.skateboard: 0.8127, IoU.surfboard: 0.8277, IoU.tennis racket: 0.8539, IoU.bottle: 0.5208, IoU.wine glass: 0.5965, IoU.cup: 0.5659, IoU.fork: 0.4829, IoU.knife: 0.4162, IoU.spoon: 0.4253, IoU.bowl: 0.4956, IoU.banana: 0.7004, IoU.apple: 0.5607, IoU.sandwich: 0.5239, IoU.orange: 0.7058, IoU.broccoli: 0.5728, IoU.carrot: 0.5863, IoU.hot dog: 0.5607, IoU.pizza: 0.7549, IoU.donut: 0.7860, IoU.cake: 0.6606, IoU.chair: 0.5207, IoU.couch: 0.5746, IoU.potted plant: 0.3504, IoU.bed: 0.6593, IoU.dining table: 0.4709, IoU.toilet: 0.8203, IoU.tv: 0.7422, IoU.laptop: 0.7781, IoU.mouse: 0.7717, IoU.remote: 0.6203, IoU.keyboard: 0.6337, IoU.cell phone: 0.7552, IoU.microwave: 0.6810, IoU.oven: 0.5893, IoU.toaster: 0.8111, IoU.sink: 0.6421, IoU.refrigerator: 0.7765, IoU.book: 0.5311, IoU.clock: 0.6864, IoU.vase: 0.6349, IoU.scissors: 0.7230, IoU.teddy bear: 0.8047, IoU.hair drier: 0.5353, IoU.toothbrush: 0.4717, IoU.banner: 0.3181, IoU.blanket: 0.0831, IoU.branch: 0.1139, IoU.bridge: 0.4245, IoU.building-other: 0.5473, IoU.bush: 0.3412, IoU.cabinet: 0.5801, IoU.cage: 0.2649, IoU.cardboard: 0.5310, IoU.carpet: 0.5479, IoU.ceiling-other: 0.6587, IoU.ceiling-tile: 0.1689, IoU.cloth: 0.0320, IoU.clothes: 0.1737, IoU.clouds: 0.5123, IoU.counter: 0.2958, IoU.cupboard: 0.0000, IoU.curtain: 0.6868, IoU.desk-stuff: 0.4519, IoU.dirt: 0.4227, IoU.door-stuff: 0.4729, IoU.fence: 0.3428, IoU.floor-marble: 0.0937, IoU.floor-other: 0.2331, IoU.floor-stone: 0.0340, IoU.floor-tile: 0.6205, IoU.floor-wood: 0.6436, IoU.flower: 0.4110, IoU.fog: 0.1392, IoU.food-other: 0.2728, IoU.fruit: 0.4661, IoU.furniture-other: 0.1663, IoU.grass: 0.7128, IoU.gravel: 0.2815, IoU.ground-other: 0.0492, IoU.hill: 0.1300, IoU.house: 0.3024, IoU.leaves: 0.3086, IoU.light: 0.4179, IoU.mat: 0.0000, IoU.metal: 0.3137, IoU.mirror-stuff: 0.5972, IoU.moss: 0.0000, IoU.mountain: 0.5447, IoU.mud: 0.0669, IoU.napkin: 0.1619, IoU.net: 0.5170, IoU.paper: 0.3255, IoU.pavement: 0.5124, IoU.pillow: 0.1608, IoU.plant-other: 0.1746, IoU.plastic: 0.2508, IoU.platform: 0.2773, IoU.playingfield: 0.6980, IoU.railing: 0.0709, IoU.railroad: 0.6043, IoU.river: 0.4908, IoU.road: 0.6655, IoU.rock: 0.4404, IoU.roof: 0.2078, IoU.rug: 0.3770, IoU.salad: 0.0248, IoU.sand: 0.6661, IoU.sea: 0.8498, IoU.shelf: 0.3663, IoU.sky-other: 0.7273, IoU.skyscraper: 0.4026, IoU.snow: 0.9080, IoU.solid-other: 0.0000, IoU.stairs: 0.3003, IoU.stone: 0.0489, IoU.straw: 0.2941, IoU.structural-other: 0.0082, IoU.table: 0.2478, IoU.tent: 0.0925, IoU.textile-other: 0.1590, IoU.towel: 0.3346, IoU.tree: 0.7361, IoU.vegetable: 0.4272, IoU.wall-brick: 0.4947, IoU.wall-concrete: 0.6166, IoU.wall-other: 0.2162, IoU.wall-panel: 0.0424, IoU.wall-stone: 0.2845, IoU.wall-tile: 0.6871, IoU.wall-wood: 0.4344, IoU.water-other: 0.2368, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5208, IoU.window-other: 0.4863, IoU.wood: 0.2858, Acc.person: 0.9580, Acc.bicycle: 0.8654, Acc.car: 0.8713, Acc.motorcycle: 0.9305, Acc.airplane: 0.9530, Acc.bus: 0.9334, Acc.train: 0.9653, Acc.truck: 0.8480, Acc.boat: 0.8605, Acc.traffic light: 0.8770, Acc.fire hydrant: 0.9736, Acc.stop sign: 0.9810, Acc.parking meter: 0.8796, Acc.bench: 0.7713, Acc.bird: 0.9218, Acc.cat: 0.9088, Acc.dog: 0.8730, Acc.horse: 0.9597, Acc.sheep: 0.9673, Acc.cow: 0.9354, Acc.elephant: 0.9791, Acc.bear: 0.9677, Acc.zebra: 0.9719, Acc.giraffe: 0.9606, Acc.backpack: 0.6762, Acc.umbrella: 0.9509, Acc.handbag: 0.5812, Acc.tie: 0.0819, Acc.suitcase: 0.9448, Acc.frisbee: 0.9123, Acc.skis: 0.6119, Acc.snowboard: 0.7628, Acc.sports ball: 0.7311, Acc.kite: 0.9014, Acc.baseball bat: 0.7831, Acc.baseball glove: 0.8775, Acc.skateboard: 0.9041, Acc.surfboard: 0.9067, Acc.tennis racket: 0.9341, Acc.bottle: 0.7063, Acc.wine glass: 0.8286, Acc.cup: 0.7881, Acc.fork: 0.6389, Acc.knife: 0.6185, Acc.spoon: 0.5826, Acc.bowl: 0.6701, Acc.banana: 0.9536, Acc.apple: 0.7969, Acc.sandwich: 0.7589, Acc.orange: 0.8207, Acc.broccoli: 0.7810, Acc.carrot: 0.8217, Acc.hot dog: 0.6831, Acc.pizza: 0.9309, Acc.donut: 0.9200, Acc.cake: 0.8566, Acc.chair: 0.7539, Acc.couch: 0.7972, Acc.potted plant: 0.5569, Acc.bed: 0.8109, Acc.dining table: 0.6924, Acc.toilet: 0.9527, Acc.tv: 0.8808, Acc.laptop: 0.9523, Acc.mouse: 0.8914, Acc.remote: 0.8113, Acc.keyboard: 0.7220, Acc.cell phone: 0.8821, Acc.microwave: 0.8313, Acc.oven: 0.8410, Acc.toaster: 0.8762, Acc.sink: 0.8499, Acc.refrigerator: 0.9321, Acc.book: 0.7656, Acc.clock: 0.8544, Acc.vase: 0.8837, Acc.scissors: 0.9627, Acc.teddy bear: 0.9362, Acc.hair drier: 0.5638, Acc.toothbrush: 0.7333, Acc.banner: 0.7053, Acc.blanket: 0.0981, Acc.branch: 0.1434, Acc.bridge: 0.6310, Acc.building-other: 0.6993, Acc.bush: 0.4514, Acc.cabinet: 0.7818, Acc.cage: 0.3864, Acc.cardboard: 0.6697, Acc.carpet: 0.7535, Acc.ceiling-other: 0.8436, Acc.ceiling-tile: 0.1892, Acc.cloth: 0.0393, Acc.clothes: 0.2056, Acc.clouds: 0.6790, Acc.counter: 0.5922, Acc.cupboard: 0.0000, Acc.curtain: 0.8194, Acc.desk-stuff: 0.6403, Acc.dirt: 0.6307, Acc.door-stuff: 0.7263, Acc.fence: 0.5795, Acc.floor-marble: 0.1164, Acc.floor-other: 0.3147, Acc.floor-stone: 0.0432, Acc.floor-tile: 0.7615, Acc.floor-wood: 0.8149, Acc.flower: 0.6529, Acc.fog: 0.1490, Acc.food-other: 0.3406, Acc.fruit: 0.6050, Acc.furniture-other: 0.2017, Acc.grass: 0.8423, Acc.gravel: 0.3970, Acc.ground-other: 0.0591, Acc.hill: 0.1594, Acc.house: 0.3828, Acc.leaves: 0.3951, Acc.light: 0.5688, Acc.mat: 0.0000, Acc.metal: 0.3955, Acc.mirror-stuff: 0.7686, Acc.moss: 0.0000, Acc.mountain: 0.7058, Acc.mud: 0.1059, Acc.napkin: 0.2332, Acc.net: 0.6728, Acc.paper: 0.4560, Acc.pavement: 0.6678, Acc.pillow: 0.2112, Acc.plant-other: 0.2517, Acc.plastic: 0.3165, Acc.platform: 0.5285, Acc.playingfield: 0.9007, Acc.railing: 0.1057, Acc.railroad: 0.8497, Acc.river: 0.7099, Acc.road: 0.8682, Acc.rock: 0.6903, Acc.roof: 0.2554, Acc.rug: 0.5564, Acc.salad: 0.0269, Acc.sand: 0.7315, Acc.sea: 0.9257, Acc.shelf: 0.5387, Acc.sky-other: 0.8749, Acc.skyscraper: 0.6013, Acc.snow: 0.9649, Acc.solid-other: 0.0000, Acc.stairs: 0.5899, Acc.stone: 0.0573, Acc.straw: 0.3689, Acc.structural-other: 0.0085, Acc.table: 0.3453, Acc.tent: 0.1234, Acc.textile-other: 0.2425, Acc.towel: 0.4400, Acc.tree: 0.8933, Acc.vegetable: 0.5888, Acc.wall-brick: 0.6896, Acc.wall-concrete: 0.8135, Acc.wall-other: 0.3011, Acc.wall-panel: 0.0476, Acc.wall-stone: 0.3577, Acc.wall-tile: 0.8909, Acc.wall-wood: 0.5879, Acc.water-other: 0.3408, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6521, Acc.window-other: 0.7129, Acc.wood: 0.4330 2022-04-19 19:22:47,129 - mmseg - INFO - Iter [72050/80000] lr: 1.427e-07, eta: 2:09:26, time: 5.736, data_time: 4.817, memory: 73037, decode.loss_ce: 0.6149, decode.acc_seg: 65.5150, aux.loss_ce: 0.2805, aux.acc_seg: 64.0526, loss: 0.8955 2022-04-19 19:23:33,740 - mmseg - INFO - Iter [72100/80000] lr: 1.418e-07, eta: 2:08:37, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6074, decode.acc_seg: 65.6913, aux.loss_ce: 0.2799, aux.acc_seg: 63.9606, loss: 0.8873 2022-04-19 19:24:19,756 - mmseg - INFO - Iter [72150/80000] lr: 1.409e-07, eta: 2:07:48, time: 0.922, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6407, decode.acc_seg: 65.4097, aux.loss_ce: 0.2958, aux.acc_seg: 63.8483, loss: 0.9366 2022-04-19 19:25:06,422 - mmseg - INFO - Iter [72200/80000] lr: 1.400e-07, eta: 2:06:59, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6422, decode.acc_seg: 65.2442, aux.loss_ce: 0.2936, aux.acc_seg: 63.5852, loss: 0.9357 2022-04-19 19:25:53,192 - mmseg - INFO - Iter [72250/80000] lr: 1.391e-07, eta: 2:06:10, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6499, decode.acc_seg: 63.6791, aux.loss_ce: 0.2973, aux.acc_seg: 62.3412, loss: 0.9473 2022-04-19 19:26:39,806 - mmseg - INFO - Iter [72300/80000] lr: 1.382e-07, eta: 2:05:21, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6200, decode.acc_seg: 66.1602, aux.loss_ce: 0.2869, aux.acc_seg: 64.7767, loss: 0.9069 2022-04-19 19:27:26,691 - mmseg - INFO - Iter [72350/80000] lr: 1.373e-07, eta: 2:04:32, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5779, decode.acc_seg: 65.6257, aux.loss_ce: 0.2657, aux.acc_seg: 64.2306, loss: 0.8435 2022-04-19 19:28:13,394 - mmseg - INFO - Iter [72400/80000] lr: 1.364e-07, eta: 2:03:43, time: 0.936, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6427, decode.acc_seg: 65.8971, aux.loss_ce: 0.2928, aux.acc_seg: 64.4892, loss: 0.9355 2022-04-19 19:29:00,269 - mmseg - INFO - Iter [72450/80000] lr: 1.355e-07, eta: 2:02:54, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6113, decode.acc_seg: 66.2676, aux.loss_ce: 0.2793, aux.acc_seg: 64.5545, loss: 0.8906 2022-04-19 19:29:46,961 - mmseg - INFO - Iter [72500/80000] lr: 1.346e-07, eta: 2:02:05, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6127, decode.acc_seg: 66.8574, aux.loss_ce: 0.2791, aux.acc_seg: 65.6034, loss: 0.8918 2022-04-19 19:30:33,169 - mmseg - INFO - Iter [72550/80000] lr: 1.337e-07, eta: 2:01:15, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6064, decode.acc_seg: 66.7796, aux.loss_ce: 0.2773, aux.acc_seg: 65.3416, loss: 0.8837 2022-04-19 19:31:20,036 - mmseg - INFO - Iter [72600/80000] lr: 1.328e-07, eta: 2:00:26, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6213, decode.acc_seg: 65.5925, aux.loss_ce: 0.2853, aux.acc_seg: 64.4350, loss: 0.9066 2022-04-19 19:32:06,297 - mmseg - INFO - Iter [72650/80000] lr: 1.319e-07, eta: 1:59:37, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6275, decode.acc_seg: 65.7084, aux.loss_ce: 0.2890, aux.acc_seg: 64.4745, loss: 0.9164 2022-04-19 19:32:52,710 - mmseg - INFO - Iter [72700/80000] lr: 1.310e-07, eta: 1:58:48, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6004, decode.acc_seg: 65.9836, aux.loss_ce: 0.2749, aux.acc_seg: 64.8459, loss: 0.8753 2022-04-19 19:33:38,883 - mmseg - INFO - Iter [72750/80000] lr: 1.301e-07, eta: 1:57:59, time: 0.923, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6181, decode.acc_seg: 66.4311, aux.loss_ce: 0.2835, aux.acc_seg: 64.7502, loss: 0.9016 2022-04-19 19:34:25,434 - mmseg - INFO - Iter [72800/80000] lr: 1.292e-07, eta: 1:57:10, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6070, decode.acc_seg: 66.5447, aux.loss_ce: 0.2785, aux.acc_seg: 64.8384, loss: 0.8855 2022-04-19 19:35:11,723 - mmseg - INFO - Iter [72850/80000] lr: 1.283e-07, eta: 1:56:21, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6104, decode.acc_seg: 66.3602, aux.loss_ce: 0.2761, aux.acc_seg: 64.6482, loss: 0.8865 2022-04-19 19:35:58,371 - mmseg - INFO - Iter [72900/80000] lr: 1.274e-07, eta: 1:55:32, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6166, decode.acc_seg: 67.2567, aux.loss_ce: 0.2843, aux.acc_seg: 65.9516, loss: 0.9009 2022-04-19 19:36:44,773 - mmseg - INFO - Iter [72950/80000] lr: 1.265e-07, eta: 1:54:43, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6051, decode.acc_seg: 65.9252, aux.loss_ce: 0.2814, aux.acc_seg: 64.2681, loss: 0.8865 2022-04-19 19:37:30,846 - mmseg - INFO - Saving checkpoint at 73000 iterations 2022-04-19 19:37:45,495 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 19:37:45,507 - mmseg - INFO - Iter [73000/80000] lr: 1.257e-07, eta: 1:53:55, time: 1.212, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6375, decode.acc_seg: 65.8269, aux.loss_ce: 0.2916, aux.acc_seg: 64.7307, loss: 0.9291 2022-04-19 19:38:32,213 - mmseg - INFO - Iter [73050/80000] lr: 1.248e-07, eta: 1:53:06, time: 0.937, data_time: 0.009, memory: 73037, decode.loss_ce: 0.6267, decode.acc_seg: 65.7378, aux.loss_ce: 0.2847, aux.acc_seg: 64.4994, loss: 0.9114 2022-04-19 19:39:18,800 - mmseg - INFO - Iter [73100/80000] lr: 1.239e-07, eta: 1:52:17, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6041, decode.acc_seg: 66.3843, aux.loss_ce: 0.2765, aux.acc_seg: 64.7257, loss: 0.8806 2022-04-19 19:40:05,395 - mmseg - INFO - Iter [73150/80000] lr: 1.230e-07, eta: 1:51:28, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6536, decode.acc_seg: 66.1271, aux.loss_ce: 0.2989, aux.acc_seg: 65.0822, loss: 0.9525 2022-04-19 19:40:51,987 - mmseg - INFO - Iter [73200/80000] lr: 1.221e-07, eta: 1:50:39, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6073, decode.acc_seg: 65.5616, aux.loss_ce: 0.2823, aux.acc_seg: 64.0849, loss: 0.8896 2022-04-19 19:41:38,354 - mmseg - INFO - Iter [73250/80000] lr: 1.212e-07, eta: 1:49:50, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6062, decode.acc_seg: 65.2972, aux.loss_ce: 0.2768, aux.acc_seg: 64.1696, loss: 0.8830 2022-04-19 19:42:24,529 - mmseg - INFO - Iter [73300/80000] lr: 1.203e-07, eta: 1:49:01, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6295, decode.acc_seg: 65.6563, aux.loss_ce: 0.2867, aux.acc_seg: 64.3297, loss: 0.9162 2022-04-19 19:43:10,805 - mmseg - INFO - Iter [73350/80000] lr: 1.194e-07, eta: 1:48:12, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6172, decode.acc_seg: 64.4882, aux.loss_ce: 0.2852, aux.acc_seg: 62.8833, loss: 0.9024 2022-04-19 19:43:57,242 - mmseg - INFO - Iter [73400/80000] lr: 1.185e-07, eta: 1:47:23, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6319, decode.acc_seg: 66.3879, aux.loss_ce: 0.2931, aux.acc_seg: 64.8942, loss: 0.9250 2022-04-19 19:44:43,465 - mmseg - INFO - Iter [73450/80000] lr: 1.176e-07, eta: 1:46:34, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6255, decode.acc_seg: 64.4796, aux.loss_ce: 0.2888, aux.acc_seg: 63.0077, loss: 0.9143 2022-04-19 19:45:29,743 - mmseg - INFO - Iter [73500/80000] lr: 1.167e-07, eta: 1:45:45, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6454, decode.acc_seg: 64.4192, aux.loss_ce: 0.2983, aux.acc_seg: 62.5998, loss: 0.9437 2022-04-19 19:46:16,166 - mmseg - INFO - Iter [73550/80000] lr: 1.158e-07, eta: 1:44:56, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5967, decode.acc_seg: 66.4831, aux.loss_ce: 0.2757, aux.acc_seg: 65.2032, loss: 0.8724 2022-04-19 19:47:02,457 - mmseg - INFO - Iter [73600/80000] lr: 1.149e-07, eta: 1:44:07, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5934, decode.acc_seg: 66.4838, aux.loss_ce: 0.2724, aux.acc_seg: 65.0330, loss: 0.8658 2022-04-19 19:47:48,818 - mmseg - INFO - Iter [73650/80000] lr: 1.140e-07, eta: 1:43:18, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6129, decode.acc_seg: 65.3947, aux.loss_ce: 0.2816, aux.acc_seg: 64.0672, loss: 0.8945 2022-04-19 19:48:34,846 - mmseg - INFO - Iter [73700/80000] lr: 1.131e-07, eta: 1:42:29, time: 0.921, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6048, decode.acc_seg: 64.6705, aux.loss_ce: 0.2741, aux.acc_seg: 63.4615, loss: 0.8789 2022-04-19 19:49:21,253 - mmseg - INFO - Iter [73750/80000] lr: 1.122e-07, eta: 1:41:40, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6278, decode.acc_seg: 65.3743, aux.loss_ce: 0.2877, aux.acc_seg: 64.0044, loss: 0.9155 2022-04-19 19:50:07,520 - mmseg - INFO - Iter [73800/80000] lr: 1.113e-07, eta: 1:40:51, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6085, decode.acc_seg: 66.4638, aux.loss_ce: 0.2822, aux.acc_seg: 64.4610, loss: 0.8907 2022-04-19 19:50:53,906 - mmseg - INFO - Iter [73850/80000] lr: 1.104e-07, eta: 1:40:02, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5942, decode.acc_seg: 66.9553, aux.loss_ce: 0.2710, aux.acc_seg: 65.7614, loss: 0.8651 2022-04-19 19:51:40,269 - mmseg - INFO - Iter [73900/80000] lr: 1.095e-07, eta: 1:39:13, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6073, decode.acc_seg: 65.8546, aux.loss_ce: 0.2804, aux.acc_seg: 64.3390, loss: 0.8877 2022-04-19 19:52:29,222 - mmseg - INFO - Iter [73950/80000] lr: 1.086e-07, eta: 1:38:24, time: 0.979, data_time: 0.054, memory: 73037, decode.loss_ce: 0.6250, decode.acc_seg: 65.7460, aux.loss_ce: 0.2885, aux.acc_seg: 63.8544, loss: 0.9135 2022-04-19 19:53:15,797 - mmseg - INFO - Saving checkpoint at 74000 iterations 2022-04-19 19:53:27,281 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 19:53:27,283 - mmseg - INFO - Iter [74000/80000] lr: 1.077e-07, eta: 1:37:36, time: 1.156, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6116, decode.acc_seg: 65.1868, aux.loss_ce: 0.2850, aux.acc_seg: 63.3864, loss: 0.8966 2022-04-19 19:54:14,102 - mmseg - INFO - Iter [74050/80000] lr: 1.068e-07, eta: 1:36:47, time: 0.942, data_time: 0.011, memory: 73037, decode.loss_ce: 0.6071, decode.acc_seg: 67.9482, aux.loss_ce: 0.2819, aux.acc_seg: 65.9887, loss: 0.8890 2022-04-19 19:55:00,465 - mmseg - INFO - Iter [74100/80000] lr: 1.059e-07, eta: 1:35:58, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5828, decode.acc_seg: 67.1015, aux.loss_ce: 0.2712, aux.acc_seg: 65.4510, loss: 0.8540 2022-04-19 19:55:46,738 - mmseg - INFO - Iter [74150/80000] lr: 1.050e-07, eta: 1:35:09, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6280, decode.acc_seg: 64.6535, aux.loss_ce: 0.2895, aux.acc_seg: 63.0529, loss: 0.9175 2022-04-19 19:56:33,405 - mmseg - INFO - Iter [74200/80000] lr: 1.041e-07, eta: 1:34:20, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5962, decode.acc_seg: 66.6283, aux.loss_ce: 0.2787, aux.acc_seg: 65.2087, loss: 0.8749 2022-04-19 19:57:19,775 - mmseg - INFO - Iter [74250/80000] lr: 1.032e-07, eta: 1:33:31, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6350, decode.acc_seg: 65.3644, aux.loss_ce: 0.2932, aux.acc_seg: 64.0485, loss: 0.9282 2022-04-19 19:58:06,372 - mmseg - INFO - Iter [74300/80000] lr: 1.023e-07, eta: 1:32:42, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5922, decode.acc_seg: 66.5594, aux.loss_ce: 0.2764, aux.acc_seg: 65.1398, loss: 0.8686 2022-04-19 19:58:52,970 - mmseg - INFO - Iter [74350/80000] lr: 1.014e-07, eta: 1:31:53, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6256, decode.acc_seg: 66.8227, aux.loss_ce: 0.2842, aux.acc_seg: 65.3640, loss: 0.9098 2022-04-19 19:59:39,425 - mmseg - INFO - Iter [74400/80000] lr: 1.005e-07, eta: 1:31:04, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6276, decode.acc_seg: 66.7647, aux.loss_ce: 0.2876, aux.acc_seg: 64.9201, loss: 0.9152 2022-04-19 20:00:25,713 - mmseg - INFO - Iter [74450/80000] lr: 9.963e-08, eta: 1:30:15, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6039, decode.acc_seg: 65.7539, aux.loss_ce: 0.2782, aux.acc_seg: 63.9263, loss: 0.8821 2022-04-19 20:01:11,892 - mmseg - INFO - Iter [74500/80000] lr: 9.873e-08, eta: 1:29:26, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6110, decode.acc_seg: 66.3866, aux.loss_ce: 0.2826, aux.acc_seg: 64.6088, loss: 0.8937 2022-04-19 20:01:58,496 - mmseg - INFO - Iter [74550/80000] lr: 9.783e-08, eta: 1:28:37, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5995, decode.acc_seg: 65.8394, aux.loss_ce: 0.2767, aux.acc_seg: 64.5610, loss: 0.8762 2022-04-19 20:02:45,694 - mmseg - INFO - Iter [74600/80000] lr: 9.693e-08, eta: 1:27:48, time: 0.944, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6072, decode.acc_seg: 65.2980, aux.loss_ce: 0.2770, aux.acc_seg: 63.6287, loss: 0.8842 2022-04-19 20:03:32,384 - mmseg - INFO - Iter [74650/80000] lr: 9.604e-08, eta: 1:26:59, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6198, decode.acc_seg: 64.3062, aux.loss_ce: 0.2876, aux.acc_seg: 62.8570, loss: 0.9074 2022-04-19 20:04:18,783 - mmseg - INFO - Iter [74700/80000] lr: 9.514e-08, eta: 1:26:10, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6374, decode.acc_seg: 66.8215, aux.loss_ce: 0.2924, aux.acc_seg: 65.4548, loss: 0.9298 2022-04-19 20:05:05,274 - mmseg - INFO - Iter [74750/80000] lr: 9.424e-08, eta: 1:25:21, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6109, decode.acc_seg: 65.6795, aux.loss_ce: 0.2816, aux.acc_seg: 63.8984, loss: 0.8925 2022-04-19 20:05:51,719 - mmseg - INFO - Iter [74800/80000] lr: 9.334e-08, eta: 1:24:33, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6333, decode.acc_seg: 65.8493, aux.loss_ce: 0.2908, aux.acc_seg: 63.9248, loss: 0.9241 2022-04-19 20:06:37,951 - mmseg - INFO - Iter [74850/80000] lr: 9.245e-08, eta: 1:23:44, time: 0.925, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5922, decode.acc_seg: 65.5283, aux.loss_ce: 0.2722, aux.acc_seg: 64.0584, loss: 0.8644 2022-04-19 20:07:24,568 - mmseg - INFO - Iter [74900/80000] lr: 9.155e-08, eta: 1:22:55, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6126, decode.acc_seg: 65.9634, aux.loss_ce: 0.2852, aux.acc_seg: 63.9388, loss: 0.8979 2022-04-19 20:08:10,828 - mmseg - INFO - Iter [74950/80000] lr: 9.065e-08, eta: 1:22:06, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6144, decode.acc_seg: 66.7599, aux.loss_ce: 0.2828, aux.acc_seg: 65.3906, loss: 0.8971 2022-04-19 20:08:57,208 - mmseg - INFO - Saving checkpoint at 75000 iterations 2022-04-19 20:09:07,695 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 20:09:07,696 - mmseg - INFO - Iter [75000/80000] lr: 8.976e-08, eta: 1:21:17, time: 1.137, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6181, decode.acc_seg: 65.8663, aux.loss_ce: 0.2891, aux.acc_seg: 64.4167, loss: 0.9071 2022-04-19 20:09:54,627 - mmseg - INFO - Iter [75050/80000] lr: 8.886e-08, eta: 1:20:29, time: 0.939, data_time: 0.008, memory: 73037, decode.loss_ce: 0.5860, decode.acc_seg: 67.1029, aux.loss_ce: 0.2733, aux.acc_seg: 65.4209, loss: 0.8593 2022-04-19 20:10:41,706 - mmseg - INFO - Iter [75100/80000] lr: 8.796e-08, eta: 1:19:40, time: 0.941, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5874, decode.acc_seg: 66.5174, aux.loss_ce: 0.2726, aux.acc_seg: 64.7879, loss: 0.8600 2022-04-19 20:11:28,511 - mmseg - INFO - Iter [75150/80000] lr: 8.706e-08, eta: 1:18:51, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6175, decode.acc_seg: 66.0786, aux.loss_ce: 0.2818, aux.acc_seg: 64.7392, loss: 0.8994 2022-04-19 20:12:15,771 - mmseg - INFO - Iter [75200/80000] lr: 8.617e-08, eta: 1:18:02, time: 0.945, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5969, decode.acc_seg: 65.3251, aux.loss_ce: 0.2747, aux.acc_seg: 63.7548, loss: 0.8716 2022-04-19 20:13:02,341 - mmseg - INFO - Iter [75250/80000] lr: 8.527e-08, eta: 1:17:13, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5958, decode.acc_seg: 66.5006, aux.loss_ce: 0.2786, aux.acc_seg: 64.5046, loss: 0.8745 2022-04-19 20:13:48,632 - mmseg - INFO - Iter [75300/80000] lr: 8.437e-08, eta: 1:16:24, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6241, decode.acc_seg: 66.0190, aux.loss_ce: 0.2856, aux.acc_seg: 64.2317, loss: 0.9097 2022-04-19 20:14:35,261 - mmseg - INFO - Iter [75350/80000] lr: 8.347e-08, eta: 1:15:35, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6029, decode.acc_seg: 65.3804, aux.loss_ce: 0.2784, aux.acc_seg: 63.9622, loss: 0.8813 2022-04-19 20:15:21,649 - mmseg - INFO - Iter [75400/80000] lr: 8.258e-08, eta: 1:14:46, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5982, decode.acc_seg: 65.6656, aux.loss_ce: 0.2803, aux.acc_seg: 64.0776, loss: 0.8785 2022-04-19 20:16:08,019 - mmseg - INFO - Iter [75450/80000] lr: 8.168e-08, eta: 1:13:57, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6141, decode.acc_seg: 64.0299, aux.loss_ce: 0.2802, aux.acc_seg: 62.8596, loss: 0.8944 2022-04-19 20:16:54,426 - mmseg - INFO - Iter [75500/80000] lr: 8.078e-08, eta: 1:13:08, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6008, decode.acc_seg: 66.0804, aux.loss_ce: 0.2784, aux.acc_seg: 64.3328, loss: 0.8792 2022-04-19 20:17:41,207 - mmseg - INFO - Iter [75550/80000] lr: 7.988e-08, eta: 1:12:20, time: 0.936, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6472, decode.acc_seg: 65.7670, aux.loss_ce: 0.3019, aux.acc_seg: 63.1932, loss: 0.9491 2022-04-19 20:18:27,623 - mmseg - INFO - Iter [75600/80000] lr: 7.899e-08, eta: 1:11:31, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5932, decode.acc_seg: 65.6526, aux.loss_ce: 0.2720, aux.acc_seg: 64.0928, loss: 0.8651 2022-04-19 20:19:14,312 - mmseg - INFO - Iter [75650/80000] lr: 7.809e-08, eta: 1:10:42, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5984, decode.acc_seg: 66.8752, aux.loss_ce: 0.2784, aux.acc_seg: 65.1933, loss: 0.8767 2022-04-19 20:20:00,573 - mmseg - INFO - Iter [75700/80000] lr: 7.719e-08, eta: 1:09:53, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6332, decode.acc_seg: 65.6177, aux.loss_ce: 0.2881, aux.acc_seg: 63.7791, loss: 0.9212 2022-04-19 20:20:47,001 - mmseg - INFO - Iter [75750/80000] lr: 7.629e-08, eta: 1:09:04, time: 0.928, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6371, decode.acc_seg: 64.7723, aux.loss_ce: 0.2962, aux.acc_seg: 63.1827, loss: 0.9333 2022-04-19 20:21:33,334 - mmseg - INFO - Iter [75800/80000] lr: 7.540e-08, eta: 1:08:15, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6224, decode.acc_seg: 65.8430, aux.loss_ce: 0.2881, aux.acc_seg: 64.0719, loss: 0.9105 2022-04-19 20:22:19,758 - mmseg - INFO - Iter [75850/80000] lr: 7.450e-08, eta: 1:07:26, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6259, decode.acc_seg: 64.2001, aux.loss_ce: 0.2878, aux.acc_seg: 62.6057, loss: 0.9137 2022-04-19 20:23:05,999 - mmseg - INFO - Iter [75900/80000] lr: 7.360e-08, eta: 1:06:37, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6079, decode.acc_seg: 65.4399, aux.loss_ce: 0.2779, aux.acc_seg: 64.0426, loss: 0.8858 2022-04-19 20:23:52,484 - mmseg - INFO - Iter [75950/80000] lr: 7.271e-08, eta: 1:05:48, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5773, decode.acc_seg: 66.0604, aux.loss_ce: 0.2660, aux.acc_seg: 64.7562, loss: 0.8434 2022-04-19 20:24:39,086 - mmseg - INFO - Saving checkpoint at 76000 iterations 2022-04-19 20:24:52,121 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 20:24:52,129 - mmseg - INFO - Iter [76000/80000] lr: 7.181e-08, eta: 1:05:00, time: 1.191, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6051, decode.acc_seg: 66.1029, aux.loss_ce: 0.2798, aux.acc_seg: 64.5531, loss: 0.8849 2022-04-19 20:25:38,603 - mmseg - INFO - Iter [76050/80000] lr: 7.091e-08, eta: 1:04:11, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6219, decode.acc_seg: 64.0786, aux.loss_ce: 0.2849, aux.acc_seg: 62.9610, loss: 0.9068 2022-04-19 20:26:25,180 - mmseg - INFO - Iter [76100/80000] lr: 7.001e-08, eta: 1:03:22, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5974, decode.acc_seg: 64.2742, aux.loss_ce: 0.2768, aux.acc_seg: 62.5010, loss: 0.8742 2022-04-19 20:27:11,364 - mmseg - INFO - Iter [76150/80000] lr: 6.912e-08, eta: 1:02:34, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5895, decode.acc_seg: 65.7205, aux.loss_ce: 0.2657, aux.acc_seg: 64.3513, loss: 0.8552 2022-04-19 20:27:57,635 - mmseg - INFO - Iter [76200/80000] lr: 6.822e-08, eta: 1:01:45, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6042, decode.acc_seg: 65.8947, aux.loss_ce: 0.2790, aux.acc_seg: 64.3075, loss: 0.8832 2022-04-19 20:28:43,948 - mmseg - INFO - Iter [76250/80000] lr: 6.732e-08, eta: 1:00:56, time: 0.928, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6308, decode.acc_seg: 66.2585, aux.loss_ce: 0.2916, aux.acc_seg: 64.7661, loss: 0.9224 2022-04-19 20:29:30,656 - mmseg - INFO - Iter [76300/80000] lr: 6.642e-08, eta: 1:00:07, time: 0.932, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5753, decode.acc_seg: 67.5069, aux.loss_ce: 0.2664, aux.acc_seg: 66.0191, loss: 0.8418 2022-04-19 20:30:16,900 - mmseg - INFO - Iter [76350/80000] lr: 6.553e-08, eta: 0:59:18, time: 0.927, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6041, decode.acc_seg: 65.2133, aux.loss_ce: 0.2741, aux.acc_seg: 64.0146, loss: 0.8782 2022-04-19 20:31:03,162 - mmseg - INFO - Iter [76400/80000] lr: 6.463e-08, eta: 0:58:29, time: 0.923, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5943, decode.acc_seg: 65.2352, aux.loss_ce: 0.2719, aux.acc_seg: 63.6611, loss: 0.8662 2022-04-19 20:31:49,594 - mmseg - INFO - Iter [76450/80000] lr: 6.373e-08, eta: 0:57:40, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5838, decode.acc_seg: 65.8382, aux.loss_ce: 0.2716, aux.acc_seg: 64.0464, loss: 0.8554 2022-04-19 20:32:35,784 - mmseg - INFO - Iter [76500/80000] lr: 6.283e-08, eta: 0:56:52, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6002, decode.acc_seg: 67.3298, aux.loss_ce: 0.2772, aux.acc_seg: 65.3861, loss: 0.8773 2022-04-19 20:33:22,419 - mmseg - INFO - Iter [76550/80000] lr: 6.194e-08, eta: 0:56:03, time: 0.932, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6094, decode.acc_seg: 65.6895, aux.loss_ce: 0.2828, aux.acc_seg: 63.9225, loss: 0.8921 2022-04-19 20:34:08,717 - mmseg - INFO - Iter [76600/80000] lr: 6.104e-08, eta: 0:55:14, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6220, decode.acc_seg: 64.9360, aux.loss_ce: 0.2866, aux.acc_seg: 63.5331, loss: 0.9086 2022-04-19 20:34:55,155 - mmseg - INFO - Iter [76650/80000] lr: 6.014e-08, eta: 0:54:25, time: 0.930, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6003, decode.acc_seg: 65.3401, aux.loss_ce: 0.2762, aux.acc_seg: 63.6791, loss: 0.8765 2022-04-19 20:35:41,909 - mmseg - INFO - Iter [76700/80000] lr: 5.924e-08, eta: 0:53:36, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5972, decode.acc_seg: 65.5250, aux.loss_ce: 0.2803, aux.acc_seg: 63.6270, loss: 0.8774 2022-04-19 20:36:28,493 - mmseg - INFO - Iter [76750/80000] lr: 5.835e-08, eta: 0:52:47, time: 0.933, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6067, decode.acc_seg: 66.0719, aux.loss_ce: 0.2777, aux.acc_seg: 64.8534, loss: 0.8844 2022-04-19 20:37:14,942 - mmseg - INFO - Iter [76800/80000] lr: 5.745e-08, eta: 0:51:59, time: 0.927, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6088, decode.acc_seg: 66.1429, aux.loss_ce: 0.2831, aux.acc_seg: 64.5725, loss: 0.8919 2022-04-19 20:38:01,575 - mmseg - INFO - Iter [76850/80000] lr: 5.655e-08, eta: 0:51:10, time: 0.934, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6255, decode.acc_seg: 65.9047, aux.loss_ce: 0.2869, aux.acc_seg: 64.6300, loss: 0.9124 2022-04-19 20:38:47,847 - mmseg - INFO - Iter [76900/80000] lr: 5.566e-08, eta: 0:50:21, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6295, decode.acc_seg: 65.3969, aux.loss_ce: 0.2884, aux.acc_seg: 64.1904, loss: 0.9179 2022-04-19 20:39:34,485 - mmseg - INFO - Iter [76950/80000] lr: 5.476e-08, eta: 0:49:32, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6147, decode.acc_seg: 65.6452, aux.loss_ce: 0.2831, aux.acc_seg: 64.1678, loss: 0.8979 2022-04-19 20:40:20,843 - mmseg - INFO - Saving checkpoint at 77000 iterations 2022-04-19 20:40:31,587 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 20:40:31,591 - mmseg - INFO - Iter [77000/80000] lr: 5.386e-08, eta: 0:48:44, time: 1.141, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6001, decode.acc_seg: 66.4015, aux.loss_ce: 0.2766, aux.acc_seg: 64.7062, loss: 0.8767 2022-04-19 20:41:18,583 - mmseg - INFO - Iter [77050/80000] lr: 5.296e-08, eta: 0:47:55, time: 0.941, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6326, decode.acc_seg: 67.2052, aux.loss_ce: 0.2897, aux.acc_seg: 65.7158, loss: 0.9223 2022-04-19 20:42:05,355 - mmseg - INFO - Iter [77100/80000] lr: 5.207e-08, eta: 0:47:06, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6389, decode.acc_seg: 63.8191, aux.loss_ce: 0.2966, aux.acc_seg: 62.0918, loss: 0.9355 2022-04-19 20:42:52,556 - mmseg - INFO - Iter [77150/80000] lr: 5.117e-08, eta: 0:46:17, time: 0.946, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6034, decode.acc_seg: 67.0973, aux.loss_ce: 0.2812, aux.acc_seg: 64.8900, loss: 0.8846 2022-04-19 20:43:39,394 - mmseg - INFO - Iter [77200/80000] lr: 5.027e-08, eta: 0:45:28, time: 0.937, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6011, decode.acc_seg: 66.8515, aux.loss_ce: 0.2789, aux.acc_seg: 65.2352, loss: 0.8801 2022-04-19 20:44:26,246 - mmseg - INFO - Iter [77250/80000] lr: 4.937e-08, eta: 0:44:40, time: 0.937, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5902, decode.acc_seg: 66.3033, aux.loss_ce: 0.2723, aux.acc_seg: 64.6647, loss: 0.8625 2022-04-19 20:45:12,452 - mmseg - INFO - Iter [77300/80000] lr: 4.848e-08, eta: 0:43:51, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6249, decode.acc_seg: 65.5520, aux.loss_ce: 0.2924, aux.acc_seg: 63.4341, loss: 0.9173 2022-04-19 20:45:59,545 - mmseg - INFO - Iter [77350/80000] lr: 4.758e-08, eta: 0:43:02, time: 0.942, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5976, decode.acc_seg: 65.9810, aux.loss_ce: 0.2815, aux.acc_seg: 64.1401, loss: 0.8791 2022-04-19 20:46:45,820 - mmseg - INFO - Iter [77400/80000] lr: 4.668e-08, eta: 0:42:13, time: 0.924, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5724, decode.acc_seg: 67.0426, aux.loss_ce: 0.2637, aux.acc_seg: 65.4795, loss: 0.8360 2022-04-19 20:47:32,300 - mmseg - INFO - Iter [77450/80000] lr: 4.578e-08, eta: 0:41:24, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.5910, decode.acc_seg: 66.2563, aux.loss_ce: 0.2699, aux.acc_seg: 65.0394, loss: 0.8610 2022-04-19 20:48:18,598 - mmseg - INFO - Iter [77500/80000] lr: 4.489e-08, eta: 0:40:36, time: 0.926, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6119, decode.acc_seg: 67.4466, aux.loss_ce: 0.2808, aux.acc_seg: 66.1278, loss: 0.8927 2022-04-19 20:49:05,449 - mmseg - INFO - Iter [77550/80000] lr: 4.399e-08, eta: 0:39:47, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6099, decode.acc_seg: 66.2272, aux.loss_ce: 0.2874, aux.acc_seg: 64.3632, loss: 0.8974 2022-04-19 20:49:52,176 - mmseg - INFO - Iter [77600/80000] lr: 4.309e-08, eta: 0:38:58, time: 0.937, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6297, decode.acc_seg: 63.6072, aux.loss_ce: 0.2836, aux.acc_seg: 62.5311, loss: 0.9133 2022-04-19 20:50:38,808 - mmseg - INFO - Iter [77650/80000] lr: 4.219e-08, eta: 0:38:09, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6140, decode.acc_seg: 65.9866, aux.loss_ce: 0.2838, aux.acc_seg: 64.4039, loss: 0.8978 2022-04-19 20:51:25,238 - mmseg - INFO - Iter [77700/80000] lr: 4.130e-08, eta: 0:37:21, time: 0.931, data_time: 0.008, memory: 73037, decode.loss_ce: 0.5917, decode.acc_seg: 66.3835, aux.loss_ce: 0.2718, aux.acc_seg: 65.2364, loss: 0.8635 2022-04-19 20:52:11,556 - mmseg - INFO - Iter [77750/80000] lr: 4.040e-08, eta: 0:36:32, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5852, decode.acc_seg: 66.2276, aux.loss_ce: 0.2675, aux.acc_seg: 64.7982, loss: 0.8527 2022-04-19 20:52:58,510 - mmseg - INFO - Iter [77800/80000] lr: 3.950e-08, eta: 0:35:43, time: 0.939, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6305, decode.acc_seg: 64.9842, aux.loss_ce: 0.2892, aux.acc_seg: 63.4351, loss: 0.9197 2022-04-19 20:53:45,004 - mmseg - INFO - Iter [77850/80000] lr: 3.860e-08, eta: 0:34:54, time: 0.930, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5995, decode.acc_seg: 66.4708, aux.loss_ce: 0.2769, aux.acc_seg: 65.0290, loss: 0.8763 2022-04-19 20:54:31,873 - mmseg - INFO - Iter [77900/80000] lr: 3.771e-08, eta: 0:34:05, time: 0.938, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6142, decode.acc_seg: 66.1351, aux.loss_ce: 0.2876, aux.acc_seg: 64.2231, loss: 0.9018 2022-04-19 20:55:18,299 - mmseg - INFO - Iter [77950/80000] lr: 3.681e-08, eta: 0:33:17, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6391, decode.acc_seg: 66.1018, aux.loss_ce: 0.2957, aux.acc_seg: 64.6383, loss: 0.9348 2022-04-19 20:56:04,692 - mmseg - INFO - Saving checkpoint at 78000 iterations 2022-04-19 20:56:16,268 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 20:56:16,269 - mmseg - INFO - Iter [78000/80000] lr: 3.591e-08, eta: 0:32:28, time: 1.159, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5992, decode.acc_seg: 67.1306, aux.loss_ce: 0.2797, aux.acc_seg: 65.2984, loss: 0.8789 2022-04-19 20:57:02,968 - mmseg - INFO - Iter [78050/80000] lr: 3.502e-08, eta: 0:31:39, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5967, decode.acc_seg: 66.9616, aux.loss_ce: 0.2732, aux.acc_seg: 65.5729, loss: 0.8699 2022-04-19 20:57:49,899 - mmseg - INFO - Iter [78100/80000] lr: 3.412e-08, eta: 0:30:51, time: 0.938, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6385, decode.acc_seg: 65.8072, aux.loss_ce: 0.2963, aux.acc_seg: 63.8796, loss: 0.9349 2022-04-19 20:58:36,624 - mmseg - INFO - Iter [78150/80000] lr: 3.322e-08, eta: 0:30:02, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5893, decode.acc_seg: 66.1372, aux.loss_ce: 0.2752, aux.acc_seg: 64.4385, loss: 0.8645 2022-04-19 20:59:23,256 - mmseg - INFO - Iter [78200/80000] lr: 3.232e-08, eta: 0:29:13, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6198, decode.acc_seg: 66.1010, aux.loss_ce: 0.2849, aux.acc_seg: 64.5738, loss: 0.9047 2022-04-19 21:00:09,823 - mmseg - INFO - Iter [78250/80000] lr: 3.143e-08, eta: 0:28:24, time: 0.931, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5890, decode.acc_seg: 66.7887, aux.loss_ce: 0.2735, aux.acc_seg: 65.0893, loss: 0.8625 2022-04-19 21:00:56,128 - mmseg - INFO - Iter [78300/80000] lr: 3.053e-08, eta: 0:27:36, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6027, decode.acc_seg: 65.9723, aux.loss_ce: 0.2820, aux.acc_seg: 63.8681, loss: 0.8848 2022-04-19 21:01:42,429 - mmseg - INFO - Iter [78350/80000] lr: 2.963e-08, eta: 0:26:47, time: 0.926, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6089, decode.acc_seg: 67.2374, aux.loss_ce: 0.2811, aux.acc_seg: 65.4503, loss: 0.8900 2022-04-19 21:02:29,279 - mmseg - INFO - Iter [78400/80000] lr: 2.873e-08, eta: 0:25:58, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6232, decode.acc_seg: 64.4580, aux.loss_ce: 0.2852, aux.acc_seg: 62.8267, loss: 0.9084 2022-04-19 21:03:15,639 - mmseg - INFO - Iter [78450/80000] lr: 2.784e-08, eta: 0:25:09, time: 0.929, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6242, decode.acc_seg: 65.1738, aux.loss_ce: 0.2856, aux.acc_seg: 64.0641, loss: 0.9099 2022-04-19 21:04:02,425 - mmseg - INFO - Iter [78500/80000] lr: 2.694e-08, eta: 0:24:21, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6152, decode.acc_seg: 66.4565, aux.loss_ce: 0.2875, aux.acc_seg: 64.6607, loss: 0.9028 2022-04-19 21:04:49,163 - mmseg - INFO - Iter [78550/80000] lr: 2.604e-08, eta: 0:23:32, time: 0.934, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6016, decode.acc_seg: 64.7674, aux.loss_ce: 0.2741, aux.acc_seg: 63.2236, loss: 0.8757 2022-04-19 21:05:35,698 - mmseg - INFO - Iter [78600/80000] lr: 2.514e-08, eta: 0:22:43, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6368, decode.acc_seg: 64.6796, aux.loss_ce: 0.2952, aux.acc_seg: 62.6778, loss: 0.9320 2022-04-19 21:06:22,342 - mmseg - INFO - Iter [78650/80000] lr: 2.425e-08, eta: 0:21:54, time: 0.933, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5970, decode.acc_seg: 65.2164, aux.loss_ce: 0.2736, aux.acc_seg: 63.8107, loss: 0.8706 2022-04-19 21:07:08,784 - mmseg - INFO - Iter [78700/80000] lr: 2.335e-08, eta: 0:21:06, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6106, decode.acc_seg: 64.9320, aux.loss_ce: 0.2832, aux.acc_seg: 63.0656, loss: 0.8938 2022-04-19 21:07:55,321 - mmseg - INFO - Iter [78750/80000] lr: 2.245e-08, eta: 0:20:17, time: 0.930, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6148, decode.acc_seg: 65.6789, aux.loss_ce: 0.2806, aux.acc_seg: 64.7799, loss: 0.8953 2022-04-19 21:08:41,836 - mmseg - INFO - Iter [78800/80000] lr: 2.155e-08, eta: 0:19:28, time: 0.931, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6205, decode.acc_seg: 65.6855, aux.loss_ce: 0.2898, aux.acc_seg: 63.5116, loss: 0.9103 2022-04-19 21:09:28,260 - mmseg - INFO - Iter [78850/80000] lr: 2.066e-08, eta: 0:18:39, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6000, decode.acc_seg: 67.0414, aux.loss_ce: 0.2798, aux.acc_seg: 65.3698, loss: 0.8798 2022-04-19 21:10:14,926 - mmseg - INFO - Iter [78900/80000] lr: 1.976e-08, eta: 0:17:51, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6024, decode.acc_seg: 66.6385, aux.loss_ce: 0.2805, aux.acc_seg: 64.8610, loss: 0.8830 2022-04-19 21:11:01,402 - mmseg - INFO - Iter [78950/80000] lr: 1.886e-08, eta: 0:17:02, time: 0.932, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6082, decode.acc_seg: 66.4441, aux.loss_ce: 0.2797, aux.acc_seg: 64.7178, loss: 0.8879 2022-04-19 21:11:47,827 - mmseg - INFO - Saving checkpoint at 79000 iterations 2022-04-19 21:12:01,144 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 21:12:01,144 - mmseg - INFO - Iter [79000/80000] lr: 1.797e-08, eta: 0:16:13, time: 1.193, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6133, decode.acc_seg: 65.4297, aux.loss_ce: 0.2812, aux.acc_seg: 63.6921, loss: 0.8945 2022-04-19 21:12:47,958 - mmseg - INFO - Iter [79050/80000] lr: 1.707e-08, eta: 0:15:25, time: 0.938, data_time: 0.008, memory: 73037, decode.loss_ce: 0.6073, decode.acc_seg: 65.2048, aux.loss_ce: 0.2769, aux.acc_seg: 63.9117, loss: 0.8842 2022-04-19 21:13:34,345 - mmseg - INFO - Iter [79100/80000] lr: 1.617e-08, eta: 0:14:36, time: 0.928, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6548, decode.acc_seg: 64.4871, aux.loss_ce: 0.2959, aux.acc_seg: 63.0705, loss: 0.9507 2022-04-19 21:14:20,959 - mmseg - INFO - Iter [79150/80000] lr: 1.527e-08, eta: 0:13:47, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6247, decode.acc_seg: 65.8487, aux.loss_ce: 0.2861, aux.acc_seg: 64.3315, loss: 0.9108 2022-04-19 21:15:07,431 - mmseg - INFO - Iter [79200/80000] lr: 1.438e-08, eta: 0:12:59, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6124, decode.acc_seg: 64.9414, aux.loss_ce: 0.2853, aux.acc_seg: 63.9358, loss: 0.8977 2022-04-19 21:15:54,169 - mmseg - INFO - Iter [79250/80000] lr: 1.348e-08, eta: 0:12:10, time: 0.935, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6391, decode.acc_seg: 64.7049, aux.loss_ce: 0.2960, aux.acc_seg: 62.7871, loss: 0.9350 2022-04-19 21:16:40,988 - mmseg - INFO - Iter [79300/80000] lr: 1.258e-08, eta: 0:11:21, time: 0.936, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5943, decode.acc_seg: 66.5746, aux.loss_ce: 0.2796, aux.acc_seg: 64.7269, loss: 0.8739 2022-04-19 21:17:27,757 - mmseg - INFO - Iter [79350/80000] lr: 1.168e-08, eta: 0:10:32, time: 0.935, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6325, decode.acc_seg: 66.0611, aux.loss_ce: 0.2901, aux.acc_seg: 64.5155, loss: 0.9226 2022-04-19 21:18:14,336 - mmseg - INFO - Iter [79400/80000] lr: 1.079e-08, eta: 0:09:44, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6258, decode.acc_seg: 64.6227, aux.loss_ce: 0.2913, aux.acc_seg: 62.7187, loss: 0.9171 2022-04-19 21:19:00,795 - mmseg - INFO - Iter [79450/80000] lr: 9.889e-09, eta: 0:08:55, time: 0.929, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5994, decode.acc_seg: 66.6123, aux.loss_ce: 0.2778, aux.acc_seg: 65.0812, loss: 0.8772 2022-04-19 21:19:46,986 - mmseg - INFO - Iter [79500/80000] lr: 8.992e-09, eta: 0:08:06, time: 0.924, data_time: 0.006, memory: 73037, decode.loss_ce: 0.5920, decode.acc_seg: 66.2709, aux.loss_ce: 0.2719, aux.acc_seg: 64.8192, loss: 0.8639 2022-04-19 21:20:33,417 - mmseg - INFO - Iter [79550/80000] lr: 8.094e-09, eta: 0:07:18, time: 0.929, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6021, decode.acc_seg: 65.7892, aux.loss_ce: 0.2778, aux.acc_seg: 64.6927, loss: 0.8799 2022-04-19 21:21:19,666 - mmseg - INFO - Iter [79600/80000] lr: 7.197e-09, eta: 0:06:29, time: 0.925, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6046, decode.acc_seg: 66.0915, aux.loss_ce: 0.2815, aux.acc_seg: 64.6537, loss: 0.8861 2022-04-19 21:22:05,779 - mmseg - INFO - Iter [79650/80000] lr: 6.300e-09, eta: 0:05:40, time: 0.922, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5698, decode.acc_seg: 66.7610, aux.loss_ce: 0.2645, aux.acc_seg: 65.0813, loss: 0.8343 2022-04-19 21:22:52,143 - mmseg - INFO - Iter [79700/80000] lr: 5.402e-09, eta: 0:04:52, time: 0.927, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6034, decode.acc_seg: 66.7611, aux.loss_ce: 0.2777, aux.acc_seg: 65.1181, loss: 0.8811 2022-04-19 21:23:39,120 - mmseg - INFO - Iter [79750/80000] lr: 4.505e-09, eta: 0:04:03, time: 0.940, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6321, decode.acc_seg: 65.9754, aux.loss_ce: 0.2891, aux.acc_seg: 64.5810, loss: 0.9211 2022-04-19 21:24:25,648 - mmseg - INFO - Iter [79800/80000] lr: 3.607e-09, eta: 0:03:14, time: 0.931, data_time: 0.007, memory: 73037, decode.loss_ce: 0.6039, decode.acc_seg: 65.4019, aux.loss_ce: 0.2785, aux.acc_seg: 63.6841, loss: 0.8825 2022-04-19 21:25:12,273 - mmseg - INFO - Iter [79850/80000] lr: 2.710e-09, eta: 0:02:26, time: 0.933, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6291, decode.acc_seg: 65.3022, aux.loss_ce: 0.2875, aux.acc_seg: 63.8595, loss: 0.9167 2022-04-19 21:25:58,886 - mmseg - INFO - Iter [79900/80000] lr: 1.813e-09, eta: 0:01:37, time: 0.932, data_time: 0.005, memory: 73037, decode.loss_ce: 0.6297, decode.acc_seg: 65.8474, aux.loss_ce: 0.2911, aux.acc_seg: 63.9626, loss: 0.9209 2022-04-19 21:26:45,598 - mmseg - INFO - Iter [79950/80000] lr: 9.153e-10, eta: 0:00:48, time: 0.934, data_time: 0.006, memory: 73037, decode.loss_ce: 0.6172, decode.acc_seg: 66.7608, aux.loss_ce: 0.2841, aux.acc_seg: 64.9939, loss: 0.9013 2022-04-19 21:27:32,090 - mmseg - INFO - Saving checkpoint at 80000 iterations 2022-04-19 21:27:43,895 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 21:27:43,896 - mmseg - INFO - Iter [80000/80000] lr: 1.795e-11, eta: 0:00:00, time: 1.166, data_time: 0.005, memory: 73037, decode.loss_ce: 0.5821, decode.acc_seg: 65.6942, aux.loss_ce: 0.2717, aux.acc_seg: 64.1111, loss: 0.8538 2022-04-19 21:31:42,192 - mmseg - INFO - per class results: 2022-04-19 21:31:42,203 - mmseg - INFO - +------------------+-------+-------+ | Class | IoU | Acc | +------------------+-------+-------+ | person | 86.76 | 95.59 | | bicycle | 71.81 | 87.56 | | car | 67.91 | 87.16 | | motorcycle | 85.29 | 92.9 | | airplane | 79.35 | 94.67 | | bus | 85.24 | 92.93 | | train | 82.4 | 96.72 | | truck | 68.08 | 86.09 | | boat | 67.61 | 85.69 | | traffic light | 67.08 | 88.48 | | fire hydrant | 88.11 | 97.17 | | stop sign | 91.0 | 98.07 | | parking meter | 80.36 | 87.58 | | bench | 56.86 | 77.02 | | bird | 82.85 | 91.51 | | cat | 82.23 | 90.47 | | dog | 79.7 | 88.29 | | horse | 86.66 | 95.93 | | sheep | 87.86 | 96.38 | | cow | 87.93 | 93.67 | | elephant | 92.11 | 97.66 | | bear | 92.12 | 96.61 | | zebra | 92.12 | 97.36 | | giraffe | 86.3 | 96.17 | | backpack | 41.81 | 65.58 | | umbrella | 86.92 | 95.28 | | handbag | 40.17 | 58.17 | | tie | 5.33 | 7.9 | | suitcase | 82.14 | 94.44 | | frisbee | 80.87 | 91.44 | | skis | 48.92 | 63.16 | | snowboard | 67.11 | 77.39 | | sports ball | 61.91 | 73.4 | | kite | 72.32 | 90.53 | | baseball bat | 56.78 | 77.71 | | baseball glove | 74.0 | 87.39 | | skateboard | 81.45 | 90.58 | | surfboard | 82.86 | 91.02 | | tennis racket | 84.43 | 93.72 | | bottle | 51.84 | 68.52 | | wine glass | 59.66 | 83.37 | | cup | 56.43 | 79.8 | | fork | 48.72 | 66.24 | | knife | 41.82 | 60.21 | | spoon | 41.19 | 55.83 | | bowl | 49.14 | 66.88 | | banana | 70.98 | 94.24 | | apple | 55.68 | 80.24 | | sandwich | 51.82 | 73.87 | | orange | 68.53 | 79.79 | | broccoli | 56.25 | 75.79 | | carrot | 59.17 | 78.0 | | hot dog | 55.39 | 67.01 | | pizza | 75.42 | 92.77 | | donut | 78.69 | 92.35 | | cake | 66.54 | 85.75 | | chair | 52.64 | 74.74 | | couch | 57.49 | 79.01 | | potted plant | 35.69 | 57.82 | | bed | 66.74 | 82.35 | | dining table | 47.44 | 70.28 | | toilet | 81.48 | 95.54 | | tv | 75.01 | 88.47 | | laptop | 78.12 | 95.43 | | mouse | 77.29 | 88.21 | | remote | 59.91 | 76.16 | | keyboard | 63.1 | 71.44 | | cell phone | 74.99 | 88.78 | | microwave | 68.45 | 83.15 | | oven | 57.92 | 86.06 | | toaster | 81.53 | 87.47 | | sink | 63.49 | 83.64 | | refrigerator | 77.99 | 93.41 | | book | 53.84 | 77.27 | | clock | 69.31 | 83.85 | | vase | 63.26 | 88.1 | | scissors | 74.42 | 95.96 | | teddy bear | 80.4 | 94.35 | | hair drier | 55.1 | 58.5 | | toothbrush | 49.62 | 72.68 | | banner | 32.03 | 70.66 | | blanket | 8.72 | 9.94 | | branch | 10.19 | 13.42 | | bridge | 43.36 | 64.9 | | building-other | 55.07 | 70.66 | | bush | 34.01 | 44.33 | | cabinet | 57.86 | 78.39 | | cage | 26.32 | 38.83 | | cardboard | 53.5 | 66.11 | | carpet | 55.28 | 77.1 | | ceiling-other | 66.41 | 84.78 | | ceiling-tile | 14.98 | 16.25 | | cloth | 3.18 | 3.62 | | clothes | 17.34 | 20.36 | | clouds | 51.39 | 69.24 | | counter | 28.41 | 59.77 | | cupboard | 0.0 | 0.0 | | curtain | 68.6 | 82.69 | | desk-stuff | 44.63 | 62.51 | | dirt | 42.55 | 64.63 | | door-stuff | 47.26 | 71.97 | | fence | 34.03 | 56.66 | | floor-marble | 9.19 | 10.88 | | floor-other | 23.41 | 31.43 | | floor-stone | 3.75 | 4.84 | | floor-tile | 61.39 | 75.93 | | floor-wood | 64.77 | 80.84 | | flower | 39.52 | 60.98 | | fog | 16.17 | 18.58 | | food-other | 28.47 | 36.56 | | fruit | 46.29 | 60.76 | | furniture-other | 17.01 | 21.08 | | grass | 71.28 | 84.21 | | gravel | 28.16 | 39.12 | | ground-other | 4.93 | 5.9 | | hill | 15.14 | 19.13 | | house | 28.62 | 35.03 | | leaves | 29.31 | 36.82 | | light | 41.99 | 57.15 | | mat | 0.0 | 0.0 | | metal | 32.19 | 41.31 | | mirror-stuff | 59.62 | 76.25 | | moss | 0.0 | 0.0 | | mountain | 55.65 | 72.65 | | mud | 6.52 | 10.27 | | napkin | 14.99 | 20.91 | | net | 48.34 | 69.8 | | paper | 32.14 | 44.9 | | pavement | 51.96 | 67.47 | | pillow | 14.39 | 18.96 | | plant-other | 17.9 | 26.65 | | plastic | 24.72 | 31.34 | | platform | 27.59 | 53.52 | | playingfield | 69.3 | 88.96 | | railing | 7.65 | 11.95 | | railroad | 60.12 | 85.11 | | river | 48.22 | 71.29 | | road | 67.03 | 86.18 | | rock | 44.34 | 69.27 | | roof | 22.24 | 28.61 | | rug | 37.5 | 56.87 | | salad | 3.97 | 4.22 | | sand | 66.75 | 72.98 | | sea | 84.62 | 92.18 | | shelf | 36.77 | 52.59 | | sky-other | 72.67 | 86.42 | | skyscraper | 40.78 | 57.32 | | snow | 90.94 | 96.15 | | solid-other | 0.0 | 0.0 | | stairs | 29.29 | 57.18 | | stone | 5.8 | 6.87 | | straw | 30.68 | 39.52 | | structural-other | 0.8 | 0.84 | | table | 23.15 | 31.69 | | tent | 9.12 | 12.33 | | textile-other | 16.91 | 26.21 | | towel | 33.45 | 43.8 | | tree | 73.74 | 88.89 | | vegetable | 42.37 | 57.05 | | wall-brick | 49.02 | 68.56 | | wall-concrete | 61.69 | 80.67 | | wall-other | 22.2 | 32.01 | | wall-panel | 4.29 | 4.82 | | wall-stone | 29.57 | 38.47 | | wall-tile | 69.56 | 88.39 | | wall-wood | 43.6 | 58.94 | | water-other | 23.58 | 33.08 | | waterdrops | 0.0 | 0.0 | | window-blind | 52.47 | 65.04 | | window-other | 48.22 | 71.85 | | wood | 28.87 | 43.75 | +------------------+-------+-------+ 2022-04-19 21:31:42,203 - mmseg - INFO - Summary: 2022-04-19 21:31:42,203 - mmseg - INFO - +-------+-------+------+ | aAcc | mIoU | mAcc | +-------+-------+------+ | 73.42 | 50.46 | 63.7 | +-------+-------+------+ 2022-04-19 21:31:42,231 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_640_slide_80k_cocostuff164k_pt2ft_try4.py 2022-04-19 21:31:42,231 - mmseg - INFO - Iter(val) [625] aAcc: 0.7342, mIoU: 0.5046, mAcc: 0.6370, IoU.person: 0.8676, IoU.bicycle: 0.7181, IoU.car: 0.6791, IoU.motorcycle: 0.8529, IoU.airplane: 0.7935, IoU.bus: 0.8524, IoU.train: 0.8240, IoU.truck: 0.6808, IoU.boat: 0.6761, IoU.traffic light: 0.6708, IoU.fire hydrant: 0.8811, IoU.stop sign: 0.9100, IoU.parking meter: 0.8036, IoU.bench: 0.5686, IoU.bird: 0.8285, IoU.cat: 0.8223, IoU.dog: 0.7970, IoU.horse: 0.8666, IoU.sheep: 0.8786, IoU.cow: 0.8793, IoU.elephant: 0.9211, IoU.bear: 0.9212, IoU.zebra: 0.9212, IoU.giraffe: 0.8630, IoU.backpack: 0.4181, IoU.umbrella: 0.8692, IoU.handbag: 0.4017, IoU.tie: 0.0533, IoU.suitcase: 0.8214, IoU.frisbee: 0.8087, IoU.skis: 0.4892, IoU.snowboard: 0.6711, IoU.sports ball: 0.6191, IoU.kite: 0.7232, IoU.baseball bat: 0.5678, IoU.baseball glove: 0.7400, IoU.skateboard: 0.8145, IoU.surfboard: 0.8286, IoU.tennis racket: 0.8443, IoU.bottle: 0.5184, IoU.wine glass: 0.5966, IoU.cup: 0.5643, IoU.fork: 0.4872, IoU.knife: 0.4182, IoU.spoon: 0.4119, IoU.bowl: 0.4914, IoU.banana: 0.7098, IoU.apple: 0.5568, IoU.sandwich: 0.5182, IoU.orange: 0.6853, IoU.broccoli: 0.5625, IoU.carrot: 0.5917, IoU.hot dog: 0.5539, IoU.pizza: 0.7542, IoU.donut: 0.7869, IoU.cake: 0.6654, IoU.chair: 0.5264, IoU.couch: 0.5749, IoU.potted plant: 0.3569, IoU.bed: 0.6674, IoU.dining table: 0.4744, IoU.toilet: 0.8148, IoU.tv: 0.7501, IoU.laptop: 0.7812, IoU.mouse: 0.7729, IoU.remote: 0.5991, IoU.keyboard: 0.6310, IoU.cell phone: 0.7499, IoU.microwave: 0.6845, IoU.oven: 0.5792, IoU.toaster: 0.8153, IoU.sink: 0.6349, IoU.refrigerator: 0.7799, IoU.book: 0.5384, IoU.clock: 0.6931, IoU.vase: 0.6326, IoU.scissors: 0.7442, IoU.teddy bear: 0.8040, IoU.hair drier: 0.5510, IoU.toothbrush: 0.4962, IoU.banner: 0.3203, IoU.blanket: 0.0872, IoU.branch: 0.1019, IoU.bridge: 0.4336, IoU.building-other: 0.5507, IoU.bush: 0.3401, IoU.cabinet: 0.5786, IoU.cage: 0.2632, IoU.cardboard: 0.5350, IoU.carpet: 0.5528, IoU.ceiling-other: 0.6641, IoU.ceiling-tile: 0.1498, IoU.cloth: 0.0318, IoU.clothes: 0.1734, IoU.clouds: 0.5139, IoU.counter: 0.2841, IoU.cupboard: 0.0000, IoU.curtain: 0.6860, IoU.desk-stuff: 0.4463, IoU.dirt: 0.4255, IoU.door-stuff: 0.4726, IoU.fence: 0.3403, IoU.floor-marble: 0.0919, IoU.floor-other: 0.2341, IoU.floor-stone: 0.0375, IoU.floor-tile: 0.6139, IoU.floor-wood: 0.6477, IoU.flower: 0.3952, IoU.fog: 0.1617, IoU.food-other: 0.2847, IoU.fruit: 0.4629, IoU.furniture-other: 0.1701, IoU.grass: 0.7128, IoU.gravel: 0.2816, IoU.ground-other: 0.0493, IoU.hill: 0.1514, IoU.house: 0.2862, IoU.leaves: 0.2931, IoU.light: 0.4199, IoU.mat: 0.0000, IoU.metal: 0.3219, IoU.mirror-stuff: 0.5962, IoU.moss: 0.0000, IoU.mountain: 0.5565, IoU.mud: 0.0652, IoU.napkin: 0.1499, IoU.net: 0.4834, IoU.paper: 0.3214, IoU.pavement: 0.5196, IoU.pillow: 0.1439, IoU.plant-other: 0.1790, IoU.plastic: 0.2472, IoU.platform: 0.2759, IoU.playingfield: 0.6930, IoU.railing: 0.0765, IoU.railroad: 0.6012, IoU.river: 0.4822, IoU.road: 0.6703, IoU.rock: 0.4434, IoU.roof: 0.2224, IoU.rug: 0.3750, IoU.salad: 0.0397, IoU.sand: 0.6675, IoU.sea: 0.8462, IoU.shelf: 0.3677, IoU.sky-other: 0.7267, IoU.skyscraper: 0.4078, IoU.snow: 0.9094, IoU.solid-other: 0.0000, IoU.stairs: 0.2929, IoU.stone: 0.0580, IoU.straw: 0.3068, IoU.structural-other: 0.0080, IoU.table: 0.2315, IoU.tent: 0.0912, IoU.textile-other: 0.1691, IoU.towel: 0.3345, IoU.tree: 0.7374, IoU.vegetable: 0.4237, IoU.wall-brick: 0.4902, IoU.wall-concrete: 0.6169, IoU.wall-other: 0.2220, IoU.wall-panel: 0.0429, IoU.wall-stone: 0.2957, IoU.wall-tile: 0.6956, IoU.wall-wood: 0.4360, IoU.water-other: 0.2358, IoU.waterdrops: 0.0000, IoU.window-blind: 0.5247, IoU.window-other: 0.4822, IoU.wood: 0.2887, Acc.person: 0.9559, Acc.bicycle: 0.8756, Acc.car: 0.8716, Acc.motorcycle: 0.9290, Acc.airplane: 0.9467, Acc.bus: 0.9293, Acc.train: 0.9672, Acc.truck: 0.8609, Acc.boat: 0.8569, Acc.traffic light: 0.8848, Acc.fire hydrant: 0.9717, Acc.stop sign: 0.9807, Acc.parking meter: 0.8758, Acc.bench: 0.7702, Acc.bird: 0.9151, Acc.cat: 0.9047, Acc.dog: 0.8829, Acc.horse: 0.9593, Acc.sheep: 0.9638, Acc.cow: 0.9367, Acc.elephant: 0.9766, Acc.bear: 0.9661, Acc.zebra: 0.9736, Acc.giraffe: 0.9617, Acc.backpack: 0.6558, Acc.umbrella: 0.9528, Acc.handbag: 0.5817, Acc.tie: 0.0790, Acc.suitcase: 0.9444, Acc.frisbee: 0.9144, Acc.skis: 0.6316, Acc.snowboard: 0.7739, Acc.sports ball: 0.7340, Acc.kite: 0.9053, Acc.baseball bat: 0.7771, Acc.baseball glove: 0.8739, Acc.skateboard: 0.9058, Acc.surfboard: 0.9102, Acc.tennis racket: 0.9372, Acc.bottle: 0.6852, Acc.wine glass: 0.8337, Acc.cup: 0.7980, Acc.fork: 0.6624, Acc.knife: 0.6021, Acc.spoon: 0.5583, Acc.bowl: 0.6688, Acc.banana: 0.9424, Acc.apple: 0.8024, Acc.sandwich: 0.7387, Acc.orange: 0.7979, Acc.broccoli: 0.7579, Acc.carrot: 0.7800, Acc.hot dog: 0.6701, Acc.pizza: 0.9277, Acc.donut: 0.9235, Acc.cake: 0.8575, Acc.chair: 0.7474, Acc.couch: 0.7901, Acc.potted plant: 0.5782, Acc.bed: 0.8235, Acc.dining table: 0.7028, Acc.toilet: 0.9554, Acc.tv: 0.8847, Acc.laptop: 0.9543, Acc.mouse: 0.8821, Acc.remote: 0.7616, Acc.keyboard: 0.7144, Acc.cell phone: 0.8878, Acc.microwave: 0.8315, Acc.oven: 0.8606, Acc.toaster: 0.8747, Acc.sink: 0.8364, Acc.refrigerator: 0.9341, Acc.book: 0.7727, Acc.clock: 0.8385, Acc.vase: 0.8810, Acc.scissors: 0.9596, Acc.teddy bear: 0.9435, Acc.hair drier: 0.5850, Acc.toothbrush: 0.7268, Acc.banner: 0.7066, Acc.blanket: 0.0994, Acc.branch: 0.1342, Acc.bridge: 0.6490, Acc.building-other: 0.7066, Acc.bush: 0.4433, Acc.cabinet: 0.7839, Acc.cage: 0.3883, Acc.cardboard: 0.6611, Acc.carpet: 0.7710, Acc.ceiling-other: 0.8478, Acc.ceiling-tile: 0.1625, Acc.cloth: 0.0362, Acc.clothes: 0.2036, Acc.clouds: 0.6924, Acc.counter: 0.5977, Acc.cupboard: 0.0000, Acc.curtain: 0.8269, Acc.desk-stuff: 0.6251, Acc.dirt: 0.6463, Acc.door-stuff: 0.7197, Acc.fence: 0.5666, Acc.floor-marble: 0.1088, Acc.floor-other: 0.3143, Acc.floor-stone: 0.0484, Acc.floor-tile: 0.7593, Acc.floor-wood: 0.8084, Acc.flower: 0.6098, Acc.fog: 0.1858, Acc.food-other: 0.3656, Acc.fruit: 0.6076, Acc.furniture-other: 0.2108, Acc.grass: 0.8421, Acc.gravel: 0.3912, Acc.ground-other: 0.0590, Acc.hill: 0.1913, Acc.house: 0.3503, Acc.leaves: 0.3682, Acc.light: 0.5715, Acc.mat: 0.0000, Acc.metal: 0.4131, Acc.mirror-stuff: 0.7625, Acc.moss: 0.0000, Acc.mountain: 0.7265, Acc.mud: 0.1027, Acc.napkin: 0.2091, Acc.net: 0.6980, Acc.paper: 0.4490, Acc.pavement: 0.6747, Acc.pillow: 0.1896, Acc.plant-other: 0.2665, Acc.plastic: 0.3134, Acc.platform: 0.5352, Acc.playingfield: 0.8896, Acc.railing: 0.1195, Acc.railroad: 0.8511, Acc.river: 0.7129, Acc.road: 0.8618, Acc.rock: 0.6927, Acc.roof: 0.2861, Acc.rug: 0.5687, Acc.salad: 0.0422, Acc.sand: 0.7298, Acc.sea: 0.9218, Acc.shelf: 0.5259, Acc.sky-other: 0.8642, Acc.skyscraper: 0.5732, Acc.snow: 0.9615, Acc.solid-other: 0.0000, Acc.stairs: 0.5718, Acc.stone: 0.0687, Acc.straw: 0.3952, Acc.structural-other: 0.0084, Acc.table: 0.3169, Acc.tent: 0.1233, Acc.textile-other: 0.2621, Acc.towel: 0.4380, Acc.tree: 0.8889, Acc.vegetable: 0.5705, Acc.wall-brick: 0.6856, Acc.wall-concrete: 0.8067, Acc.wall-other: 0.3201, Acc.wall-panel: 0.0482, Acc.wall-stone: 0.3847, Acc.wall-tile: 0.8839, Acc.wall-wood: 0.5894, Acc.water-other: 0.3308, Acc.waterdrops: 0.0000, Acc.window-blind: 0.6504, Acc.window-other: 0.7185, Acc.wood: 0.4375