2022-05-06 00:12:16,824 - mmseg - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.7.0 (default, Oct 9 2018, 10:31:47) [GCC 7.3.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: A100-SXM-80GB CUDA_HOME: /mnt/lustre/share/cuda-11.1 NVCC: Build cuda_11.1.TC455_06.29069683_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+1f70964 ------------------------------------------------------------ 2022-05-06 00:12:16,833 - mmseg - INFO - Distributed training: True 2022-05-06 00:12:17,215 - 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=480, 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=59, 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=59, 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=(480, 480), stride=(320, 320))) dataset_type = 'PascalContextDataset59' data_root = 'data/VOCdevkit/VOC2010/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) img_scale = (520, 520) crop_size = (480, 480) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', reduce_zero_label=True), dict(type='Resize', img_scale=(520, 520), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=(480, 480), 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=(480, 480), 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=(4096, 520), 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='PascalContextDataset59', data_root='data/VOCdevkit/VOC2010/', img_dir='JPEGImages', ann_dir='SegmentationClassContext', split='ImageSets/SegmentationContext/train.txt', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', reduce_zero_label=True), dict(type='Resize', img_scale=(520, 520), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=(480, 480), 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=(480, 480), pad_val=0, seg_pad_val=255), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']) ]), val=dict( type='PascalContextDataset59', data_root='data/VOCdevkit/VOC2010/', img_dir='JPEGImages', ann_dir='SegmentationClassContext', split='ImageSets/SegmentationContext/val.txt', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(4096, 520), 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='PascalContextDataset59', data_root='data/VOCdevkit/VOC2010/', img_dir='JPEGImages', ann_dir='SegmentationClassContext', split='ImageSets/SegmentationContext/val.txt', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(4096, 520), 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=1) evaluation = dict( interval=8000, metric='mIoU', pre_eval=True, save_best='mIoU') work_dir = './work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2' gpu_ids = range(0, 8) auto_resume = False 2022-05-06 00:12:25,724 - mmseg - INFO - Set random seed to 1361080087, deterministic: False 2022-05-06 00:12:39,381 - 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 2022-05-06 00:12:41,164 - mmseg - INFO - initialize UPerHead with init_cfg {'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} 2022-05-06 00:12:41,658 - 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([3484, 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([59, 1024, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 decode_head.conv_seg.bias - torch.Size([59]): 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([59, 256, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 auxiliary_head.conv_seg.bias - torch.Size([59]): 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 2022-05-06 00:12:41,664 - 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(avg_non_ignore=False) (conv_seg): Conv2d(1024, 59, 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(avg_non_ignore=False) (conv_seg): Conv2d(256, 59, 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'}} ) 2022-05-06 00:12:41,699 - mmseg - INFO - Loaded 4996 images 2022-05-06 00:12:43,026 - mmseg - INFO - Loaded 5104 images 2022-05-06 00:12:43,027 - mmseg - INFO - Start running, host: duanyuchen@SH-IDC1-10-140-1-137, work_dir: /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2 2022-05-06 00:12:43,027 - 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 -------------------- 2022-05-06 00:12:43,027 - mmseg - INFO - workflow: [('train', 1)], max: 80000 iters 2022-05-06 00:12:43,027 - mmseg - INFO - Checkpoints will be saved to /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2 by HardDiskBackend. 2022-05-06 00:14:13,670 - mmseg - INFO - Iter [50/80000] lr: 4.688e-08, eta: 19:41:29, time: 0.887, data_time: 0.008, memory: 58091, decode.loss_ce: 2.8840, decode.acc_seg: 2.2972, aux.loss_ce: 1.1529, aux.acc_seg: 3.7011, loss: 4.0369 2022-05-06 00:14:40,895 - mmseg - INFO - Iter [100/80000] lr: 9.465e-08, eta: 15:53:34, time: 0.545, data_time: 0.006, memory: 58091, decode.loss_ce: 2.8861, decode.acc_seg: 5.0234, aux.loss_ce: 1.1700, aux.acc_seg: 3.4892, loss: 4.0561 2022-05-06 00:15:08,022 - mmseg - INFO - Iter [150/80000] lr: 1.424e-07, eta: 14:36:02, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 2.7711, decode.acc_seg: 10.4555, aux.loss_ce: 1.1481, aux.acc_seg: 3.7466, loss: 3.9192 2022-05-06 00:15:35,065 - mmseg - INFO - Iter [200/80000] lr: 1.900e-07, eta: 13:56:26, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 2.7297, decode.acc_seg: 17.9349, aux.loss_ce: 1.1593, aux.acc_seg: 4.8067, loss: 3.8890 2022-05-06 00:16:02,105 - mmseg - INFO - Iter [250/80000] lr: 2.376e-07, eta: 13:32:30, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 2.6399, decode.acc_seg: 25.5441, aux.loss_ce: 1.1681, aux.acc_seg: 6.7869, loss: 3.8080 2022-05-06 00:16:28,828 - mmseg - INFO - Iter [300/80000] lr: 2.851e-07, eta: 13:15:00, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 2.4616, decode.acc_seg: 27.9334, aux.loss_ce: 1.1389, aux.acc_seg: 8.0028, loss: 3.6005 2022-05-06 00:16:58,119 - mmseg - INFO - Iter [350/80000] lr: 3.326e-07, eta: 13:12:04, time: 0.586, data_time: 0.054, memory: 58091, decode.loss_ce: 2.2488, decode.acc_seg: 32.0866, aux.loss_ce: 1.1136, aux.acc_seg: 10.7575, loss: 3.3624 2022-05-06 00:17:25,534 - mmseg - INFO - Iter [400/80000] lr: 3.800e-07, eta: 13:03:33, time: 0.548, data_time: 0.008, memory: 58091, decode.loss_ce: 2.1396, decode.acc_seg: 36.3117, aux.loss_ce: 1.1448, aux.acc_seg: 13.7474, loss: 3.2844 2022-05-06 00:17:52,694 - mmseg - INFO - Iter [450/80000] lr: 4.274e-07, eta: 12:56:03, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 1.8980, decode.acc_seg: 38.7136, aux.loss_ce: 1.0729, aux.acc_seg: 17.7233, loss: 2.9709 2022-05-06 00:18:19,859 - mmseg - INFO - Iter [500/80000] lr: 4.747e-07, eta: 12:50:00, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 1.8808, decode.acc_seg: 38.6854, aux.loss_ce: 1.0840, aux.acc_seg: 22.7501, loss: 2.9648 2022-05-06 00:18:47,162 - mmseg - INFO - Iter [550/80000] lr: 5.219e-07, eta: 12:45:18, time: 0.546, data_time: 0.005, memory: 58091, decode.loss_ce: 1.8213, decode.acc_seg: 41.3478, aux.loss_ce: 1.0977, aux.acc_seg: 25.3609, loss: 2.9190 2022-05-06 00:19:14,305 - mmseg - INFO - Iter [600/80000] lr: 5.691e-07, eta: 12:40:57, time: 0.543, data_time: 0.006, memory: 58091, decode.loss_ce: 1.7473, decode.acc_seg: 42.2976, aux.loss_ce: 1.0822, aux.acc_seg: 28.0767, loss: 2.8295 2022-05-06 00:19:43,711 - mmseg - INFO - Iter [650/80000] lr: 6.162e-07, eta: 12:41:47, time: 0.588, data_time: 0.055, memory: 58091, decode.loss_ce: 1.5877, decode.acc_seg: 46.6046, aux.loss_ce: 1.0260, aux.acc_seg: 32.1137, loss: 2.6137 2022-05-06 00:20:10,960 - mmseg - INFO - Iter [700/80000] lr: 6.632e-07, eta: 12:38:17, time: 0.544, data_time: 0.008, memory: 58091, decode.loss_ce: 1.5119, decode.acc_seg: 48.7515, aux.loss_ce: 1.0140, aux.acc_seg: 34.5756, loss: 2.5259 2022-05-06 00:20:37,790 - mmseg - INFO - Iter [750/80000] lr: 7.102e-07, eta: 12:34:36, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 1.4168, decode.acc_seg: 51.4295, aux.loss_ce: 0.9822, aux.acc_seg: 37.7329, loss: 2.3990 2022-05-06 00:21:04,900 - mmseg - INFO - Iter [800/80000] lr: 7.572e-07, eta: 12:31:45, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 1.3753, decode.acc_seg: 53.8778, aux.loss_ce: 0.9710, aux.acc_seg: 38.6033, loss: 2.3464 2022-05-06 00:21:31,716 - mmseg - INFO - Iter [850/80000] lr: 8.040e-07, eta: 12:28:42, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 1.3237, decode.acc_seg: 53.4266, aux.loss_ce: 0.9332, aux.acc_seg: 36.8160, loss: 2.2569 2022-05-06 00:21:58,382 - mmseg - INFO - Iter [900/80000] lr: 8.509e-07, eta: 12:25:43, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 1.2861, decode.acc_seg: 56.9619, aux.loss_ce: 0.9398, aux.acc_seg: 40.4793, loss: 2.2259 2022-05-06 00:22:27,651 - mmseg - INFO - Iter [950/80000] lr: 8.976e-07, eta: 12:26:37, time: 0.586, data_time: 0.052, memory: 58091, decode.loss_ce: 1.2151, decode.acc_seg: 58.7372, aux.loss_ce: 0.8968, aux.acc_seg: 41.4090, loss: 2.1118 2022-05-06 00:22:54,263 - mmseg - INFO - Saving checkpoint at 1000 iterations 2022-05-06 00:23:15,756 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 00:23:15,759 - mmseg - INFO - Iter [1000/80000] lr: 9.443e-07, eta: 12:52:03, time: 0.960, data_time: 0.005, memory: 58091, decode.loss_ce: 1.1399, decode.acc_seg: 60.8282, aux.loss_ce: 0.8722, aux.acc_seg: 43.7683, loss: 2.0121 2022-05-06 00:23:43,562 - mmseg - INFO - Iter [1050/80000] lr: 9.909e-07, eta: 12:49:47, time: 0.558, data_time: 0.006, memory: 58091, decode.loss_ce: 1.0850, decode.acc_seg: 63.4740, aux.loss_ce: 0.8591, aux.acc_seg: 45.1161, loss: 1.9440 2022-05-06 00:24:10,501 - mmseg - INFO - Iter [1100/80000] lr: 1.038e-06, eta: 12:46:31, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 1.0619, decode.acc_seg: 63.6898, aux.loss_ce: 0.8445, aux.acc_seg: 45.4706, loss: 1.9064 2022-05-06 00:24:37,985 - mmseg - INFO - Iter [1150/80000] lr: 1.084e-06, eta: 12:44:09, time: 0.550, data_time: 0.005, memory: 58091, decode.loss_ce: 0.9917, decode.acc_seg: 65.5574, aux.loss_ce: 0.8062, aux.acc_seg: 46.0559, loss: 1.7979 2022-05-06 00:25:04,877 - mmseg - INFO - Iter [1200/80000] lr: 1.130e-06, eta: 12:41:16, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.9066, decode.acc_seg: 68.0909, aux.loss_ce: 0.7609, aux.acc_seg: 50.6273, loss: 1.6675 2022-05-06 00:25:34,623 - mmseg - INFO - Iter [1250/80000] lr: 1.177e-06, eta: 12:41:35, time: 0.595, data_time: 0.055, memory: 58091, decode.loss_ce: 0.8893, decode.acc_seg: 70.5539, aux.loss_ce: 0.7764, aux.acc_seg: 49.9742, loss: 1.6658 2022-05-06 00:26:01,574 - mmseg - INFO - Iter [1300/80000] lr: 1.223e-06, eta: 12:39:02, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.8280, decode.acc_seg: 70.5928, aux.loss_ce: 0.7338, aux.acc_seg: 51.6246, loss: 1.5619 2022-05-06 00:26:28,267 - mmseg - INFO - Iter [1350/80000] lr: 1.269e-06, eta: 12:36:22, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.7547, decode.acc_seg: 72.9347, aux.loss_ce: 0.6912, aux.acc_seg: 53.4552, loss: 1.4458 2022-05-06 00:26:55,112 - mmseg - INFO - Iter [1400/80000] lr: 1.316e-06, eta: 12:34:00, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.7838, decode.acc_seg: 71.7881, aux.loss_ce: 0.6965, aux.acc_seg: 53.7695, loss: 1.4803 2022-05-06 00:27:21,901 - mmseg - INFO - Iter [1450/80000] lr: 1.362e-06, eta: 12:31:44, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.7140, decode.acc_seg: 73.8682, aux.loss_ce: 0.6731, aux.acc_seg: 53.7702, loss: 1.3871 2022-05-06 00:27:48,839 - mmseg - INFO - Iter [1500/80000] lr: 1.408e-06, eta: 12:29:42, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.6912, decode.acc_seg: 74.7947, aux.loss_ce: 0.6430, aux.acc_seg: 56.9837, loss: 1.3342 2022-05-06 00:28:15,719 - mmseg - INFO - Iter [1550/80000] lr: 1.408e-06, eta: 12:27:44, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.6697, decode.acc_seg: 75.3006, aux.loss_ce: 0.6327, aux.acc_seg: 57.4606, loss: 1.3025 2022-05-06 00:28:45,295 - mmseg - INFO - Iter [1600/80000] lr: 1.407e-06, eta: 12:27:59, time: 0.590, data_time: 0.056, memory: 58091, decode.loss_ce: 0.6246, decode.acc_seg: 76.9273, aux.loss_ce: 0.6194, aux.acc_seg: 57.7353, loss: 1.2440 2022-05-06 00:29:12,305 - mmseg - INFO - Iter [1650/80000] lr: 1.406e-06, eta: 12:26:18, time: 0.542, data_time: 0.007, memory: 58091, decode.loss_ce: 0.6691, decode.acc_seg: 75.1430, aux.loss_ce: 0.6213, aux.acc_seg: 57.0827, loss: 1.2904 2022-05-06 00:29:39,397 - mmseg - INFO - Iter [1700/80000] lr: 1.405e-06, eta: 12:24:41, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.6012, decode.acc_seg: 76.7680, aux.loss_ce: 0.5715, aux.acc_seg: 60.1686, loss: 1.1726 2022-05-06 00:30:06,273 - mmseg - INFO - Iter [1750/80000] lr: 1.404e-06, eta: 12:22:59, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.5562, decode.acc_seg: 78.8328, aux.loss_ce: 0.5497, aux.acc_seg: 62.5496, loss: 1.1059 2022-05-06 00:30:33,104 - mmseg - INFO - Iter [1800/80000] lr: 1.404e-06, eta: 12:21:17, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.5899, decode.acc_seg: 78.0513, aux.loss_ce: 0.5689, aux.acc_seg: 61.6166, loss: 1.1587 2022-05-06 00:31:00,204 - mmseg - INFO - Iter [1850/80000] lr: 1.403e-06, eta: 12:19:51, time: 0.541, data_time: 0.006, memory: 58091, decode.loss_ce: 0.5455, decode.acc_seg: 78.6052, aux.loss_ce: 0.5332, aux.acc_seg: 62.8592, loss: 1.0786 2022-05-06 00:31:29,726 - mmseg - INFO - Iter [1900/80000] lr: 1.402e-06, eta: 12:20:11, time: 0.592, data_time: 0.055, memory: 58091, decode.loss_ce: 0.5052, decode.acc_seg: 80.2877, aux.loss_ce: 0.5241, aux.acc_seg: 64.0104, loss: 1.0293 2022-05-06 00:31:57,044 - mmseg - INFO - Iter [1950/80000] lr: 1.401e-06, eta: 12:18:58, time: 0.546, data_time: 0.005, memory: 58091, decode.loss_ce: 0.5052, decode.acc_seg: 79.2681, aux.loss_ce: 0.5073, aux.acc_seg: 63.8004, loss: 1.0125 2022-05-06 00:32:23,718 - mmseg - INFO - Saving checkpoint at 2000 iterations 2022-05-06 00:32:44,596 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 00:32:44,600 - mmseg - INFO - Iter [2000/80000] lr: 1.400e-06, eta: 12:30:42, time: 0.944, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4918, decode.acc_seg: 81.0558, aux.loss_ce: 0.5015, aux.acc_seg: 65.9474, loss: 0.9934 2022-05-06 00:33:11,988 - mmseg - INFO - Iter [2050/80000] lr: 1.399e-06, eta: 12:29:30, time: 0.555, data_time: 0.013, memory: 58091, decode.loss_ce: 0.5008, decode.acc_seg: 80.6314, aux.loss_ce: 0.5112, aux.acc_seg: 64.2297, loss: 1.0120 2022-05-06 00:33:38,610 - mmseg - INFO - Iter [2100/80000] lr: 1.398e-06, eta: 12:27:39, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4818, decode.acc_seg: 80.2460, aux.loss_ce: 0.4722, aux.acc_seg: 65.8852, loss: 0.9541 2022-05-06 00:34:05,351 - mmseg - INFO - Iter [2150/80000] lr: 1.397e-06, eta: 12:25:56, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4677, decode.acc_seg: 81.5869, aux.loss_ce: 0.4652, aux.acc_seg: 68.7038, loss: 0.9330 2022-05-06 00:34:34,663 - mmseg - INFO - Iter [2200/80000] lr: 1.396e-06, eta: 12:25:47, time: 0.586, data_time: 0.054, memory: 58091, decode.loss_ce: 0.4467, decode.acc_seg: 82.2565, aux.loss_ce: 0.4662, aux.acc_seg: 67.9896, loss: 0.9130 2022-05-06 00:35:01,917 - mmseg - INFO - Iter [2250/80000] lr: 1.395e-06, eta: 12:24:27, time: 0.545, data_time: 0.006, memory: 58091, decode.loss_ce: 0.4456, decode.acc_seg: 82.4929, aux.loss_ce: 0.4637, aux.acc_seg: 67.7108, loss: 0.9093 2022-05-06 00:35:28,801 - mmseg - INFO - Iter [2300/80000] lr: 1.395e-06, eta: 12:22:56, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4378, decode.acc_seg: 83.0167, aux.loss_ce: 0.4650, aux.acc_seg: 66.9069, loss: 0.9028 2022-05-06 00:35:55,607 - mmseg - INFO - Iter [2350/80000] lr: 1.394e-06, eta: 12:21:25, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4352, decode.acc_seg: 82.6218, aux.loss_ce: 0.4350, aux.acc_seg: 70.1993, loss: 0.8703 2022-05-06 00:36:22,795 - mmseg - INFO - Iter [2400/80000] lr: 1.393e-06, eta: 12:20:09, time: 0.544, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4117, decode.acc_seg: 83.5360, aux.loss_ce: 0.4095, aux.acc_seg: 72.5535, loss: 0.8211 2022-05-06 00:36:49,900 - mmseg - INFO - Iter [2450/80000] lr: 1.392e-06, eta: 12:18:53, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.4098, decode.acc_seg: 83.2545, aux.loss_ce: 0.4063, aux.acc_seg: 71.3006, loss: 0.8161 2022-05-06 00:37:19,383 - mmseg - INFO - Iter [2500/80000] lr: 1.391e-06, eta: 12:18:52, time: 0.590, data_time: 0.053, memory: 58091, decode.loss_ce: 0.4114, decode.acc_seg: 83.1177, aux.loss_ce: 0.3965, aux.acc_seg: 71.8646, loss: 0.8079 2022-05-06 00:37:46,384 - mmseg - INFO - Iter [2550/80000] lr: 1.390e-06, eta: 12:17:34, time: 0.540, data_time: 0.004, memory: 58091, decode.loss_ce: 0.3848, decode.acc_seg: 84.7957, aux.loss_ce: 0.4076, aux.acc_seg: 72.1010, loss: 0.7925 2022-05-06 00:38:13,165 - mmseg - INFO - Iter [2600/80000] lr: 1.389e-06, eta: 12:16:13, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3861, decode.acc_seg: 84.5825, aux.loss_ce: 0.3948, aux.acc_seg: 72.9160, loss: 0.7809 2022-05-06 00:38:39,964 - mmseg - INFO - Iter [2650/80000] lr: 1.388e-06, eta: 12:14:53, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.3832, decode.acc_seg: 84.9122, aux.loss_ce: 0.3925, aux.acc_seg: 72.6593, loss: 0.7757 2022-05-06 00:39:06,899 - mmseg - INFO - Iter [2700/80000] lr: 1.387e-06, eta: 12:13:40, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3580, decode.acc_seg: 85.6620, aux.loss_ce: 0.3564, aux.acc_seg: 74.8934, loss: 0.7144 2022-05-06 00:39:33,911 - mmseg - INFO - Iter [2750/80000] lr: 1.386e-06, eta: 12:12:31, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3692, decode.acc_seg: 84.6594, aux.loss_ce: 0.3807, aux.acc_seg: 72.5936, loss: 0.7499 2022-05-06 00:40:01,093 - mmseg - INFO - Iter [2800/80000] lr: 1.386e-06, eta: 12:11:27, time: 0.544, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3678, decode.acc_seg: 84.5254, aux.loss_ce: 0.3573, aux.acc_seg: 73.5210, loss: 0.7250 2022-05-06 00:40:30,719 - mmseg - INFO - Iter [2850/80000] lr: 1.385e-06, eta: 12:11:32, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.3292, decode.acc_seg: 86.2585, aux.loss_ce: 0.3437, aux.acc_seg: 75.2861, loss: 0.6730 2022-05-06 00:40:57,554 - mmseg - INFO - Iter [2900/80000] lr: 1.384e-06, eta: 12:10:20, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.3415, decode.acc_seg: 85.5909, aux.loss_ce: 0.3376, aux.acc_seg: 75.5332, loss: 0.6791 2022-05-06 00:41:24,899 - mmseg - INFO - Iter [2950/80000] lr: 1.383e-06, eta: 12:09:24, time: 0.547, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3455, decode.acc_seg: 85.5526, aux.loss_ce: 0.3475, aux.acc_seg: 74.3664, loss: 0.6930 2022-05-06 00:41:51,919 - mmseg - INFO - Saving checkpoint at 3000 iterations 2022-05-06 00:42:12,117 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 00:42:12,124 - mmseg - INFO - Iter [3000/80000] lr: 1.382e-06, eta: 12:16:55, time: 0.942, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3418, decode.acc_seg: 85.4566, aux.loss_ce: 0.3319, aux.acc_seg: 75.2856, loss: 0.6737 2022-05-06 00:42:39,511 - mmseg - INFO - Iter [3050/80000] lr: 1.381e-06, eta: 12:15:56, time: 0.550, data_time: 0.007, memory: 58091, decode.loss_ce: 0.3570, decode.acc_seg: 85.5715, aux.loss_ce: 0.3468, aux.acc_seg: 75.5443, loss: 0.7038 2022-05-06 00:43:06,383 - mmseg - INFO - Iter [3100/80000] lr: 1.380e-06, eta: 12:14:42, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3317, decode.acc_seg: 86.2454, aux.loss_ce: 0.3215, aux.acc_seg: 77.1666, loss: 0.6533 2022-05-06 00:43:35,826 - mmseg - INFO - Iter [3150/80000] lr: 1.379e-06, eta: 12:14:33, time: 0.589, data_time: 0.052, memory: 58091, decode.loss_ce: 0.3114, decode.acc_seg: 86.9207, aux.loss_ce: 0.3140, aux.acc_seg: 77.0159, loss: 0.6254 2022-05-06 00:44:03,162 - mmseg - INFO - Iter [3200/80000] lr: 1.378e-06, eta: 12:13:31, time: 0.546, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3223, decode.acc_seg: 85.7759, aux.loss_ce: 0.3117, aux.acc_seg: 76.0400, loss: 0.6340 2022-05-06 00:44:30,450 - mmseg - INFO - Iter [3250/80000] lr: 1.377e-06, eta: 12:12:31, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.3245, decode.acc_seg: 87.0805, aux.loss_ce: 0.3254, aux.acc_seg: 78.0978, loss: 0.6499 2022-05-06 00:44:57,555 - mmseg - INFO - Iter [3300/80000] lr: 1.377e-06, eta: 12:11:27, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3100, decode.acc_seg: 86.4816, aux.loss_ce: 0.2896, aux.acc_seg: 78.0769, loss: 0.5997 2022-05-06 00:45:24,552 - mmseg - INFO - Iter [3350/80000] lr: 1.376e-06, eta: 12:10:21, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3000, decode.acc_seg: 87.3497, aux.loss_ce: 0.2940, aux.acc_seg: 77.9991, loss: 0.5941 2022-05-06 00:45:51,276 - mmseg - INFO - Iter [3400/80000] lr: 1.375e-06, eta: 12:09:11, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3172, decode.acc_seg: 86.4145, aux.loss_ce: 0.3043, aux.acc_seg: 77.2987, loss: 0.6215 2022-05-06 00:46:20,638 - mmseg - INFO - Iter [3450/80000] lr: 1.374e-06, eta: 12:09:00, time: 0.587, data_time: 0.054, memory: 58091, decode.loss_ce: 0.3096, decode.acc_seg: 87.1734, aux.loss_ce: 0.2998, aux.acc_seg: 78.9151, loss: 0.6094 2022-05-06 00:46:47,241 - mmseg - INFO - Iter [3500/80000] lr: 1.373e-06, eta: 12:07:49, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2819, decode.acc_seg: 87.6789, aux.loss_ce: 0.2710, aux.acc_seg: 79.2483, loss: 0.5528 2022-05-06 00:47:13,998 - mmseg - INFO - Iter [3550/80000] lr: 1.372e-06, eta: 12:06:42, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3023, decode.acc_seg: 87.4771, aux.loss_ce: 0.2960, aux.acc_seg: 78.0388, loss: 0.5983 2022-05-06 00:47:40,842 - mmseg - INFO - Iter [3600/80000] lr: 1.371e-06, eta: 12:05:38, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2864, decode.acc_seg: 87.7782, aux.loss_ce: 0.2782, aux.acc_seg: 79.3882, loss: 0.5646 2022-05-06 00:48:07,493 - mmseg - INFO - Iter [3650/80000] lr: 1.370e-06, eta: 12:04:30, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.3066, decode.acc_seg: 86.7639, aux.loss_ce: 0.2754, aux.acc_seg: 79.5014, loss: 0.5820 2022-05-06 00:48:34,258 - mmseg - INFO - Iter [3700/80000] lr: 1.369e-06, eta: 12:03:26, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2817, decode.acc_seg: 88.5074, aux.loss_ce: 0.2672, aux.acc_seg: 81.2183, loss: 0.5489 2022-05-06 00:49:03,708 - mmseg - INFO - Iter [3750/80000] lr: 1.369e-06, eta: 12:03:18, time: 0.588, data_time: 0.054, memory: 58091, decode.loss_ce: 0.3028, decode.acc_seg: 86.5894, aux.loss_ce: 0.2677, aux.acc_seg: 78.4375, loss: 0.5705 2022-05-06 00:49:30,952 - mmseg - INFO - Iter [3800/80000] lr: 1.368e-06, eta: 12:02:26, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.2616, decode.acc_seg: 88.5176, aux.loss_ce: 0.2602, aux.acc_seg: 79.5605, loss: 0.5218 2022-05-06 00:49:57,950 - mmseg - INFO - Iter [3850/80000] lr: 1.367e-06, eta: 12:01:29, time: 0.540, data_time: 0.006, memory: 58091, decode.loss_ce: 0.2720, decode.acc_seg: 88.1536, aux.loss_ce: 0.2492, aux.acc_seg: 80.3310, loss: 0.5212 2022-05-06 00:50:24,899 - mmseg - INFO - Iter [3900/80000] lr: 1.366e-06, eta: 12:00:32, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2714, decode.acc_seg: 88.7956, aux.loss_ce: 0.2492, aux.acc_seg: 80.9914, loss: 0.5206 2022-05-06 00:50:52,198 - mmseg - INFO - Iter [3950/80000] lr: 1.365e-06, eta: 11:59:42, time: 0.546, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2581, decode.acc_seg: 88.8760, aux.loss_ce: 0.2424, aux.acc_seg: 80.9937, loss: 0.5004 2022-05-06 00:51:18,965 - mmseg - INFO - Saving checkpoint at 4000 iterations 2022-05-06 00:51:40,808 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 00:51:40,817 - mmseg - INFO - Iter [4000/80000] lr: 1.364e-06, eta: 12:05:35, time: 0.970, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2515, decode.acc_seg: 89.0981, aux.loss_ce: 0.2341, aux.acc_seg: 81.4798, loss: 0.4856 2022-05-06 00:52:07,974 - mmseg - INFO - Iter [4050/80000] lr: 1.363e-06, eta: 12:04:42, time: 0.546, data_time: 0.007, memory: 58091, decode.loss_ce: 0.2841, decode.acc_seg: 88.2139, aux.loss_ce: 0.2493, aux.acc_seg: 81.0212, loss: 0.5334 2022-05-06 00:52:37,406 - mmseg - INFO - Iter [4100/80000] lr: 1.362e-06, eta: 12:04:28, time: 0.589, data_time: 0.055, memory: 58091, decode.loss_ce: 0.2586, decode.acc_seg: 88.5284, aux.loss_ce: 0.2405, aux.acc_seg: 81.0192, loss: 0.4992 2022-05-06 00:53:04,333 - mmseg - INFO - Iter [4150/80000] lr: 1.361e-06, eta: 12:03:28, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2545, decode.acc_seg: 89.2840, aux.loss_ce: 0.2414, aux.acc_seg: 81.3159, loss: 0.4960 2022-05-06 00:53:30,994 - mmseg - INFO - Iter [4200/80000] lr: 1.360e-06, eta: 12:02:24, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2517, decode.acc_seg: 89.2056, aux.loss_ce: 0.2399, aux.acc_seg: 81.4451, loss: 0.4916 2022-05-06 00:53:57,964 - mmseg - INFO - Iter [4250/80000] lr: 1.360e-06, eta: 12:01:27, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2701, decode.acc_seg: 88.4432, aux.loss_ce: 0.2405, aux.acc_seg: 81.8875, loss: 0.5107 2022-05-06 00:54:24,818 - mmseg - INFO - Iter [4300/80000] lr: 1.359e-06, eta: 12:00:28, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2491, decode.acc_seg: 89.3127, aux.loss_ce: 0.2223, aux.acc_seg: 83.0608, loss: 0.4714 2022-05-06 00:54:52,002 - mmseg - INFO - Iter [4350/80000] lr: 1.358e-06, eta: 11:59:35, time: 0.544, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2455, decode.acc_seg: 89.2212, aux.loss_ce: 0.2126, aux.acc_seg: 82.6819, loss: 0.4580 2022-05-06 00:55:21,811 - mmseg - INFO - Iter [4400/80000] lr: 1.357e-06, eta: 11:59:29, time: 0.596, data_time: 0.056, memory: 58091, decode.loss_ce: 0.2351, decode.acc_seg: 89.9963, aux.loss_ce: 0.2177, aux.acc_seg: 83.3771, loss: 0.4528 2022-05-06 00:55:48,450 - mmseg - INFO - Iter [4450/80000] lr: 1.356e-06, eta: 11:58:28, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2248, decode.acc_seg: 89.8898, aux.loss_ce: 0.2108, aux.acc_seg: 82.9363, loss: 0.4355 2022-05-06 00:56:15,269 - mmseg - INFO - Iter [4500/80000] lr: 1.355e-06, eta: 11:57:30, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2375, decode.acc_seg: 89.4594, aux.loss_ce: 0.2182, aux.acc_seg: 82.3529, loss: 0.4558 2022-05-06 00:56:41,917 - mmseg - INFO - Iter [4550/80000] lr: 1.354e-06, eta: 11:56:31, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2271, decode.acc_seg: 89.9906, aux.loss_ce: 0.2038, aux.acc_seg: 83.5642, loss: 0.4309 2022-05-06 00:57:08,589 - mmseg - INFO - Iter [4600/80000] lr: 1.353e-06, eta: 11:55:33, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2280, decode.acc_seg: 90.2109, aux.loss_ce: 0.2082, aux.acc_seg: 83.5851, loss: 0.4362 2022-05-06 00:57:35,608 - mmseg - INFO - Iter [4650/80000] lr: 1.352e-06, eta: 11:54:41, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2371, decode.acc_seg: 89.5747, aux.loss_ce: 0.1991, aux.acc_seg: 84.1865, loss: 0.4361 2022-05-06 00:58:05,259 - mmseg - INFO - Iter [4700/80000] lr: 1.351e-06, eta: 11:54:31, time: 0.592, data_time: 0.058, memory: 58091, decode.loss_ce: 0.2434, decode.acc_seg: 89.3616, aux.loss_ce: 0.2122, aux.acc_seg: 82.8833, loss: 0.4557 2022-05-06 00:58:32,145 - mmseg - INFO - Iter [4750/80000] lr: 1.351e-06, eta: 11:53:37, time: 0.538, data_time: 0.006, memory: 58091, decode.loss_ce: 0.2319, decode.acc_seg: 89.7882, aux.loss_ce: 0.1976, aux.acc_seg: 83.2866, loss: 0.4295 2022-05-06 00:58:59,269 - mmseg - INFO - Iter [4800/80000] lr: 1.350e-06, eta: 11:52:49, time: 0.544, data_time: 0.006, memory: 58091, decode.loss_ce: 0.2229, decode.acc_seg: 90.2503, aux.loss_ce: 0.1874, aux.acc_seg: 85.0507, loss: 0.4103 2022-05-06 00:59:26,233 - mmseg - INFO - Iter [4850/80000] lr: 1.349e-06, eta: 11:51:58, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2177, decode.acc_seg: 89.9323, aux.loss_ce: 0.1846, aux.acc_seg: 84.5657, loss: 0.4023 2022-05-06 00:59:53,209 - mmseg - INFO - Iter [4900/80000] lr: 1.348e-06, eta: 11:51:07, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2327, decode.acc_seg: 89.9132, aux.loss_ce: 0.1984, aux.acc_seg: 84.0577, loss: 0.4311 2022-05-06 01:00:20,060 - mmseg - INFO - Iter [4950/80000] lr: 1.347e-06, eta: 11:50:15, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2137, decode.acc_seg: 90.3704, aux.loss_ce: 0.1864, aux.acc_seg: 84.6444, loss: 0.4002 2022-05-06 01:00:49,429 - mmseg - INFO - Saving checkpoint at 5000 iterations 2022-05-06 01:01:09,908 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:01:09,915 - mmseg - INFO - Iter [5000/80000] lr: 1.346e-06, eta: 11:55:07, time: 0.995, data_time: 0.054, memory: 58091, decode.loss_ce: 0.2291, decode.acc_seg: 89.7362, aux.loss_ce: 0.1930, aux.acc_seg: 83.5693, loss: 0.4221 2022-05-06 01:01:37,693 - mmseg - INFO - Iter [5050/80000] lr: 1.345e-06, eta: 11:54:27, time: 0.557, data_time: 0.007, memory: 58091, decode.loss_ce: 0.2103, decode.acc_seg: 91.1174, aux.loss_ce: 0.1854, aux.acc_seg: 85.0033, loss: 0.3958 2022-05-06 01:02:05,099 - mmseg - INFO - Iter [5100/80000] lr: 1.344e-06, eta: 11:53:41, time: 0.548, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2055, decode.acc_seg: 90.8088, aux.loss_ce: 0.1790, aux.acc_seg: 85.0206, loss: 0.3845 2022-05-06 01:02:31,831 - mmseg - INFO - Iter [5150/80000] lr: 1.343e-06, eta: 11:52:46, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2018, decode.acc_seg: 90.9888, aux.loss_ce: 0.1783, aux.acc_seg: 84.7394, loss: 0.3801 2022-05-06 01:02:58,647 - mmseg - INFO - Iter [5200/80000] lr: 1.342e-06, eta: 11:51:52, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2024, decode.acc_seg: 91.2572, aux.loss_ce: 0.1851, aux.acc_seg: 85.1058, loss: 0.3876 2022-05-06 01:03:25,430 - mmseg - INFO - Iter [5250/80000] lr: 1.342e-06, eta: 11:50:58, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2138, decode.acc_seg: 90.7498, aux.loss_ce: 0.1724, aux.acc_seg: 85.6669, loss: 0.3862 2022-05-06 01:03:52,375 - mmseg - INFO - Iter [5300/80000] lr: 1.341e-06, eta: 11:50:07, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2162, decode.acc_seg: 90.3686, aux.loss_ce: 0.1769, aux.acc_seg: 85.3207, loss: 0.3931 2022-05-06 01:04:22,235 - mmseg - INFO - Iter [5350/80000] lr: 1.340e-06, eta: 11:49:58, time: 0.597, data_time: 0.051, memory: 58091, decode.loss_ce: 0.2163, decode.acc_seg: 90.5022, aux.loss_ce: 0.1748, aux.acc_seg: 85.3444, loss: 0.3910 2022-05-06 01:04:49,086 - mmseg - INFO - Iter [5400/80000] lr: 1.339e-06, eta: 11:49:06, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1933, decode.acc_seg: 91.4477, aux.loss_ce: 0.1668, aux.acc_seg: 86.6312, loss: 0.3602 2022-05-06 01:05:16,031 - mmseg - INFO - Iter [5450/80000] lr: 1.338e-06, eta: 11:48:16, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2001, decode.acc_seg: 91.3801, aux.loss_ce: 0.1653, aux.acc_seg: 86.2292, loss: 0.3654 2022-05-06 01:05:43,380 - mmseg - INFO - Iter [5500/80000] lr: 1.337e-06, eta: 11:47:32, time: 0.547, data_time: 0.006, memory: 58091, decode.loss_ce: 0.2019, decode.acc_seg: 91.5482, aux.loss_ce: 0.1674, aux.acc_seg: 86.3691, loss: 0.3693 2022-05-06 01:06:10,206 - mmseg - INFO - Iter [5550/80000] lr: 1.336e-06, eta: 11:46:41, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2127, decode.acc_seg: 91.4051, aux.loss_ce: 0.1749, aux.acc_seg: 86.0629, loss: 0.3877 2022-05-06 01:06:37,151 - mmseg - INFO - Iter [5600/80000] lr: 1.335e-06, eta: 11:45:52, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1965, decode.acc_seg: 91.3204, aux.loss_ce: 0.1707, aux.acc_seg: 85.4515, loss: 0.3673 2022-05-06 01:07:06,924 - mmseg - INFO - Iter [5650/80000] lr: 1.334e-06, eta: 11:45:41, time: 0.595, data_time: 0.058, memory: 58091, decode.loss_ce: 0.2015, decode.acc_seg: 90.7920, aux.loss_ce: 0.1575, aux.acc_seg: 86.0583, loss: 0.3590 2022-05-06 01:07:33,941 - mmseg - INFO - Iter [5700/80000] lr: 1.334e-06, eta: 11:44:53, time: 0.540, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1808, decode.acc_seg: 92.2795, aux.loss_ce: 0.1560, aux.acc_seg: 86.4991, loss: 0.3368 2022-05-06 01:08:00,680 - mmseg - INFO - Iter [5750/80000] lr: 1.333e-06, eta: 11:44:03, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1892, decode.acc_seg: 92.0826, aux.loss_ce: 0.1614, aux.acc_seg: 86.4028, loss: 0.3506 2022-05-06 01:08:27,843 - mmseg - INFO - Iter [5800/80000] lr: 1.332e-06, eta: 11:43:18, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1927, decode.acc_seg: 91.4707, aux.loss_ce: 0.1611, aux.acc_seg: 86.4989, loss: 0.3538 2022-05-06 01:08:55,007 - mmseg - INFO - Iter [5850/80000] lr: 1.331e-06, eta: 11:42:33, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2002, decode.acc_seg: 91.2966, aux.loss_ce: 0.1698, aux.acc_seg: 85.5539, loss: 0.3700 2022-05-06 01:09:21,902 - mmseg - INFO - Iter [5900/80000] lr: 1.330e-06, eta: 11:41:46, time: 0.538, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1985, decode.acc_seg: 91.0027, aux.loss_ce: 0.1526, aux.acc_seg: 86.4212, loss: 0.3511 2022-05-06 01:09:51,339 - mmseg - INFO - Iter [5950/80000] lr: 1.329e-06, eta: 11:41:30, time: 0.589, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1789, decode.acc_seg: 91.9786, aux.loss_ce: 0.1479, aux.acc_seg: 86.8927, loss: 0.3268 2022-05-06 01:10:18,671 - mmseg - INFO - Saving checkpoint at 6000 iterations 2022-05-06 01:10:39,132 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:10:39,134 - mmseg - INFO - Iter [6000/80000] lr: 1.328e-06, eta: 11:45:00, time: 0.955, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1791, decode.acc_seg: 92.2401, aux.loss_ce: 0.1480, aux.acc_seg: 87.2885, loss: 0.3271 2022-05-06 01:11:06,691 - mmseg - INFO - Iter [6050/80000] lr: 1.327e-06, eta: 11:44:19, time: 0.552, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1842, decode.acc_seg: 91.7608, aux.loss_ce: 0.1535, aux.acc_seg: 86.3624, loss: 0.3377 2022-05-06 01:11:33,748 - mmseg - INFO - Iter [6100/80000] lr: 1.326e-06, eta: 11:43:32, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1729, decode.acc_seg: 92.5024, aux.loss_ce: 0.1498, aux.acc_seg: 87.5396, loss: 0.3227 2022-05-06 01:12:00,645 - mmseg - INFO - Iter [6150/80000] lr: 1.325e-06, eta: 11:42:44, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.2073, decode.acc_seg: 91.1708, aux.loss_ce: 0.1565, aux.acc_seg: 86.6659, loss: 0.3639 2022-05-06 01:12:27,412 - mmseg - INFO - Iter [6200/80000] lr: 1.325e-06, eta: 11:41:54, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1777, decode.acc_seg: 92.2743, aux.loss_ce: 0.1496, aux.acc_seg: 86.7864, loss: 0.3272 2022-05-06 01:12:56,748 - mmseg - INFO - Iter [6250/80000] lr: 1.324e-06, eta: 11:41:35, time: 0.586, data_time: 0.055, memory: 58091, decode.loss_ce: 0.1708, decode.acc_seg: 92.1949, aux.loss_ce: 0.1422, aux.acc_seg: 87.1980, loss: 0.3131 2022-05-06 01:13:23,921 - mmseg - INFO - Iter [6300/80000] lr: 1.323e-06, eta: 11:40:50, time: 0.544, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1673, decode.acc_seg: 92.4498, aux.loss_ce: 0.1423, aux.acc_seg: 87.6790, loss: 0.3096 2022-05-06 01:13:50,862 - mmseg - INFO - Iter [6350/80000] lr: 1.322e-06, eta: 11:40:03, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1739, decode.acc_seg: 92.5139, aux.loss_ce: 0.1405, aux.acc_seg: 87.4901, loss: 0.3145 2022-05-06 01:14:17,938 - mmseg - INFO - Iter [6400/80000] lr: 1.321e-06, eta: 11:39:18, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1790, decode.acc_seg: 92.1224, aux.loss_ce: 0.1459, aux.acc_seg: 87.0515, loss: 0.3249 2022-05-06 01:14:44,941 - mmseg - INFO - Iter [6450/80000] lr: 1.320e-06, eta: 11:38:32, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1716, decode.acc_seg: 92.4834, aux.loss_ce: 0.1399, aux.acc_seg: 87.8416, loss: 0.3115 2022-05-06 01:15:11,706 - mmseg - INFO - Iter [6500/80000] lr: 1.319e-06, eta: 11:37:45, time: 0.536, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1630, decode.acc_seg: 92.8713, aux.loss_ce: 0.1367, aux.acc_seg: 87.9269, loss: 0.2998 2022-05-06 01:15:38,585 - mmseg - INFO - Iter [6550/80000] lr: 1.318e-06, eta: 11:36:58, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1842, decode.acc_seg: 91.9836, aux.loss_ce: 0.1451, aux.acc_seg: 87.4418, loss: 0.3293 2022-05-06 01:16:07,901 - mmseg - INFO - Iter [6600/80000] lr: 1.317e-06, eta: 11:36:39, time: 0.586, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1678, decode.acc_seg: 92.4248, aux.loss_ce: 0.1289, aux.acc_seg: 88.4488, loss: 0.2967 2022-05-06 01:16:34,806 - mmseg - INFO - Iter [6650/80000] lr: 1.316e-06, eta: 11:35:54, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1632, decode.acc_seg: 92.5966, aux.loss_ce: 0.1369, aux.acc_seg: 87.4778, loss: 0.3002 2022-05-06 01:17:01,428 - mmseg - INFO - Iter [6700/80000] lr: 1.316e-06, eta: 11:35:05, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1655, decode.acc_seg: 92.5613, aux.loss_ce: 0.1319, aux.acc_seg: 88.4645, loss: 0.2974 2022-05-06 01:17:28,387 - mmseg - INFO - Iter [6750/80000] lr: 1.315e-06, eta: 11:34:20, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1681, decode.acc_seg: 92.3985, aux.loss_ce: 0.1319, aux.acc_seg: 87.7854, loss: 0.3000 2022-05-06 01:17:55,788 - mmseg - INFO - Iter [6800/80000] lr: 1.314e-06, eta: 11:33:41, time: 0.548, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1602, decode.acc_seg: 92.7289, aux.loss_ce: 0.1307, aux.acc_seg: 87.2173, loss: 0.2909 2022-05-06 01:18:22,625 - mmseg - INFO - Iter [6850/80000] lr: 1.313e-06, eta: 11:32:55, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1692, decode.acc_seg: 92.4337, aux.loss_ce: 0.1322, aux.acc_seg: 87.7779, loss: 0.3013 2022-05-06 01:18:51,988 - mmseg - INFO - Iter [6900/80000] lr: 1.312e-06, eta: 11:32:37, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1558, decode.acc_seg: 93.1300, aux.loss_ce: 0.1317, aux.acc_seg: 88.2801, loss: 0.2875 2022-05-06 01:19:18,637 - mmseg - INFO - Iter [6950/80000] lr: 1.311e-06, eta: 11:31:50, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1640, decode.acc_seg: 92.6645, aux.loss_ce: 0.1304, aux.acc_seg: 88.0633, loss: 0.2944 2022-05-06 01:19:45,870 - mmseg - INFO - Saving checkpoint at 7000 iterations 2022-05-06 01:20:06,507 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:20:06,519 - mmseg - INFO - Iter [7000/80000] lr: 1.310e-06, eta: 11:34:43, time: 0.955, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1627, decode.acc_seg: 92.5704, aux.loss_ce: 0.1298, aux.acc_seg: 87.8702, loss: 0.2925 2022-05-06 01:20:33,994 - mmseg - INFO - Iter [7050/80000] lr: 1.309e-06, eta: 11:34:05, time: 0.552, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1607, decode.acc_seg: 92.7601, aux.loss_ce: 0.1272, aux.acc_seg: 88.2622, loss: 0.2878 2022-05-06 01:21:00,853 - mmseg - INFO - Iter [7100/80000] lr: 1.308e-06, eta: 11:33:19, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1900, decode.acc_seg: 91.5027, aux.loss_ce: 0.1406, aux.acc_seg: 86.5760, loss: 0.3306 2022-05-06 01:21:27,712 - mmseg - INFO - Iter [7150/80000] lr: 1.307e-06, eta: 11:32:33, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1642, decode.acc_seg: 92.3558, aux.loss_ce: 0.1243, aux.acc_seg: 88.1825, loss: 0.2885 2022-05-06 01:21:57,459 - mmseg - INFO - Iter [7200/80000] lr: 1.307e-06, eta: 11:32:17, time: 0.594, data_time: 0.054, memory: 58091, decode.loss_ce: 0.1544, decode.acc_seg: 92.9112, aux.loss_ce: 0.1283, aux.acc_seg: 87.8912, loss: 0.2827 2022-05-06 01:22:24,363 - mmseg - INFO - Iter [7250/80000] lr: 1.306e-06, eta: 11:31:32, time: 0.539, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1575, decode.acc_seg: 92.9776, aux.loss_ce: 0.1228, aux.acc_seg: 88.8066, loss: 0.2803 2022-05-06 01:22:51,376 - mmseg - INFO - Iter [7300/80000] lr: 1.305e-06, eta: 11:30:49, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1490, decode.acc_seg: 93.3741, aux.loss_ce: 0.1182, aux.acc_seg: 88.7800, loss: 0.2672 2022-05-06 01:23:18,732 - mmseg - INFO - Iter [7350/80000] lr: 1.304e-06, eta: 11:30:09, time: 0.547, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1516, decode.acc_seg: 92.9611, aux.loss_ce: 0.1220, aux.acc_seg: 88.6113, loss: 0.2736 2022-05-06 01:23:45,472 - mmseg - INFO - Iter [7400/80000] lr: 1.303e-06, eta: 11:29:23, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1500, decode.acc_seg: 92.8797, aux.loss_ce: 0.1117, aux.acc_seg: 89.5331, loss: 0.2616 2022-05-06 01:24:12,137 - mmseg - INFO - Iter [7450/80000] lr: 1.302e-06, eta: 11:28:37, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1584, decode.acc_seg: 92.6829, aux.loss_ce: 0.1275, aux.acc_seg: 87.8238, loss: 0.2860 2022-05-06 01:24:42,010 - mmseg - INFO - Iter [7500/80000] lr: 1.301e-06, eta: 11:28:22, time: 0.597, data_time: 0.050, memory: 58091, decode.loss_ce: 0.1427, decode.acc_seg: 93.4551, aux.loss_ce: 0.1143, aux.acc_seg: 89.4129, loss: 0.2570 2022-05-06 01:25:08,952 - mmseg - INFO - Iter [7550/80000] lr: 1.300e-06, eta: 11:27:39, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1555, decode.acc_seg: 93.0282, aux.loss_ce: 0.1278, aux.acc_seg: 88.1109, loss: 0.2833 2022-05-06 01:25:35,680 - mmseg - INFO - Iter [7600/80000] lr: 1.299e-06, eta: 11:26:54, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1453, decode.acc_seg: 93.3842, aux.loss_ce: 0.1154, aux.acc_seg: 89.2329, loss: 0.2607 2022-05-06 01:26:02,579 - mmseg - INFO - Iter [7650/80000] lr: 1.299e-06, eta: 11:26:10, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1558, decode.acc_seg: 93.0677, aux.loss_ce: 0.1240, aux.acc_seg: 88.1605, loss: 0.2798 2022-05-06 01:26:29,408 - mmseg - INFO - Iter [7700/80000] lr: 1.298e-06, eta: 11:25:27, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1488, decode.acc_seg: 93.2091, aux.loss_ce: 0.1108, aux.acc_seg: 89.0593, loss: 0.2597 2022-05-06 01:26:56,145 - mmseg - INFO - Iter [7750/80000] lr: 1.297e-06, eta: 11:24:42, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1565, decode.acc_seg: 93.1805, aux.loss_ce: 0.1194, aux.acc_seg: 89.0583, loss: 0.2759 2022-05-06 01:27:22,829 - mmseg - INFO - Iter [7800/80000] lr: 1.296e-06, eta: 11:23:58, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1539, decode.acc_seg: 93.2130, aux.loss_ce: 0.1205, aux.acc_seg: 88.8642, loss: 0.2743 2022-05-06 01:27:52,162 - mmseg - INFO - Iter [7850/80000] lr: 1.295e-06, eta: 11:23:38, time: 0.587, data_time: 0.052, memory: 58091, decode.loss_ce: 0.1380, decode.acc_seg: 93.8721, aux.loss_ce: 0.1087, aux.acc_seg: 90.1721, loss: 0.2467 2022-05-06 01:28:18,883 - mmseg - INFO - Iter [7900/80000] lr: 1.294e-06, eta: 11:22:53, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1330, decode.acc_seg: 93.9102, aux.loss_ce: 0.1116, aux.acc_seg: 89.2751, loss: 0.2445 2022-05-06 01:28:45,750 - mmseg - INFO - Iter [7950/80000] lr: 1.293e-06, eta: 11:22:11, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1356, decode.acc_seg: 93.8310, aux.loss_ce: 0.1118, aux.acc_seg: 89.4119, loss: 0.2474 2022-05-06 01:29:12,763 - mmseg - INFO - Saving checkpoint at 8000 iterations 2022-05-06 01:29:32,677 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:29:32,686 - mmseg - INFO - Iter [8000/80000] lr: 1.292e-06, eta: 11:24:29, time: 0.938, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1394, decode.acc_seg: 93.6938, aux.loss_ce: 0.1090, aux.acc_seg: 89.7032, loss: 0.2484 2022-05-06 01:34:11,067 - mmseg - INFO - per class results: 2022-05-06 01:34:11,094 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 91.46 | 97.3 | | bag | 45.95 | 60.15 | | bed | 38.41 | 58.18 | | bedclothes | 42.67 | 60.17 | | bench | 29.75 | 42.16 | | bicycle | 79.51 | 92.5 | | bird | 93.1 | 97.61 | | boat | 84.04 | 92.95 | | book | 58.07 | 70.0 | | bottle | 87.47 | 95.37 | | building | 68.42 | 82.61 | | bus | 94.11 | 97.63 | | cabinet | 53.01 | 73.52 | | car | 92.52 | 96.5 | | cat | 93.07 | 97.28 | | ceiling | 61.24 | 78.04 | | chair | 65.37 | 77.39 | | cloth | 25.2 | 32.75 | | computer | 57.84 | 72.87 | | cow | 93.51 | 98.85 | | cup | 45.08 | 60.52 | | curtain | 59.83 | 75.18 | | dog | 90.93 | 96.42 | | door | 38.0 | 56.24 | | fence | 41.65 | 51.38 | | floor | 77.01 | 86.55 | | flower | 34.88 | 49.32 | | food | 36.11 | 45.23 | | grass | 81.61 | 87.9 | | ground | 57.58 | 72.87 | | horse | 93.34 | 97.94 | | keyboard | 83.84 | 92.6 | | light | 55.81 | 72.2 | | motorbike | 89.34 | 96.68 | | mountain | 55.26 | 75.46 | | mouse | 0.0 | 0.0 | | person | 89.83 | 95.51 | | plate | 24.1 | 28.31 | | platform | 59.71 | 80.7 | | pottedplant | 79.1 | 91.88 | | road | 51.27 | 64.5 | | rock | 54.14 | 62.58 | | sheep | 92.06 | 97.98 | | shelves | 34.97 | 43.55 | | sidewalk | 24.08 | 63.94 | | sign | 51.54 | 61.04 | | sky | 94.32 | 96.41 | | snow | 73.06 | 91.01 | | sofa | 65.31 | 82.55 | | table | 71.29 | 84.89 | | track | 66.44 | 78.86 | | train | 92.24 | 97.75 | | tree | 80.6 | 90.05 | | truck | 49.36 | 58.38 | | tvmonitor | 89.88 | 94.12 | | wall | 73.83 | 83.38 | | water | 91.57 | 95.86 | | window | 47.78 | 67.25 | | wood | 26.28 | 34.64 | +-------------+-------+-------+ 2022-05-06 01:34:11,094 - mmseg - INFO - Summary: 2022-05-06 01:34:11,094 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 85.96 | 64.03 | 75.18 | +-------+-------+-------+ 2022-05-06 01:34:33,211 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_8000.pth. 2022-05-06 01:34:33,224 - mmseg - INFO - Best mIoU is 0.6403 at 8000 iter. 2022-05-06 01:34:33,251 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:34:33,252 - mmseg - INFO - Iter(val) [638] aAcc: 0.8596, mIoU: 0.6403, mAcc: 0.7518, IoU.aeroplane: 0.9146, IoU.bag: 0.4595, IoU.bed: 0.3841, IoU.bedclothes: 0.4267, IoU.bench: 0.2975, IoU.bicycle: 0.7951, IoU.bird: 0.9310, IoU.boat: 0.8404, IoU.book: 0.5807, IoU.bottle: 0.8747, IoU.building: 0.6842, IoU.bus: 0.9411, IoU.cabinet: 0.5301, IoU.car: 0.9252, IoU.cat: 0.9307, IoU.ceiling: 0.6124, IoU.chair: 0.6537, IoU.cloth: 0.2520, IoU.computer: 0.5784, IoU.cow: 0.9351, IoU.cup: 0.4508, IoU.curtain: 0.5983, IoU.dog: 0.9093, IoU.door: 0.3800, IoU.fence: 0.4165, IoU.floor: 0.7701, IoU.flower: 0.3488, IoU.food: 0.3611, IoU.grass: 0.8161, IoU.ground: 0.5758, IoU.horse: 0.9334, IoU.keyboard: 0.8384, IoU.light: 0.5581, IoU.motorbike: 0.8934, IoU.mountain: 0.5526, IoU.mouse: 0.0000, IoU.person: 0.8983, IoU.plate: 0.2410, IoU.platform: 0.5971, IoU.pottedplant: 0.7910, IoU.road: 0.5127, IoU.rock: 0.5414, IoU.sheep: 0.9206, IoU.shelves: 0.3497, IoU.sidewalk: 0.2408, IoU.sign: 0.5154, IoU.sky: 0.9432, IoU.snow: 0.7306, IoU.sofa: 0.6531, IoU.table: 0.7129, IoU.track: 0.6644, IoU.train: 0.9224, IoU.tree: 0.8060, IoU.truck: 0.4936, IoU.tvmonitor: 0.8988, IoU.wall: 0.7383, IoU.water: 0.9157, IoU.window: 0.4778, IoU.wood: 0.2628, Acc.aeroplane: 0.9730, Acc.bag: 0.6015, Acc.bed: 0.5818, Acc.bedclothes: 0.6017, Acc.bench: 0.4216, Acc.bicycle: 0.9250, Acc.bird: 0.9761, Acc.boat: 0.9295, Acc.book: 0.7000, Acc.bottle: 0.9537, Acc.building: 0.8261, Acc.bus: 0.9763, Acc.cabinet: 0.7352, Acc.car: 0.9650, Acc.cat: 0.9728, Acc.ceiling: 0.7804, Acc.chair: 0.7739, Acc.cloth: 0.3275, Acc.computer: 0.7287, Acc.cow: 0.9885, Acc.cup: 0.6052, Acc.curtain: 0.7518, Acc.dog: 0.9642, Acc.door: 0.5624, Acc.fence: 0.5138, Acc.floor: 0.8655, Acc.flower: 0.4932, Acc.food: 0.4523, Acc.grass: 0.8790, Acc.ground: 0.7287, Acc.horse: 0.9794, Acc.keyboard: 0.9260, Acc.light: 0.7220, Acc.motorbike: 0.9668, Acc.mountain: 0.7546, Acc.mouse: 0.0000, Acc.person: 0.9551, Acc.plate: 0.2831, Acc.platform: 0.8070, Acc.pottedplant: 0.9188, Acc.road: 0.6450, Acc.rock: 0.6258, Acc.sheep: 0.9798, Acc.shelves: 0.4355, Acc.sidewalk: 0.6394, Acc.sign: 0.6104, Acc.sky: 0.9641, Acc.snow: 0.9101, Acc.sofa: 0.8255, Acc.table: 0.8489, Acc.track: 0.7886, Acc.train: 0.9775, Acc.tree: 0.9005, Acc.truck: 0.5838, Acc.tvmonitor: 0.9412, Acc.wall: 0.8338, Acc.water: 0.9586, Acc.window: 0.6725, Acc.wood: 0.3464 2022-05-06 01:35:00,582 - mmseg - INFO - Iter [8050/80000] lr: 1.291e-06, eta: 12:08:37, time: 6.559, data_time: 6.018, memory: 58091, decode.loss_ce: 0.1517, decode.acc_seg: 93.0973, aux.loss_ce: 0.1088, aux.acc_seg: 89.2683, loss: 0.2605 2022-05-06 01:35:27,484 - mmseg - INFO - Iter [8100/80000] lr: 1.290e-06, eta: 12:07:36, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1620, decode.acc_seg: 92.6692, aux.loss_ce: 0.1193, aux.acc_seg: 88.5532, loss: 0.2812 2022-05-06 01:35:56,514 - mmseg - INFO - Iter [8150/80000] lr: 1.290e-06, eta: 12:06:53, time: 0.580, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1480, decode.acc_seg: 93.0975, aux.loss_ce: 0.1125, aux.acc_seg: 88.9617, loss: 0.2605 2022-05-06 01:36:23,201 - mmseg - INFO - Iter [8200/80000] lr: 1.289e-06, eta: 12:05:51, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1377, decode.acc_seg: 93.7830, aux.loss_ce: 0.1071, aux.acc_seg: 90.0483, loss: 0.2448 2022-05-06 01:36:49,988 - mmseg - INFO - Iter [8250/80000] lr: 1.288e-06, eta: 12:04:50, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1574, decode.acc_seg: 92.7016, aux.loss_ce: 0.1181, aux.acc_seg: 88.0309, loss: 0.2755 2022-05-06 01:37:16,795 - mmseg - INFO - Iter [8300/80000] lr: 1.287e-06, eta: 12:03:49, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1399, decode.acc_seg: 93.8382, aux.loss_ce: 0.1028, aux.acc_seg: 90.2781, loss: 0.2428 2022-05-06 01:37:43,706 - mmseg - INFO - Iter [8350/80000] lr: 1.286e-06, eta: 12:02:50, time: 0.538, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1474, decode.acc_seg: 93.4214, aux.loss_ce: 0.1073, aux.acc_seg: 89.9770, loss: 0.2546 2022-05-06 01:38:10,525 - mmseg - INFO - Iter [8400/80000] lr: 1.285e-06, eta: 12:01:51, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1509, decode.acc_seg: 93.1214, aux.loss_ce: 0.1130, aux.acc_seg: 89.0310, loss: 0.2639 2022-05-06 01:38:40,168 - mmseg - INFO - Iter [8450/80000] lr: 1.284e-06, eta: 12:01:14, time: 0.591, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1447, decode.acc_seg: 93.6444, aux.loss_ce: 0.1099, aux.acc_seg: 89.5252, loss: 0.2546 2022-05-06 01:39:07,036 - mmseg - INFO - Iter [8500/80000] lr: 1.283e-06, eta: 12:00:17, time: 0.540, data_time: 0.008, memory: 58091, decode.loss_ce: 0.1401, decode.acc_seg: 93.6231, aux.loss_ce: 0.1078, aux.acc_seg: 89.5294, loss: 0.2479 2022-05-06 01:39:33,788 - mmseg - INFO - Iter [8550/80000] lr: 1.282e-06, eta: 11:59:17, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1330, decode.acc_seg: 93.8097, aux.loss_ce: 0.0987, aux.acc_seg: 90.6481, loss: 0.2317 2022-05-06 01:40:00,653 - mmseg - INFO - Iter [8600/80000] lr: 1.281e-06, eta: 11:58:19, time: 0.537, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1363, decode.acc_seg: 93.9033, aux.loss_ce: 0.1029, aux.acc_seg: 89.8360, loss: 0.2392 2022-05-06 01:40:27,311 - mmseg - INFO - Iter [8650/80000] lr: 1.281e-06, eta: 11:57:20, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1294, decode.acc_seg: 93.9568, aux.loss_ce: 0.0997, aux.acc_seg: 90.2979, loss: 0.2292 2022-05-06 01:40:54,058 - mmseg - INFO - Iter [8700/80000] lr: 1.280e-06, eta: 11:56:22, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1399, decode.acc_seg: 93.7605, aux.loss_ce: 0.1024, aux.acc_seg: 89.8572, loss: 0.2423 2022-05-06 01:41:23,291 - mmseg - INFO - Iter [8750/80000] lr: 1.279e-06, eta: 11:55:44, time: 0.584, data_time: 0.052, memory: 58091, decode.loss_ce: 0.1364, decode.acc_seg: 93.9707, aux.loss_ce: 0.1006, aux.acc_seg: 90.4736, loss: 0.2369 2022-05-06 01:41:50,141 - mmseg - INFO - Iter [8800/80000] lr: 1.278e-06, eta: 11:54:48, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1331, decode.acc_seg: 93.8693, aux.loss_ce: 0.1012, aux.acc_seg: 89.6645, loss: 0.2343 2022-05-06 01:42:16,896 - mmseg - INFO - Iter [8850/80000] lr: 1.277e-06, eta: 11:53:51, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1396, decode.acc_seg: 93.4999, aux.loss_ce: 0.1049, aux.acc_seg: 89.3101, loss: 0.2445 2022-05-06 01:42:43,431 - mmseg - INFO - Iter [8900/80000] lr: 1.276e-06, eta: 11:52:52, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1217, decode.acc_seg: 94.1770, aux.loss_ce: 0.0915, aux.acc_seg: 90.7668, loss: 0.2132 2022-05-06 01:43:10,154 - mmseg - INFO - Iter [8950/80000] lr: 1.275e-06, eta: 11:51:55, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1356, decode.acc_seg: 93.8046, aux.loss_ce: 0.1005, aux.acc_seg: 90.3072, loss: 0.2361 2022-05-06 01:43:36,854 - mmseg - INFO - Saving checkpoint at 9000 iterations 2022-05-06 01:43:56,929 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:43:56,944 - mmseg - INFO - Iter [9000/80000] lr: 1.274e-06, eta: 11:53:36, time: 0.932, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1425, decode.acc_seg: 93.5936, aux.loss_ce: 0.1058, aux.acc_seg: 89.8687, loss: 0.2483 2022-05-06 01:44:27,561 - mmseg - INFO - Iter [9050/80000] lr: 1.273e-06, eta: 11:53:11, time: 0.616, data_time: 0.074, memory: 58091, decode.loss_ce: 0.1372, decode.acc_seg: 93.7966, aux.loss_ce: 0.1046, aux.acc_seg: 90.1200, loss: 0.2419 2022-05-06 01:44:54,611 - mmseg - INFO - Iter [9100/80000] lr: 1.272e-06, eta: 11:52:16, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1246, decode.acc_seg: 94.2413, aux.loss_ce: 0.0969, aux.acc_seg: 90.6985, loss: 0.2216 2022-05-06 01:45:21,127 - mmseg - INFO - Iter [9150/80000] lr: 1.272e-06, eta: 11:51:18, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1404, decode.acc_seg: 93.6449, aux.loss_ce: 0.1003, aux.acc_seg: 90.2483, loss: 0.2407 2022-05-06 01:45:47,851 - mmseg - INFO - Iter [9200/80000] lr: 1.271e-06, eta: 11:50:22, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1200, decode.acc_seg: 94.3941, aux.loss_ce: 0.0904, aux.acc_seg: 91.2143, loss: 0.2104 2022-05-06 01:46:14,465 - mmseg - INFO - Iter [9250/80000] lr: 1.270e-06, eta: 11:49:25, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1297, decode.acc_seg: 94.1361, aux.loss_ce: 0.0946, aux.acc_seg: 90.7556, loss: 0.2243 2022-05-06 01:46:41,502 - mmseg - INFO - Iter [9300/80000] lr: 1.269e-06, eta: 11:48:32, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1222, decode.acc_seg: 94.4083, aux.loss_ce: 0.0928, aux.acc_seg: 90.7463, loss: 0.2150 2022-05-06 01:47:08,545 - mmseg - INFO - Iter [9350/80000] lr: 1.268e-06, eta: 11:47:39, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1425, decode.acc_seg: 93.1360, aux.loss_ce: 0.0997, aux.acc_seg: 89.7008, loss: 0.2421 2022-05-06 01:47:38,359 - mmseg - INFO - Iter [9400/80000] lr: 1.267e-06, eta: 11:47:06, time: 0.595, data_time: 0.055, memory: 58091, decode.loss_ce: 0.1305, decode.acc_seg: 93.8752, aux.loss_ce: 0.0956, aux.acc_seg: 90.2566, loss: 0.2261 2022-05-06 01:48:05,586 - mmseg - INFO - Iter [9450/80000] lr: 1.266e-06, eta: 11:46:16, time: 0.546, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1320, decode.acc_seg: 94.0952, aux.loss_ce: 0.0928, aux.acc_seg: 91.2716, loss: 0.2248 2022-05-06 01:48:32,506 - mmseg - INFO - Iter [9500/80000] lr: 1.265e-06, eta: 11:45:23, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1266, decode.acc_seg: 94.1185, aux.loss_ce: 0.0932, aux.acc_seg: 90.7556, loss: 0.2198 2022-05-06 01:48:59,547 - mmseg - INFO - Iter [9550/80000] lr: 1.264e-06, eta: 11:44:31, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1268, decode.acc_seg: 94.1611, aux.loss_ce: 0.0933, aux.acc_seg: 90.7460, loss: 0.2201 2022-05-06 01:49:26,261 - mmseg - INFO - Iter [9600/80000] lr: 1.264e-06, eta: 11:43:37, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1294, decode.acc_seg: 93.9759, aux.loss_ce: 0.0973, aux.acc_seg: 90.4891, loss: 0.2267 2022-05-06 01:49:53,167 - mmseg - INFO - Iter [9650/80000] lr: 1.263e-06, eta: 11:42:44, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1295, decode.acc_seg: 94.1050, aux.loss_ce: 0.0948, aux.acc_seg: 90.6546, loss: 0.2243 2022-05-06 01:50:22,311 - mmseg - INFO - Iter [9700/80000] lr: 1.262e-06, eta: 11:42:08, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1142, decode.acc_seg: 94.5150, aux.loss_ce: 0.0908, aux.acc_seg: 90.7820, loss: 0.2051 2022-05-06 01:50:49,431 - mmseg - INFO - Iter [9750/80000] lr: 1.261e-06, eta: 11:41:18, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1169, decode.acc_seg: 94.5907, aux.loss_ce: 0.0916, aux.acc_seg: 90.9852, loss: 0.2086 2022-05-06 01:51:15,955 - mmseg - INFO - Iter [9800/80000] lr: 1.260e-06, eta: 11:40:24, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1206, decode.acc_seg: 94.3436, aux.loss_ce: 0.0854, aux.acc_seg: 91.3146, loss: 0.2060 2022-05-06 01:51:42,718 - mmseg - INFO - Iter [9850/80000] lr: 1.259e-06, eta: 11:39:31, time: 0.535, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1205, decode.acc_seg: 94.2986, aux.loss_ce: 0.0878, aux.acc_seg: 91.3452, loss: 0.2083 2022-05-06 01:52:09,385 - mmseg - INFO - Iter [9900/80000] lr: 1.258e-06, eta: 11:38:37, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1170, decode.acc_seg: 94.5692, aux.loss_ce: 0.0830, aux.acc_seg: 91.8658, loss: 0.2001 2022-05-06 01:52:36,077 - mmseg - INFO - Iter [9950/80000] lr: 1.257e-06, eta: 11:37:46, time: 0.536, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1353, decode.acc_seg: 93.7977, aux.loss_ce: 0.0978, aux.acc_seg: 90.4317, loss: 0.2331 2022-05-06 01:53:05,226 - mmseg - INFO - Saving checkpoint at 10000 iterations 2022-05-06 01:53:24,992 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 01:53:24,994 - mmseg - INFO - Iter [10000/80000] lr: 1.256e-06, eta: 11:39:29, time: 0.977, data_time: 0.050, memory: 58091, decode.loss_ce: 0.1263, decode.acc_seg: 94.0523, aux.loss_ce: 0.0858, aux.acc_seg: 91.1958, loss: 0.2121 2022-05-06 01:53:52,193 - mmseg - INFO - Iter [10050/80000] lr: 1.255e-06, eta: 11:38:40, time: 0.545, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1213, decode.acc_seg: 94.1351, aux.loss_ce: 0.0862, aux.acc_seg: 91.1808, loss: 0.2074 2022-05-06 01:54:18,970 - mmseg - INFO - Iter [10100/80000] lr: 1.255e-06, eta: 11:37:48, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1180, decode.acc_seg: 94.5427, aux.loss_ce: 0.0882, aux.acc_seg: 91.3782, loss: 0.2061 2022-05-06 01:54:46,069 - mmseg - INFO - Iter [10150/80000] lr: 1.254e-06, eta: 11:36:58, time: 0.542, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1215, decode.acc_seg: 94.3351, aux.loss_ce: 0.0908, aux.acc_seg: 91.0412, loss: 0.2123 2022-05-06 01:55:12,865 - mmseg - INFO - Iter [10200/80000] lr: 1.253e-06, eta: 11:36:07, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1180, decode.acc_seg: 94.4755, aux.loss_ce: 0.0869, aux.acc_seg: 91.3791, loss: 0.2049 2022-05-06 01:55:39,610 - mmseg - INFO - Iter [10250/80000] lr: 1.252e-06, eta: 11:35:15, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1114, decode.acc_seg: 94.8026, aux.loss_ce: 0.0828, aux.acc_seg: 91.6812, loss: 0.1943 2022-05-06 01:56:09,100 - mmseg - INFO - Iter [10300/80000] lr: 1.251e-06, eta: 11:34:42, time: 0.590, data_time: 0.054, memory: 58091, decode.loss_ce: 0.1160, decode.acc_seg: 94.4351, aux.loss_ce: 0.0851, aux.acc_seg: 91.3881, loss: 0.2010 2022-05-06 01:56:35,826 - mmseg - INFO - Iter [10350/80000] lr: 1.250e-06, eta: 11:33:51, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1142, decode.acc_seg: 94.4922, aux.loss_ce: 0.0806, aux.acc_seg: 91.6787, loss: 0.1948 2022-05-06 01:57:02,743 - mmseg - INFO - Iter [10400/80000] lr: 1.249e-06, eta: 11:33:01, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1094, decode.acc_seg: 94.8374, aux.loss_ce: 0.0794, aux.acc_seg: 91.9543, loss: 0.1888 2022-05-06 01:57:29,238 - mmseg - INFO - Iter [10450/80000] lr: 1.248e-06, eta: 11:32:09, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1124, decode.acc_seg: 94.5930, aux.loss_ce: 0.0837, aux.acc_seg: 91.3140, loss: 0.1961 2022-05-06 01:57:55,844 - mmseg - INFO - Iter [10500/80000] lr: 1.247e-06, eta: 11:31:18, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1209, decode.acc_seg: 94.3429, aux.loss_ce: 0.0882, aux.acc_seg: 91.3004, loss: 0.2091 2022-05-06 01:58:22,598 - mmseg - INFO - Iter [10550/80000] lr: 1.246e-06, eta: 11:30:27, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1095, decode.acc_seg: 94.8945, aux.loss_ce: 0.0834, aux.acc_seg: 91.9056, loss: 0.1930 2022-05-06 01:58:49,394 - mmseg - INFO - Iter [10600/80000] lr: 1.246e-06, eta: 11:29:38, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1252, decode.acc_seg: 94.0676, aux.loss_ce: 0.0871, aux.acc_seg: 91.1362, loss: 0.2123 2022-05-06 01:59:18,668 - mmseg - INFO - Iter [10650/80000] lr: 1.245e-06, eta: 11:29:05, time: 0.585, data_time: 0.052, memory: 58091, decode.loss_ce: 0.1057, decode.acc_seg: 95.1325, aux.loss_ce: 0.0758, aux.acc_seg: 92.4717, loss: 0.1814 2022-05-06 01:59:45,434 - mmseg - INFO - Iter [10700/80000] lr: 1.244e-06, eta: 11:28:15, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1155, decode.acc_seg: 94.8244, aux.loss_ce: 0.0844, aux.acc_seg: 91.8785, loss: 0.1998 2022-05-06 02:00:14,385 - mmseg - INFO - Iter [10750/80000] lr: 1.243e-06, eta: 11:27:40, time: 0.579, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1119, decode.acc_seg: 94.6465, aux.loss_ce: 0.0823, aux.acc_seg: 91.4657, loss: 0.1942 2022-05-06 02:00:41,517 - mmseg - INFO - Iter [10800/80000] lr: 1.242e-06, eta: 11:26:53, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1169, decode.acc_seg: 94.4363, aux.loss_ce: 0.0825, aux.acc_seg: 91.5100, loss: 0.1994 2022-05-06 02:01:08,513 - mmseg - INFO - Iter [10850/80000] lr: 1.241e-06, eta: 11:26:05, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1145, decode.acc_seg: 94.5408, aux.loss_ce: 0.0814, aux.acc_seg: 91.6260, loss: 0.1960 2022-05-06 02:01:35,097 - mmseg - INFO - Iter [10900/80000] lr: 1.240e-06, eta: 11:25:15, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1087, decode.acc_seg: 95.0373, aux.loss_ce: 0.0770, aux.acc_seg: 92.5943, loss: 0.1857 2022-05-06 02:02:04,686 - mmseg - INFO - Iter [10950/80000] lr: 1.239e-06, eta: 11:24:45, time: 0.591, data_time: 0.054, memory: 58091, decode.loss_ce: 0.1142, decode.acc_seg: 94.5756, aux.loss_ce: 0.0807, aux.acc_seg: 91.7304, loss: 0.1949 2022-05-06 02:02:31,366 - mmseg - INFO - Saving checkpoint at 11000 iterations 2022-05-06 02:02:52,919 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:02:52,927 - mmseg - INFO - Iter [11000/80000] lr: 1.238e-06, eta: 11:26:10, time: 0.963, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1200, decode.acc_seg: 94.7493, aux.loss_ce: 0.0830, aux.acc_seg: 92.1139, loss: 0.2029 2022-05-06 02:03:20,135 - mmseg - INFO - Iter [11050/80000] lr: 1.237e-06, eta: 11:25:25, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1145, decode.acc_seg: 94.4020, aux.loss_ce: 0.0789, aux.acc_seg: 91.5626, loss: 0.1934 2022-05-06 02:03:47,086 - mmseg - INFO - Iter [11100/80000] lr: 1.237e-06, eta: 11:24:37, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1055, decode.acc_seg: 95.1036, aux.loss_ce: 0.0762, aux.acc_seg: 92.3429, loss: 0.1817 2022-05-06 02:04:13,950 - mmseg - INFO - Iter [11150/80000] lr: 1.236e-06, eta: 11:23:49, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1100, decode.acc_seg: 94.8448, aux.loss_ce: 0.0784, aux.acc_seg: 92.1533, loss: 0.1884 2022-05-06 02:04:40,776 - mmseg - INFO - Iter [11200/80000] lr: 1.235e-06, eta: 11:23:01, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1133, decode.acc_seg: 94.6700, aux.loss_ce: 0.0778, aux.acc_seg: 91.9096, loss: 0.1911 2022-05-06 02:05:10,069 - mmseg - INFO - Iter [11250/80000] lr: 1.234e-06, eta: 11:22:28, time: 0.586, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1131, decode.acc_seg: 94.8286, aux.loss_ce: 0.0804, aux.acc_seg: 91.7423, loss: 0.1935 2022-05-06 02:05:36,841 - mmseg - INFO - Iter [11300/80000] lr: 1.233e-06, eta: 11:21:40, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1022, decode.acc_seg: 95.0711, aux.loss_ce: 0.0721, aux.acc_seg: 92.5578, loss: 0.1743 2022-05-06 02:06:03,658 - mmseg - INFO - Iter [11350/80000] lr: 1.232e-06, eta: 11:20:53, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1072, decode.acc_seg: 94.8021, aux.loss_ce: 0.0786, aux.acc_seg: 91.9079, loss: 0.1858 2022-05-06 02:06:30,401 - mmseg - INFO - Iter [11400/80000] lr: 1.231e-06, eta: 11:20:05, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1044, decode.acc_seg: 95.1196, aux.loss_ce: 0.0761, aux.acc_seg: 92.2620, loss: 0.1805 2022-05-06 02:06:57,158 - mmseg - INFO - Iter [11450/80000] lr: 1.230e-06, eta: 11:19:17, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1050, decode.acc_seg: 94.9781, aux.loss_ce: 0.0768, aux.acc_seg: 92.3207, loss: 0.1818 2022-05-06 02:07:23,858 - mmseg - INFO - Iter [11500/80000] lr: 1.229e-06, eta: 11:18:29, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1084, decode.acc_seg: 95.0388, aux.loss_ce: 0.0758, aux.acc_seg: 92.6307, loss: 0.1842 2022-05-06 02:07:53,404 - mmseg - INFO - Iter [11550/80000] lr: 1.229e-06, eta: 11:17:59, time: 0.591, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1129, decode.acc_seg: 94.7845, aux.loss_ce: 0.0764, aux.acc_seg: 92.3728, loss: 0.1893 2022-05-06 02:08:20,320 - mmseg - INFO - Iter [11600/80000] lr: 1.228e-06, eta: 11:17:12, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1104, decode.acc_seg: 94.5950, aux.loss_ce: 0.0759, aux.acc_seg: 91.8279, loss: 0.1863 2022-05-06 02:08:46,965 - mmseg - INFO - Iter [11650/80000] lr: 1.227e-06, eta: 11:16:25, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1094, decode.acc_seg: 94.8593, aux.loss_ce: 0.0756, aux.acc_seg: 92.3465, loss: 0.1850 2022-05-06 02:09:13,616 - mmseg - INFO - Iter [11700/80000] lr: 1.226e-06, eta: 11:15:37, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1044, decode.acc_seg: 94.9868, aux.loss_ce: 0.0718, aux.acc_seg: 92.4817, loss: 0.1763 2022-05-06 02:09:40,353 - mmseg - INFO - Iter [11750/80000] lr: 1.225e-06, eta: 11:14:50, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1129, decode.acc_seg: 94.9608, aux.loss_ce: 0.0778, aux.acc_seg: 92.4429, loss: 0.1907 2022-05-06 02:10:06,899 - mmseg - INFO - Iter [11800/80000] lr: 1.224e-06, eta: 11:14:03, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1137, decode.acc_seg: 94.6422, aux.loss_ce: 0.0776, aux.acc_seg: 92.2547, loss: 0.1912 2022-05-06 02:10:33,442 - mmseg - INFO - Iter [11850/80000] lr: 1.223e-06, eta: 11:13:15, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0990, decode.acc_seg: 95.2645, aux.loss_ce: 0.0727, aux.acc_seg: 92.6663, loss: 0.1717 2022-05-06 02:11:03,222 - mmseg - INFO - Iter [11900/80000] lr: 1.222e-06, eta: 11:12:46, time: 0.596, data_time: 0.053, memory: 58091, decode.loss_ce: 0.1028, decode.acc_seg: 95.2493, aux.loss_ce: 0.0732, aux.acc_seg: 92.7519, loss: 0.1761 2022-05-06 02:11:29,895 - mmseg - INFO - Iter [11950/80000] lr: 1.221e-06, eta: 11:12:00, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1033, decode.acc_seg: 94.9204, aux.loss_ce: 0.0736, aux.acc_seg: 92.3812, loss: 0.1770 2022-05-06 02:11:56,422 - mmseg - INFO - Saving checkpoint at 12000 iterations 2022-05-06 02:12:17,949 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:12:17,956 - mmseg - INFO - Iter [12000/80000] lr: 1.220e-06, eta: 11:13:14, time: 0.960, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1058, decode.acc_seg: 94.9675, aux.loss_ce: 0.0741, aux.acc_seg: 92.3120, loss: 0.1799 2022-05-06 02:12:45,202 - mmseg - INFO - Iter [12050/80000] lr: 1.220e-06, eta: 11:12:31, time: 0.545, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1078, decode.acc_seg: 94.7568, aux.loss_ce: 0.0741, aux.acc_seg: 92.0932, loss: 0.1819 2022-05-06 02:13:12,313 - mmseg - INFO - Iter [12100/80000] lr: 1.219e-06, eta: 11:11:47, time: 0.544, data_time: 0.008, memory: 58091, decode.loss_ce: 0.1045, decode.acc_seg: 95.0417, aux.loss_ce: 0.0729, aux.acc_seg: 92.1434, loss: 0.1774 2022-05-06 02:13:38,897 - mmseg - INFO - Iter [12150/80000] lr: 1.218e-06, eta: 11:11:00, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0962, decode.acc_seg: 95.4812, aux.loss_ce: 0.0657, aux.acc_seg: 93.4213, loss: 0.1619 2022-05-06 02:14:08,267 - mmseg - INFO - Iter [12200/80000] lr: 1.217e-06, eta: 11:10:29, time: 0.587, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0956, decode.acc_seg: 95.5392, aux.loss_ce: 0.0683, aux.acc_seg: 93.3756, loss: 0.1638 2022-05-06 02:14:34,944 - mmseg - INFO - Iter [12250/80000] lr: 1.216e-06, eta: 11:09:43, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1131, decode.acc_seg: 94.9277, aux.loss_ce: 0.0746, aux.acc_seg: 92.5545, loss: 0.1877 2022-05-06 02:15:01,596 - mmseg - INFO - Iter [12300/80000] lr: 1.215e-06, eta: 11:08:56, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1105, decode.acc_seg: 94.9813, aux.loss_ce: 0.0751, aux.acc_seg: 92.5814, loss: 0.1856 2022-05-06 02:15:28,428 - mmseg - INFO - Iter [12350/80000] lr: 1.214e-06, eta: 11:08:11, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1010, decode.acc_seg: 95.2284, aux.loss_ce: 0.0712, aux.acc_seg: 92.9809, loss: 0.1722 2022-05-06 02:15:55,120 - mmseg - INFO - Iter [12400/80000] lr: 1.213e-06, eta: 11:07:26, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.1018, decode.acc_seg: 95.1093, aux.loss_ce: 0.0698, aux.acc_seg: 92.8209, loss: 0.1716 2022-05-06 02:16:22,200 - mmseg - INFO - Iter [12450/80000] lr: 1.212e-06, eta: 11:06:42, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1056, decode.acc_seg: 95.0611, aux.loss_ce: 0.0718, aux.acc_seg: 92.8098, loss: 0.1774 2022-05-06 02:16:51,563 - mmseg - INFO - Iter [12500/80000] lr: 1.211e-06, eta: 11:06:11, time: 0.585, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0996, decode.acc_seg: 94.9237, aux.loss_ce: 0.0701, aux.acc_seg: 92.5019, loss: 0.1697 2022-05-06 02:17:18,328 - mmseg - INFO - Iter [12550/80000] lr: 1.211e-06, eta: 11:05:26, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0998, decode.acc_seg: 95.3549, aux.loss_ce: 0.0680, aux.acc_seg: 92.9839, loss: 0.1678 2022-05-06 02:17:45,072 - mmseg - INFO - Iter [12600/80000] lr: 1.210e-06, eta: 11:04:42, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1109, decode.acc_seg: 95.0488, aux.loss_ce: 0.0719, aux.acc_seg: 92.7748, loss: 0.1828 2022-05-06 02:18:11,859 - mmseg - INFO - Iter [12650/80000] lr: 1.209e-06, eta: 11:03:57, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1095, decode.acc_seg: 95.2739, aux.loss_ce: 0.0723, aux.acc_seg: 92.9970, loss: 0.1818 2022-05-06 02:18:38,491 - mmseg - INFO - Iter [12700/80000] lr: 1.208e-06, eta: 11:03:12, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0989, decode.acc_seg: 95.1290, aux.loss_ce: 0.0638, aux.acc_seg: 92.8772, loss: 0.1627 2022-05-06 02:19:05,347 - mmseg - INFO - Iter [12750/80000] lr: 1.207e-06, eta: 11:02:28, time: 0.537, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0949, decode.acc_seg: 95.4445, aux.loss_ce: 0.0650, aux.acc_seg: 93.2945, loss: 0.1599 2022-05-06 02:19:34,841 - mmseg - INFO - Iter [12800/80000] lr: 1.206e-06, eta: 11:01:58, time: 0.590, data_time: 0.055, memory: 58091, decode.loss_ce: 0.1088, decode.acc_seg: 94.7214, aux.loss_ce: 0.0741, aux.acc_seg: 92.3133, loss: 0.1829 2022-05-06 02:20:01,322 - mmseg - INFO - Iter [12850/80000] lr: 1.205e-06, eta: 11:01:13, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0959, decode.acc_seg: 95.3174, aux.loss_ce: 0.0655, aux.acc_seg: 93.0507, loss: 0.1613 2022-05-06 02:20:28,190 - mmseg - INFO - Iter [12900/80000] lr: 1.204e-06, eta: 11:00:29, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1083, decode.acc_seg: 94.7701, aux.loss_ce: 0.0702, aux.acc_seg: 92.5820, loss: 0.1785 2022-05-06 02:20:54,850 - mmseg - INFO - Iter [12950/80000] lr: 1.203e-06, eta: 10:59:45, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1001, decode.acc_seg: 95.2450, aux.loss_ce: 0.0687, aux.acc_seg: 92.9937, loss: 0.1688 2022-05-06 02:21:21,373 - mmseg - INFO - Saving checkpoint at 13000 iterations 2022-05-06 02:21:41,412 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:21:41,422 - mmseg - INFO - Iter [13000/80000] lr: 1.202e-06, eta: 11:00:42, time: 0.929, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0973, decode.acc_seg: 95.2068, aux.loss_ce: 0.0672, aux.acc_seg: 93.0414, loss: 0.1645 2022-05-06 02:22:08,527 - mmseg - INFO - Iter [13050/80000] lr: 1.202e-06, eta: 11:00:01, time: 0.545, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1051, decode.acc_seg: 95.1307, aux.loss_ce: 0.0694, aux.acc_seg: 93.0840, loss: 0.1745 2022-05-06 02:22:35,585 - mmseg - INFO - Iter [13100/80000] lr: 1.201e-06, eta: 10:59:18, time: 0.541, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0996, decode.acc_seg: 95.2971, aux.loss_ce: 0.0657, aux.acc_seg: 93.2898, loss: 0.1653 2022-05-06 02:23:05,493 - mmseg - INFO - Iter [13150/80000] lr: 1.200e-06, eta: 10:58:51, time: 0.598, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0983, decode.acc_seg: 95.4205, aux.loss_ce: 0.0688, aux.acc_seg: 93.1315, loss: 0.1672 2022-05-06 02:23:32,433 - mmseg - INFO - Iter [13200/80000] lr: 1.199e-06, eta: 10:58:07, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0938, decode.acc_seg: 95.5376, aux.loss_ce: 0.0645, aux.acc_seg: 93.2267, loss: 0.1583 2022-05-06 02:23:59,207 - mmseg - INFO - Iter [13250/80000] lr: 1.198e-06, eta: 10:57:24, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1060, decode.acc_seg: 94.9534, aux.loss_ce: 0.0695, aux.acc_seg: 92.9344, loss: 0.1756 2022-05-06 02:24:26,476 - mmseg - INFO - Iter [13300/80000] lr: 1.197e-06, eta: 10:56:43, time: 0.545, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1059, decode.acc_seg: 94.9645, aux.loss_ce: 0.0658, aux.acc_seg: 93.2237, loss: 0.1717 2022-05-06 02:24:53,483 - mmseg - INFO - Iter [13350/80000] lr: 1.196e-06, eta: 10:56:01, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0955, decode.acc_seg: 95.3602, aux.loss_ce: 0.0673, aux.acc_seg: 93.2455, loss: 0.1629 2022-05-06 02:25:20,446 - mmseg - INFO - Iter [13400/80000] lr: 1.195e-06, eta: 10:55:19, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1003, decode.acc_seg: 95.1729, aux.loss_ce: 0.0671, aux.acc_seg: 92.8880, loss: 0.1674 2022-05-06 02:25:50,447 - mmseg - INFO - Iter [13450/80000] lr: 1.194e-06, eta: 10:54:52, time: 0.600, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0998, decode.acc_seg: 95.3599, aux.loss_ce: 0.0675, aux.acc_seg: 93.0603, loss: 0.1673 2022-05-06 02:26:17,281 - mmseg - INFO - Iter [13500/80000] lr: 1.194e-06, eta: 10:54:09, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0991, decode.acc_seg: 95.2926, aux.loss_ce: 0.0665, aux.acc_seg: 93.1145, loss: 0.1656 2022-05-06 02:26:44,029 - mmseg - INFO - Iter [13550/80000] lr: 1.193e-06, eta: 10:53:26, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0946, decode.acc_seg: 95.4792, aux.loss_ce: 0.0645, aux.acc_seg: 93.2823, loss: 0.1590 2022-05-06 02:27:10,889 - mmseg - INFO - Iter [13600/80000] lr: 1.192e-06, eta: 10:52:43, time: 0.537, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0946, decode.acc_seg: 95.5029, aux.loss_ce: 0.0647, aux.acc_seg: 93.4803, loss: 0.1593 2022-05-06 02:27:37,976 - mmseg - INFO - Iter [13650/80000] lr: 1.191e-06, eta: 10:52:02, time: 0.542, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0948, decode.acc_seg: 95.3878, aux.loss_ce: 0.0631, aux.acc_seg: 93.4027, loss: 0.1579 2022-05-06 02:28:04,742 - mmseg - INFO - Iter [13700/80000] lr: 1.190e-06, eta: 10:51:20, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0920, decode.acc_seg: 95.4785, aux.loss_ce: 0.0609, aux.acc_seg: 93.6586, loss: 0.1529 2022-05-06 02:28:33,807 - mmseg - INFO - Iter [13750/80000] lr: 1.189e-06, eta: 10:50:48, time: 0.581, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0943, decode.acc_seg: 95.4020, aux.loss_ce: 0.0649, aux.acc_seg: 93.3578, loss: 0.1591 2022-05-06 02:29:00,437 - mmseg - INFO - Iter [13800/80000] lr: 1.188e-06, eta: 10:50:05, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0924, decode.acc_seg: 95.5579, aux.loss_ce: 0.0629, aux.acc_seg: 93.5593, loss: 0.1552 2022-05-06 02:29:26,898 - mmseg - INFO - Iter [13850/80000] lr: 1.187e-06, eta: 10:49:21, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0983, decode.acc_seg: 95.2924, aux.loss_ce: 0.0637, aux.acc_seg: 93.2543, loss: 0.1619 2022-05-06 02:29:53,617 - mmseg - INFO - Iter [13900/80000] lr: 1.186e-06, eta: 10:48:39, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0970, decode.acc_seg: 95.3812, aux.loss_ce: 0.0628, aux.acc_seg: 93.5603, loss: 0.1598 2022-05-06 02:30:20,277 - mmseg - INFO - Iter [13950/80000] lr: 1.185e-06, eta: 10:47:56, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1036, decode.acc_seg: 95.1764, aux.loss_ce: 0.0675, aux.acc_seg: 93.2417, loss: 0.1711 2022-05-06 02:30:47,178 - mmseg - INFO - Saving checkpoint at 14000 iterations 2022-05-06 02:31:08,934 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:31:08,937 - mmseg - INFO - Iter [14000/80000] lr: 1.185e-06, eta: 10:48:57, time: 0.972, data_time: 0.006, memory: 58091, decode.loss_ce: 0.1022, decode.acc_seg: 95.1670, aux.loss_ce: 0.0664, aux.acc_seg: 93.2147, loss: 0.1687 2022-05-06 02:31:38,589 - mmseg - INFO - Iter [14050/80000] lr: 1.184e-06, eta: 10:48:29, time: 0.595, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0869, decode.acc_seg: 95.9119, aux.loss_ce: 0.0580, aux.acc_seg: 94.0077, loss: 0.1449 2022-05-06 02:32:05,176 - mmseg - INFO - Iter [14100/80000] lr: 1.183e-06, eta: 10:47:45, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0912, decode.acc_seg: 95.6195, aux.loss_ce: 0.0608, aux.acc_seg: 93.6735, loss: 0.1520 2022-05-06 02:32:32,408 - mmseg - INFO - Iter [14150/80000] lr: 1.182e-06, eta: 10:47:05, time: 0.543, data_time: 0.007, memory: 58091, decode.loss_ce: 0.1018, decode.acc_seg: 95.0913, aux.loss_ce: 0.0664, aux.acc_seg: 93.1370, loss: 0.1682 2022-05-06 02:32:58,856 - mmseg - INFO - Iter [14200/80000] lr: 1.181e-06, eta: 10:46:22, time: 0.531, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0946, decode.acc_seg: 95.4709, aux.loss_ce: 0.0601, aux.acc_seg: 93.6868, loss: 0.1548 2022-05-06 02:33:25,879 - mmseg - INFO - Iter [14250/80000] lr: 1.180e-06, eta: 10:45:41, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0982, decode.acc_seg: 95.2825, aux.loss_ce: 0.0637, aux.acc_seg: 93.3009, loss: 0.1619 2022-05-06 02:33:52,760 - mmseg - INFO - Iter [14300/80000] lr: 1.179e-06, eta: 10:45:00, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0938, decode.acc_seg: 95.6031, aux.loss_ce: 0.0603, aux.acc_seg: 93.6874, loss: 0.1541 2022-05-06 02:34:19,627 - mmseg - INFO - Iter [14350/80000] lr: 1.178e-06, eta: 10:44:19, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0988, decode.acc_seg: 95.3981, aux.loss_ce: 0.0654, aux.acc_seg: 93.3745, loss: 0.1642 2022-05-06 02:34:48,766 - mmseg - INFO - Iter [14400/80000] lr: 1.177e-06, eta: 10:43:48, time: 0.583, data_time: 0.051, memory: 58091, decode.loss_ce: 0.1005, decode.acc_seg: 95.3100, aux.loss_ce: 0.0623, aux.acc_seg: 93.5138, loss: 0.1627 2022-05-06 02:35:15,553 - mmseg - INFO - Iter [14450/80000] lr: 1.176e-06, eta: 10:43:06, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0929, decode.acc_seg: 95.5104, aux.loss_ce: 0.0619, aux.acc_seg: 93.4999, loss: 0.1548 2022-05-06 02:35:42,161 - mmseg - INFO - Iter [14500/80000] lr: 1.176e-06, eta: 10:42:24, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0883, decode.acc_seg: 95.6815, aux.loss_ce: 0.0593, aux.acc_seg: 93.7646, loss: 0.1476 2022-05-06 02:36:08,796 - mmseg - INFO - Iter [14550/80000] lr: 1.175e-06, eta: 10:41:42, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0936, decode.acc_seg: 95.3328, aux.loss_ce: 0.0614, aux.acc_seg: 93.4986, loss: 0.1550 2022-05-06 02:36:35,505 - mmseg - INFO - Iter [14600/80000] lr: 1.174e-06, eta: 10:41:01, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0910, decode.acc_seg: 95.7050, aux.loss_ce: 0.0597, aux.acc_seg: 93.9299, loss: 0.1507 2022-05-06 02:37:02,352 - mmseg - INFO - Iter [14650/80000] lr: 1.173e-06, eta: 10:40:20, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0956, decode.acc_seg: 95.3809, aux.loss_ce: 0.0625, aux.acc_seg: 93.4042, loss: 0.1581 2022-05-06 02:37:31,361 - mmseg - INFO - Iter [14700/80000] lr: 1.172e-06, eta: 10:39:49, time: 0.580, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0951, decode.acc_seg: 95.5019, aux.loss_ce: 0.0615, aux.acc_seg: 93.7025, loss: 0.1565 2022-05-06 02:37:57,837 - mmseg - INFO - Iter [14750/80000] lr: 1.171e-06, eta: 10:39:06, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1018, decode.acc_seg: 95.1216, aux.loss_ce: 0.0639, aux.acc_seg: 93.1930, loss: 0.1657 2022-05-06 02:38:24,712 - mmseg - INFO - Iter [14800/80000] lr: 1.170e-06, eta: 10:38:26, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0955, decode.acc_seg: 95.3938, aux.loss_ce: 0.0602, aux.acc_seg: 93.6303, loss: 0.1557 2022-05-06 02:38:51,383 - mmseg - INFO - Iter [14850/80000] lr: 1.169e-06, eta: 10:37:45, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1104, decode.acc_seg: 94.5357, aux.loss_ce: 0.0648, aux.acc_seg: 92.8279, loss: 0.1752 2022-05-06 02:39:18,265 - mmseg - INFO - Iter [14900/80000] lr: 1.168e-06, eta: 10:37:04, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0975, decode.acc_seg: 95.2841, aux.loss_ce: 0.0632, aux.acc_seg: 93.3663, loss: 0.1606 2022-05-06 02:39:44,914 - mmseg - INFO - Iter [14950/80000] lr: 1.167e-06, eta: 10:36:23, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0917, decode.acc_seg: 95.5079, aux.loss_ce: 0.0573, aux.acc_seg: 93.6567, loss: 0.1490 2022-05-06 02:40:14,319 - mmseg - INFO - Saving checkpoint at 15000 iterations 2022-05-06 02:40:34,591 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:40:34,604 - mmseg - INFO - Iter [15000/80000] lr: 1.167e-06, eta: 10:37:21, time: 0.989, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0978, decode.acc_seg: 95.1601, aux.loss_ce: 0.0609, aux.acc_seg: 93.5346, loss: 0.1588 2022-05-06 02:41:01,670 - mmseg - INFO - Iter [15050/80000] lr: 1.166e-06, eta: 10:36:42, time: 0.546, data_time: 0.009, memory: 58091, decode.loss_ce: 0.0980, decode.acc_seg: 95.2291, aux.loss_ce: 0.0612, aux.acc_seg: 93.3731, loss: 0.1593 2022-05-06 02:41:28,464 - mmseg - INFO - Iter [15100/80000] lr: 1.165e-06, eta: 10:36:02, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0867, decode.acc_seg: 95.8133, aux.loss_ce: 0.0566, aux.acc_seg: 94.1560, loss: 0.1434 2022-05-06 02:41:54,997 - mmseg - INFO - Iter [15150/80000] lr: 1.164e-06, eta: 10:35:20, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1008, decode.acc_seg: 95.1459, aux.loss_ce: 0.0628, aux.acc_seg: 93.4181, loss: 0.1636 2022-05-06 02:42:21,424 - mmseg - INFO - Iter [15200/80000] lr: 1.163e-06, eta: 10:34:38, time: 0.528, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0980, decode.acc_seg: 95.3377, aux.loss_ce: 0.0617, aux.acc_seg: 93.7079, loss: 0.1598 2022-05-06 02:42:48,170 - mmseg - INFO - Iter [15250/80000] lr: 1.162e-06, eta: 10:33:58, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0910, decode.acc_seg: 95.6037, aux.loss_ce: 0.0584, aux.acc_seg: 93.8079, loss: 0.1495 2022-05-06 02:43:17,336 - mmseg - INFO - Iter [15300/80000] lr: 1.161e-06, eta: 10:33:27, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0850, decode.acc_seg: 95.7164, aux.loss_ce: 0.0572, aux.acc_seg: 93.7854, loss: 0.1422 2022-05-06 02:43:44,300 - mmseg - INFO - Iter [15350/80000] lr: 1.160e-06, eta: 10:32:48, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0896, decode.acc_seg: 95.6266, aux.loss_ce: 0.0591, aux.acc_seg: 93.8247, loss: 0.1487 2022-05-06 02:44:10,918 - mmseg - INFO - Iter [15400/80000] lr: 1.159e-06, eta: 10:32:07, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.1001, decode.acc_seg: 95.2777, aux.loss_ce: 0.0607, aux.acc_seg: 93.5157, loss: 0.1608 2022-05-06 02:44:37,741 - mmseg - INFO - Iter [15450/80000] lr: 1.159e-06, eta: 10:31:27, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0955, decode.acc_seg: 95.3745, aux.loss_ce: 0.0586, aux.acc_seg: 93.6310, loss: 0.1541 2022-05-06 02:45:04,646 - mmseg - INFO - Iter [15500/80000] lr: 1.158e-06, eta: 10:30:47, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0897, decode.acc_seg: 95.5146, aux.loss_ce: 0.0578, aux.acc_seg: 93.6518, loss: 0.1476 2022-05-06 02:45:31,312 - mmseg - INFO - Iter [15550/80000] lr: 1.157e-06, eta: 10:30:07, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0927, decode.acc_seg: 95.5863, aux.loss_ce: 0.0593, aux.acc_seg: 93.8107, loss: 0.1520 2022-05-06 02:45:57,981 - mmseg - INFO - Iter [15600/80000] lr: 1.156e-06, eta: 10:29:27, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0926, decode.acc_seg: 95.4190, aux.loss_ce: 0.0582, aux.acc_seg: 93.7363, loss: 0.1508 2022-05-06 02:46:27,034 - mmseg - INFO - Iter [15650/80000] lr: 1.155e-06, eta: 10:28:56, time: 0.581, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0879, decode.acc_seg: 95.7701, aux.loss_ce: 0.0574, aux.acc_seg: 93.9461, loss: 0.1453 2022-05-06 02:46:53,703 - mmseg - INFO - Iter [15700/80000] lr: 1.154e-06, eta: 10:28:16, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0955, decode.acc_seg: 95.5328, aux.loss_ce: 0.0579, aux.acc_seg: 94.0631, loss: 0.1534 2022-05-06 02:47:20,276 - mmseg - INFO - Iter [15750/80000] lr: 1.153e-06, eta: 10:27:36, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0993, decode.acc_seg: 95.0894, aux.loss_ce: 0.0616, aux.acc_seg: 93.3891, loss: 0.1609 2022-05-06 02:47:46,803 - mmseg - INFO - Iter [15800/80000] lr: 1.152e-06, eta: 10:26:55, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0905, decode.acc_seg: 95.3519, aux.loss_ce: 0.0573, aux.acc_seg: 93.6572, loss: 0.1478 2022-05-06 02:48:13,379 - mmseg - INFO - Iter [15850/80000] lr: 1.151e-06, eta: 10:26:15, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0858, decode.acc_seg: 95.9123, aux.loss_ce: 0.0553, aux.acc_seg: 94.1251, loss: 0.1412 2022-05-06 02:48:39,803 - mmseg - INFO - Iter [15900/80000] lr: 1.150e-06, eta: 10:25:34, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0875, decode.acc_seg: 95.8265, aux.loss_ce: 0.0583, aux.acc_seg: 93.9383, loss: 0.1458 2022-05-06 02:49:08,977 - mmseg - INFO - Iter [15950/80000] lr: 1.150e-06, eta: 10:25:04, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0877, decode.acc_seg: 95.7477, aux.loss_ce: 0.0550, aux.acc_seg: 94.1638, loss: 0.1427 2022-05-06 02:49:35,725 - mmseg - INFO - Saving checkpoint at 16000 iterations 2022-05-06 02:49:56,743 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:49:56,755 - mmseg - INFO - Iter [16000/80000] lr: 1.149e-06, eta: 10:25:48, time: 0.952, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0919, decode.acc_seg: 95.6198, aux.loss_ce: 0.0593, aux.acc_seg: 93.8245, loss: 0.1511 2022-05-06 02:54:06,734 - mmseg - INFO - per class results: 2022-05-06 02:54:06,753 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 92.43 | 97.55 | | bag | 49.26 | 63.58 | | bed | 33.86 | 44.87 | | bedclothes | 47.49 | 70.35 | | bench | 30.05 | 39.8 | | bicycle | 82.17 | 93.05 | | bird | 93.73 | 97.89 | | boat | 85.46 | 93.21 | | book | 60.92 | 79.1 | | bottle | 88.11 | 96.18 | | building | 67.77 | 80.15 | | bus | 94.26 | 97.73 | | cabinet | 51.26 | 63.7 | | car | 93.62 | 96.37 | | cat | 93.39 | 98.56 | | ceiling | 60.24 | 78.52 | | chair | 64.21 | 83.13 | | cloth | 26.41 | 33.82 | | computer | 57.93 | 75.29 | | cow | 92.89 | 98.68 | | cup | 45.61 | 60.95 | | curtain | 58.15 | 67.64 | | dog | 91.62 | 96.86 | | door | 37.81 | 60.27 | | fence | 45.13 | 58.82 | | floor | 75.9 | 88.69 | | flower | 33.12 | 48.81 | | food | 38.97 | 47.3 | | grass | 83.07 | 90.87 | | ground | 58.08 | 72.96 | | horse | 93.4 | 96.87 | | keyboard | 87.2 | 93.9 | | light | 58.78 | 74.75 | | motorbike | 90.24 | 96.8 | | mountain | 57.51 | 75.38 | | mouse | 71.72 | 75.1 | | person | 90.28 | 96.07 | | plate | 30.07 | 44.48 | | platform | 61.82 | 78.34 | | pottedplant | 80.57 | 90.82 | | road | 51.93 | 65.73 | | rock | 57.62 | 67.52 | | sheep | 94.45 | 98.91 | | shelves | 36.52 | 52.1 | | sidewalk | 31.17 | 47.56 | | sign | 51.99 | 61.85 | | sky | 94.33 | 96.74 | | snow | 72.89 | 93.25 | | sofa | 59.96 | 71.43 | | table | 71.23 | 81.42 | | track | 70.19 | 83.69 | | train | 92.78 | 97.6 | | tree | 81.58 | 90.83 | | truck | 52.91 | 61.88 | | tvmonitor | 90.11 | 93.45 | | wall | 73.2 | 84.99 | | water | 91.26 | 95.56 | | window | 47.27 | 60.37 | | wood | 25.51 | 33.19 | +-------------+-------+-------+ 2022-05-06 02:54:06,753 - mmseg - INFO - Summary: 2022-05-06 02:54:06,753 - mmseg - INFO - +------+-------+-------+ | aAcc | mIoU | mAcc | +------+-------+-------+ | 86.3 | 66.13 | 76.87 | +------+-------+-------+ 2022-05-06 02:54:06,756 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_8000.pth was removed 2022-05-06 02:54:26,219 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_16000.pth. 2022-05-06 02:54:26,225 - mmseg - INFO - Best mIoU is 0.6613 at 16000 iter. 2022-05-06 02:54:26,249 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 02:54:26,249 - mmseg - INFO - Iter(val) [638] aAcc: 0.8630, mIoU: 0.6613, mAcc: 0.7687, IoU.aeroplane: 0.9243, IoU.bag: 0.4926, IoU.bed: 0.3386, IoU.bedclothes: 0.4749, IoU.bench: 0.3005, IoU.bicycle: 0.8217, IoU.bird: 0.9373, IoU.boat: 0.8546, IoU.book: 0.6092, IoU.bottle: 0.8811, IoU.building: 0.6777, IoU.bus: 0.9426, IoU.cabinet: 0.5126, IoU.car: 0.9362, IoU.cat: 0.9339, IoU.ceiling: 0.6024, IoU.chair: 0.6421, IoU.cloth: 0.2641, IoU.computer: 0.5793, IoU.cow: 0.9289, IoU.cup: 0.4561, IoU.curtain: 0.5815, IoU.dog: 0.9162, IoU.door: 0.3781, IoU.fence: 0.4513, IoU.floor: 0.7590, IoU.flower: 0.3312, IoU.food: 0.3897, IoU.grass: 0.8307, IoU.ground: 0.5808, IoU.horse: 0.9340, IoU.keyboard: 0.8720, IoU.light: 0.5878, IoU.motorbike: 0.9024, IoU.mountain: 0.5751, IoU.mouse: 0.7172, IoU.person: 0.9028, IoU.plate: 0.3007, IoU.platform: 0.6182, IoU.pottedplant: 0.8057, IoU.road: 0.5193, IoU.rock: 0.5762, IoU.sheep: 0.9445, IoU.shelves: 0.3652, IoU.sidewalk: 0.3117, IoU.sign: 0.5199, IoU.sky: 0.9433, IoU.snow: 0.7289, IoU.sofa: 0.5996, IoU.table: 0.7123, IoU.track: 0.7019, IoU.train: 0.9278, IoU.tree: 0.8158, IoU.truck: 0.5291, IoU.tvmonitor: 0.9011, IoU.wall: 0.7320, IoU.water: 0.9126, IoU.window: 0.4727, IoU.wood: 0.2551, Acc.aeroplane: 0.9755, Acc.bag: 0.6358, Acc.bed: 0.4487, Acc.bedclothes: 0.7035, Acc.bench: 0.3980, Acc.bicycle: 0.9305, Acc.bird: 0.9789, Acc.boat: 0.9321, Acc.book: 0.7910, Acc.bottle: 0.9618, Acc.building: 0.8015, Acc.bus: 0.9773, Acc.cabinet: 0.6370, Acc.car: 0.9637, Acc.cat: 0.9856, Acc.ceiling: 0.7852, Acc.chair: 0.8313, Acc.cloth: 0.3382, Acc.computer: 0.7529, Acc.cow: 0.9868, Acc.cup: 0.6095, Acc.curtain: 0.6764, Acc.dog: 0.9686, Acc.door: 0.6027, Acc.fence: 0.5882, Acc.floor: 0.8869, Acc.flower: 0.4881, Acc.food: 0.4730, Acc.grass: 0.9087, Acc.ground: 0.7296, Acc.horse: 0.9687, Acc.keyboard: 0.9390, Acc.light: 0.7475, Acc.motorbike: 0.9680, Acc.mountain: 0.7538, Acc.mouse: 0.7510, Acc.person: 0.9607, Acc.plate: 0.4448, Acc.platform: 0.7834, Acc.pottedplant: 0.9082, Acc.road: 0.6573, Acc.rock: 0.6752, Acc.sheep: 0.9891, Acc.shelves: 0.5210, Acc.sidewalk: 0.4756, Acc.sign: 0.6185, Acc.sky: 0.9674, Acc.snow: 0.9325, Acc.sofa: 0.7143, Acc.table: 0.8142, Acc.track: 0.8369, Acc.train: 0.9760, Acc.tree: 0.9083, Acc.truck: 0.6188, Acc.tvmonitor: 0.9345, Acc.wall: 0.8499, Acc.water: 0.9556, Acc.window: 0.6037, Acc.wood: 0.3319 2022-05-06 02:54:53,636 - mmseg - INFO - Iter [16050/80000] lr: 1.148e-06, eta: 10:43:06, time: 5.941, data_time: 5.399, memory: 58091, decode.loss_ce: 0.0854, decode.acc_seg: 95.9280, aux.loss_ce: 0.0549, aux.acc_seg: 94.1953, loss: 0.1403 2022-05-06 02:55:20,246 - mmseg - INFO - Iter [16100/80000] lr: 1.147e-06, eta: 10:42:21, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0863, decode.acc_seg: 95.8698, aux.loss_ce: 0.0585, aux.acc_seg: 93.8250, loss: 0.1447 2022-05-06 02:55:47,089 - mmseg - INFO - Iter [16150/80000] lr: 1.146e-06, eta: 10:41:38, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0910, decode.acc_seg: 95.6892, aux.loss_ce: 0.0582, aux.acc_seg: 94.0271, loss: 0.1492 2022-05-06 02:56:13,747 - mmseg - INFO - Iter [16200/80000] lr: 1.145e-06, eta: 10:40:54, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0892, decode.acc_seg: 95.6364, aux.loss_ce: 0.0575, aux.acc_seg: 93.7752, loss: 0.1468 2022-05-06 02:56:43,235 - mmseg - INFO - Iter [16250/80000] lr: 1.144e-06, eta: 10:40:21, time: 0.590, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0850, decode.acc_seg: 95.7909, aux.loss_ce: 0.0548, aux.acc_seg: 94.0522, loss: 0.1398 2022-05-06 02:57:09,965 - mmseg - INFO - Iter [16300/80000] lr: 1.143e-06, eta: 10:39:38, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0870, decode.acc_seg: 95.7875, aux.loss_ce: 0.0559, aux.acc_seg: 94.1335, loss: 0.1429 2022-05-06 02:57:36,651 - mmseg - INFO - Iter [16350/80000] lr: 1.142e-06, eta: 10:38:55, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0863, decode.acc_seg: 95.8705, aux.loss_ce: 0.0549, aux.acc_seg: 94.2580, loss: 0.1412 2022-05-06 02:58:03,280 - mmseg - INFO - Iter [16400/80000] lr: 1.141e-06, eta: 10:38:11, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0818, decode.acc_seg: 95.9264, aux.loss_ce: 0.0520, aux.acc_seg: 94.2697, loss: 0.1338 2022-05-06 02:58:29,924 - mmseg - INFO - Iter [16450/80000] lr: 1.141e-06, eta: 10:37:27, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0910, decode.acc_seg: 95.4809, aux.loss_ce: 0.0594, aux.acc_seg: 93.5521, loss: 0.1504 2022-05-06 02:58:56,700 - mmseg - INFO - Iter [16500/80000] lr: 1.140e-06, eta: 10:36:45, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0890, decode.acc_seg: 95.4999, aux.loss_ce: 0.0565, aux.acc_seg: 93.6982, loss: 0.1455 2022-05-06 02:59:26,066 - mmseg - INFO - Iter [16550/80000] lr: 1.139e-06, eta: 10:36:11, time: 0.586, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0841, decode.acc_seg: 96.0005, aux.loss_ce: 0.0551, aux.acc_seg: 94.0833, loss: 0.1392 2022-05-06 02:59:52,754 - mmseg - INFO - Iter [16600/80000] lr: 1.138e-06, eta: 10:35:29, time: 0.535, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0806, decode.acc_seg: 95.9381, aux.loss_ce: 0.0528, aux.acc_seg: 94.1385, loss: 0.1335 2022-05-06 03:00:19,458 - mmseg - INFO - Iter [16650/80000] lr: 1.137e-06, eta: 10:34:46, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0872, decode.acc_seg: 95.6530, aux.loss_ce: 0.0569, aux.acc_seg: 93.7212, loss: 0.1442 2022-05-06 03:00:46,000 - mmseg - INFO - Iter [16700/80000] lr: 1.136e-06, eta: 10:34:02, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0847, decode.acc_seg: 96.0274, aux.loss_ce: 0.0536, aux.acc_seg: 94.4861, loss: 0.1384 2022-05-06 03:01:12,697 - mmseg - INFO - Iter [16750/80000] lr: 1.135e-06, eta: 10:33:20, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0824, decode.acc_seg: 96.0535, aux.loss_ce: 0.0535, aux.acc_seg: 94.3673, loss: 0.1359 2022-05-06 03:01:39,590 - mmseg - INFO - Iter [16800/80000] lr: 1.134e-06, eta: 10:32:38, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0897, decode.acc_seg: 95.7405, aux.loss_ce: 0.0575, aux.acc_seg: 93.9043, loss: 0.1473 2022-05-06 03:02:08,867 - mmseg - INFO - Iter [16850/80000] lr: 1.133e-06, eta: 10:32:05, time: 0.585, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0900, decode.acc_seg: 95.7646, aux.loss_ce: 0.0573, aux.acc_seg: 93.9638, loss: 0.1473 2022-05-06 03:02:35,749 - mmseg - INFO - Iter [16900/80000] lr: 1.133e-06, eta: 10:31:23, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0865, decode.acc_seg: 95.8946, aux.loss_ce: 0.0558, aux.acc_seg: 94.2351, loss: 0.1424 2022-05-06 03:03:02,405 - mmseg - INFO - Iter [16950/80000] lr: 1.132e-06, eta: 10:30:41, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0785, decode.acc_seg: 96.1596, aux.loss_ce: 0.0498, aux.acc_seg: 94.7008, loss: 0.1283 2022-05-06 03:03:28,987 - mmseg - INFO - Saving checkpoint at 17000 iterations 2022-05-06 03:03:49,990 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 03:03:49,993 - mmseg - INFO - Iter [17000/80000] lr: 1.131e-06, eta: 10:31:15, time: 0.950, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0826, decode.acc_seg: 95.7693, aux.loss_ce: 0.0534, aux.acc_seg: 93.9498, loss: 0.1360 2022-05-06 03:04:17,707 - mmseg - INFO - Iter [17050/80000] lr: 1.130e-06, eta: 10:30:37, time: 0.556, data_time: 0.009, memory: 58091, decode.loss_ce: 0.0771, decode.acc_seg: 96.2347, aux.loss_ce: 0.0509, aux.acc_seg: 94.6272, loss: 0.1280 2022-05-06 03:04:44,510 - mmseg - INFO - Iter [17100/80000] lr: 1.129e-06, eta: 10:29:55, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0777, decode.acc_seg: 96.2478, aux.loss_ce: 0.0523, aux.acc_seg: 94.5784, loss: 0.1300 2022-05-06 03:05:11,119 - mmseg - INFO - Iter [17150/80000] lr: 1.128e-06, eta: 10:29:12, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0800, decode.acc_seg: 96.0254, aux.loss_ce: 0.0529, aux.acc_seg: 94.1944, loss: 0.1329 2022-05-06 03:05:40,258 - mmseg - INFO - Iter [17200/80000] lr: 1.127e-06, eta: 10:28:39, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0807, decode.acc_seg: 95.8292, aux.loss_ce: 0.0523, aux.acc_seg: 94.0271, loss: 0.1329 2022-05-06 03:06:06,922 - mmseg - INFO - Iter [17250/80000] lr: 1.126e-06, eta: 10:27:57, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0806, decode.acc_seg: 96.0824, aux.loss_ce: 0.0503, aux.acc_seg: 94.5904, loss: 0.1309 2022-05-06 03:06:33,720 - mmseg - INFO - Iter [17300/80000] lr: 1.125e-06, eta: 10:27:15, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0746, decode.acc_seg: 96.0933, aux.loss_ce: 0.0489, aux.acc_seg: 94.4312, loss: 0.1234 2022-05-06 03:07:00,606 - mmseg - INFO - Iter [17350/80000] lr: 1.124e-06, eta: 10:26:34, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0897, decode.acc_seg: 95.7821, aux.loss_ce: 0.0564, aux.acc_seg: 94.1702, loss: 0.1461 2022-05-06 03:07:27,607 - mmseg - INFO - Iter [17400/80000] lr: 1.124e-06, eta: 10:25:53, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0812, decode.acc_seg: 95.9918, aux.loss_ce: 0.0524, aux.acc_seg: 94.3504, loss: 0.1336 2022-05-06 03:07:54,332 - mmseg - INFO - Iter [17450/80000] lr: 1.123e-06, eta: 10:25:11, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0796, decode.acc_seg: 96.2065, aux.loss_ce: 0.0517, aux.acc_seg: 94.5389, loss: 0.1313 2022-05-06 03:08:23,491 - mmseg - INFO - Iter [17500/80000] lr: 1.122e-06, eta: 10:24:38, time: 0.583, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0851, decode.acc_seg: 95.8747, aux.loss_ce: 0.0547, aux.acc_seg: 94.1183, loss: 0.1398 2022-05-06 03:08:50,425 - mmseg - INFO - Iter [17550/80000] lr: 1.121e-06, eta: 10:23:58, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0866, decode.acc_seg: 95.8296, aux.loss_ce: 0.0550, aux.acc_seg: 94.1295, loss: 0.1415 2022-05-06 03:09:17,228 - mmseg - INFO - Iter [17600/80000] lr: 1.120e-06, eta: 10:23:16, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0813, decode.acc_seg: 96.0621, aux.loss_ce: 0.0528, aux.acc_seg: 94.4232, loss: 0.1341 2022-05-06 03:09:44,000 - mmseg - INFO - Iter [17650/80000] lr: 1.119e-06, eta: 10:22:35, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0848, decode.acc_seg: 95.9297, aux.loss_ce: 0.0518, aux.acc_seg: 94.5088, loss: 0.1366 2022-05-06 03:10:10,750 - mmseg - INFO - Iter [17700/80000] lr: 1.118e-06, eta: 10:21:54, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0884, decode.acc_seg: 95.7670, aux.loss_ce: 0.0540, aux.acc_seg: 94.0778, loss: 0.1424 2022-05-06 03:10:37,569 - mmseg - INFO - Iter [17750/80000] lr: 1.117e-06, eta: 10:21:13, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0875, decode.acc_seg: 95.7793, aux.loss_ce: 0.0542, aux.acc_seg: 94.0849, loss: 0.1417 2022-05-06 03:11:06,853 - mmseg - INFO - Iter [17800/80000] lr: 1.116e-06, eta: 10:20:41, time: 0.585, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0796, decode.acc_seg: 96.0829, aux.loss_ce: 0.0517, aux.acc_seg: 94.4864, loss: 0.1313 2022-05-06 03:11:33,698 - mmseg - INFO - Iter [17850/80000] lr: 1.115e-06, eta: 10:20:00, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0788, decode.acc_seg: 96.0355, aux.loss_ce: 0.0513, aux.acc_seg: 94.4793, loss: 0.1301 2022-05-06 03:12:00,584 - mmseg - INFO - Iter [17900/80000] lr: 1.115e-06, eta: 10:19:19, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0761, decode.acc_seg: 96.2574, aux.loss_ce: 0.0498, aux.acc_seg: 94.6753, loss: 0.1259 2022-05-06 03:12:27,327 - mmseg - INFO - Iter [17950/80000] lr: 1.114e-06, eta: 10:18:39, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0817, decode.acc_seg: 96.0617, aux.loss_ce: 0.0513, aux.acc_seg: 94.5701, loss: 0.1331 2022-05-06 03:12:53,917 - mmseg - INFO - Saving checkpoint at 18000 iterations 2022-05-06 03:13:13,881 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 03:13:13,883 - mmseg - INFO - Iter [18000/80000] lr: 1.113e-06, eta: 10:19:06, time: 0.930, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0852, decode.acc_seg: 95.9861, aux.loss_ce: 0.0548, aux.acc_seg: 94.3487, loss: 0.1400 2022-05-06 03:13:40,584 - mmseg - INFO - Iter [18050/80000] lr: 1.112e-06, eta: 10:18:25, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0814, decode.acc_seg: 95.9046, aux.loss_ce: 0.0507, aux.acc_seg: 94.3063, loss: 0.1321 2022-05-06 03:14:10,039 - mmseg - INFO - Iter [18100/80000] lr: 1.111e-06, eta: 10:17:53, time: 0.589, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0837, decode.acc_seg: 95.8691, aux.loss_ce: 0.0526, aux.acc_seg: 94.2175, loss: 0.1363 2022-05-06 03:14:36,886 - mmseg - INFO - Iter [18150/80000] lr: 1.110e-06, eta: 10:17:12, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0879, decode.acc_seg: 95.8227, aux.loss_ce: 0.0559, aux.acc_seg: 94.0431, loss: 0.1439 2022-05-06 03:15:03,525 - mmseg - INFO - Iter [18200/80000] lr: 1.109e-06, eta: 10:16:32, time: 0.535, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0787, decode.acc_seg: 96.1217, aux.loss_ce: 0.0519, aux.acc_seg: 94.4101, loss: 0.1305 2022-05-06 03:15:30,288 - mmseg - INFO - Iter [18250/80000] lr: 1.108e-06, eta: 10:15:51, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0775, decode.acc_seg: 96.2263, aux.loss_ce: 0.0505, aux.acc_seg: 94.5714, loss: 0.1281 2022-05-06 03:15:57,233 - mmseg - INFO - Iter [18300/80000] lr: 1.107e-06, eta: 10:15:11, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0765, decode.acc_seg: 96.2602, aux.loss_ce: 0.0490, aux.acc_seg: 94.7265, loss: 0.1255 2022-05-06 03:16:23,892 - mmseg - INFO - Iter [18350/80000] lr: 1.106e-06, eta: 10:14:30, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0762, decode.acc_seg: 96.1451, aux.loss_ce: 0.0488, aux.acc_seg: 94.6313, loss: 0.1250 2022-05-06 03:16:50,319 - mmseg - INFO - Iter [18400/80000] lr: 1.106e-06, eta: 10:13:49, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0867, decode.acc_seg: 95.8665, aux.loss_ce: 0.0534, aux.acc_seg: 94.2925, loss: 0.1401 2022-05-06 03:17:19,723 - mmseg - INFO - Iter [18450/80000] lr: 1.105e-06, eta: 10:13:17, time: 0.588, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0856, decode.acc_seg: 95.7683, aux.loss_ce: 0.0517, aux.acc_seg: 94.1747, loss: 0.1373 2022-05-06 03:17:46,310 - mmseg - INFO - Iter [18500/80000] lr: 1.104e-06, eta: 10:12:36, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0831, decode.acc_seg: 95.9686, aux.loss_ce: 0.0534, aux.acc_seg: 94.1926, loss: 0.1365 2022-05-06 03:18:12,927 - mmseg - INFO - Iter [18550/80000] lr: 1.103e-06, eta: 10:11:56, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0791, decode.acc_seg: 96.0596, aux.loss_ce: 0.0494, aux.acc_seg: 94.5220, loss: 0.1285 2022-05-06 03:18:39,765 - mmseg - INFO - Iter [18600/80000] lr: 1.102e-06, eta: 10:11:16, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0804, decode.acc_seg: 96.0307, aux.loss_ce: 0.0506, aux.acc_seg: 94.3823, loss: 0.1309 2022-05-06 03:19:06,338 - mmseg - INFO - Iter [18650/80000] lr: 1.101e-06, eta: 10:10:35, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0820, decode.acc_seg: 95.8971, aux.loss_ce: 0.0523, aux.acc_seg: 94.2356, loss: 0.1343 2022-05-06 03:19:32,886 - mmseg - INFO - Iter [18700/80000] lr: 1.100e-06, eta: 10:09:54, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0779, decode.acc_seg: 96.1475, aux.loss_ce: 0.0501, aux.acc_seg: 94.5229, loss: 0.1280 2022-05-06 03:20:02,753 - mmseg - INFO - Iter [18750/80000] lr: 1.099e-06, eta: 10:09:24, time: 0.597, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0813, decode.acc_seg: 96.0099, aux.loss_ce: 0.0501, aux.acc_seg: 94.6074, loss: 0.1314 2022-05-06 03:20:29,530 - mmseg - INFO - Iter [18800/80000] lr: 1.098e-06, eta: 10:08:45, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0790, decode.acc_seg: 96.0754, aux.loss_ce: 0.0511, aux.acc_seg: 94.3355, loss: 0.1301 2022-05-06 03:20:56,391 - mmseg - INFO - Iter [18850/80000] lr: 1.098e-06, eta: 10:08:05, time: 0.536, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0850, decode.acc_seg: 95.8663, aux.loss_ce: 0.0528, aux.acc_seg: 94.3156, loss: 0.1378 2022-05-06 03:21:23,046 - mmseg - INFO - Iter [18900/80000] lr: 1.097e-06, eta: 10:07:25, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0842, decode.acc_seg: 96.0249, aux.loss_ce: 0.0506, aux.acc_seg: 94.5784, loss: 0.1348 2022-05-06 03:21:49,887 - mmseg - INFO - Iter [18950/80000] lr: 1.096e-06, eta: 10:06:46, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0737, decode.acc_seg: 96.2790, aux.loss_ce: 0.0468, aux.acc_seg: 94.7201, loss: 0.1205 2022-05-06 03:22:16,631 - mmseg - INFO - Saving checkpoint at 19000 iterations 2022-05-06 03:22:37,594 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 03:22:37,606 - mmseg - INFO - Iter [19000/80000] lr: 1.095e-06, eta: 10:07:13, time: 0.951, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0756, decode.acc_seg: 96.2545, aux.loss_ce: 0.0478, aux.acc_seg: 94.7365, loss: 0.1234 2022-05-06 03:23:07,360 - mmseg - INFO - Iter [19050/80000] lr: 1.094e-06, eta: 10:06:43, time: 0.598, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0771, decode.acc_seg: 96.1879, aux.loss_ce: 0.0495, aux.acc_seg: 94.6186, loss: 0.1266 2022-05-06 03:23:34,350 - mmseg - INFO - Iter [19100/80000] lr: 1.093e-06, eta: 10:06:04, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0778, decode.acc_seg: 96.0233, aux.loss_ce: 0.0489, aux.acc_seg: 94.4180, loss: 0.1267 2022-05-06 03:24:01,172 - mmseg - INFO - Iter [19150/80000] lr: 1.092e-06, eta: 10:05:24, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0739, decode.acc_seg: 96.3722, aux.loss_ce: 0.0478, aux.acc_seg: 94.7473, loss: 0.1217 2022-05-06 03:24:28,061 - mmseg - INFO - Iter [19200/80000] lr: 1.091e-06, eta: 10:04:45, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0789, decode.acc_seg: 95.9729, aux.loss_ce: 0.0497, aux.acc_seg: 94.4071, loss: 0.1286 2022-05-06 03:24:55,126 - mmseg - INFO - Iter [19250/80000] lr: 1.090e-06, eta: 10:04:07, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0778, decode.acc_seg: 95.9832, aux.loss_ce: 0.0497, aux.acc_seg: 94.4838, loss: 0.1274 2022-05-06 03:25:21,944 - mmseg - INFO - Iter [19300/80000] lr: 1.089e-06, eta: 10:03:27, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0822, decode.acc_seg: 95.9217, aux.loss_ce: 0.0502, aux.acc_seg: 94.5103, loss: 0.1324 2022-05-06 03:25:51,083 - mmseg - INFO - Iter [19350/80000] lr: 1.089e-06, eta: 10:02:55, time: 0.583, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0817, decode.acc_seg: 96.1124, aux.loss_ce: 0.0511, aux.acc_seg: 94.5948, loss: 0.1328 2022-05-06 03:26:17,664 - mmseg - INFO - Iter [19400/80000] lr: 1.088e-06, eta: 10:02:15, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0793, decode.acc_seg: 96.0465, aux.loss_ce: 0.0499, aux.acc_seg: 94.3850, loss: 0.1292 2022-05-06 03:26:44,520 - mmseg - INFO - Iter [19450/80000] lr: 1.087e-06, eta: 10:01:36, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0782, decode.acc_seg: 96.0659, aux.loss_ce: 0.0486, aux.acc_seg: 94.6141, loss: 0.1268 2022-05-06 03:27:11,125 - mmseg - INFO - Iter [19500/80000] lr: 1.086e-06, eta: 10:00:57, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0788, decode.acc_seg: 96.2139, aux.loss_ce: 0.0500, aux.acc_seg: 94.5692, loss: 0.1288 2022-05-06 03:27:37,663 - mmseg - INFO - Iter [19550/80000] lr: 1.085e-06, eta: 10:00:17, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0800, decode.acc_seg: 96.0937, aux.loss_ce: 0.0489, aux.acc_seg: 94.4641, loss: 0.1289 2022-05-06 03:28:04,340 - mmseg - INFO - Iter [19600/80000] lr: 1.084e-06, eta: 9:59:37, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0791, decode.acc_seg: 96.1527, aux.loss_ce: 0.0498, aux.acc_seg: 94.5766, loss: 0.1290 2022-05-06 03:28:31,429 - mmseg - INFO - Iter [19650/80000] lr: 1.083e-06, eta: 9:58:59, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0817, decode.acc_seg: 96.0710, aux.loss_ce: 0.0515, aux.acc_seg: 94.4368, loss: 0.1332 2022-05-06 03:29:00,778 - mmseg - INFO - Iter [19700/80000] lr: 1.082e-06, eta: 9:58:28, time: 0.587, data_time: 0.051, memory: 58091, decode.loss_ce: 0.0750, decode.acc_seg: 96.2393, aux.loss_ce: 0.0472, aux.acc_seg: 94.7268, loss: 0.1223 2022-05-06 03:29:27,569 - mmseg - INFO - Iter [19750/80000] lr: 1.081e-06, eta: 9:57:49, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0731, decode.acc_seg: 96.2792, aux.loss_ce: 0.0458, aux.acc_seg: 94.8274, loss: 0.1190 2022-05-06 03:29:54,194 - mmseg - INFO - Iter [19800/80000] lr: 1.080e-06, eta: 9:57:10, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0745, decode.acc_seg: 96.3824, aux.loss_ce: 0.0479, aux.acc_seg: 94.8728, loss: 0.1224 2022-05-06 03:30:20,773 - mmseg - INFO - Iter [19850/80000] lr: 1.080e-06, eta: 9:56:31, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0751, decode.acc_seg: 96.3021, aux.loss_ce: 0.0469, aux.acc_seg: 94.9179, loss: 0.1220 2022-05-06 03:30:47,264 - mmseg - INFO - Iter [19900/80000] lr: 1.079e-06, eta: 9:55:51, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0736, decode.acc_seg: 96.2833, aux.loss_ce: 0.0462, aux.acc_seg: 94.9323, loss: 0.1198 2022-05-06 03:31:13,876 - mmseg - INFO - Iter [19950/80000] lr: 1.078e-06, eta: 9:55:12, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0753, decode.acc_seg: 96.2159, aux.loss_ce: 0.0477, aux.acc_seg: 94.7031, loss: 0.1230 2022-05-06 03:31:42,980 - mmseg - INFO - Saving checkpoint at 20000 iterations 2022-05-06 03:32:03,629 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 03:32:03,631 - mmseg - INFO - Iter [20000/80000] lr: 1.077e-06, eta: 9:55:42, time: 0.994, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0806, decode.acc_seg: 95.9436, aux.loss_ce: 0.0492, aux.acc_seg: 94.5256, loss: 0.1297 2022-05-06 03:32:30,839 - mmseg - INFO - Iter [20050/80000] lr: 1.076e-06, eta: 9:55:05, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0783, decode.acc_seg: 96.2491, aux.loss_ce: 0.0502, aux.acc_seg: 94.6388, loss: 0.1284 2022-05-06 03:32:57,741 - mmseg - INFO - Iter [20100/80000] lr: 1.075e-06, eta: 9:54:26, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0724, decode.acc_seg: 96.4136, aux.loss_ce: 0.0465, aux.acc_seg: 94.7926, loss: 0.1189 2022-05-06 03:33:24,285 - mmseg - INFO - Iter [20150/80000] lr: 1.074e-06, eta: 9:53:47, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0717, decode.acc_seg: 96.3748, aux.loss_ce: 0.0461, aux.acc_seg: 94.8078, loss: 0.1178 2022-05-06 03:33:50,906 - mmseg - INFO - Iter [20200/80000] lr: 1.073e-06, eta: 9:53:08, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0758, decode.acc_seg: 96.2549, aux.loss_ce: 0.0477, aux.acc_seg: 94.7835, loss: 0.1235 2022-05-06 03:34:17,595 - mmseg - INFO - Iter [20250/80000] lr: 1.072e-06, eta: 9:52:29, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0808, decode.acc_seg: 95.9829, aux.loss_ce: 0.0491, aux.acc_seg: 94.5652, loss: 0.1299 2022-05-06 03:34:46,965 - mmseg - INFO - Iter [20300/80000] lr: 1.071e-06, eta: 9:51:58, time: 0.587, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0838, decode.acc_seg: 95.8662, aux.loss_ce: 0.0513, aux.acc_seg: 94.2786, loss: 0.1351 2022-05-06 03:35:13,900 - mmseg - INFO - Iter [20350/80000] lr: 1.071e-06, eta: 9:51:20, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0735, decode.acc_seg: 96.2655, aux.loss_ce: 0.0463, aux.acc_seg: 94.7509, loss: 0.1198 2022-05-06 03:35:40,540 - mmseg - INFO - Iter [20400/80000] lr: 1.070e-06, eta: 9:50:41, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0719, decode.acc_seg: 96.3058, aux.loss_ce: 0.0467, aux.acc_seg: 94.7196, loss: 0.1186 2022-05-06 03:36:07,441 - mmseg - INFO - Iter [20450/80000] lr: 1.069e-06, eta: 9:50:03, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0784, decode.acc_seg: 96.0989, aux.loss_ce: 0.0496, aux.acc_seg: 94.5969, loss: 0.1280 2022-05-06 03:36:34,047 - mmseg - INFO - Iter [20500/80000] lr: 1.068e-06, eta: 9:49:25, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0709, decode.acc_seg: 96.4139, aux.loss_ce: 0.0447, aux.acc_seg: 94.9244, loss: 0.1156 2022-05-06 03:37:00,622 - mmseg - INFO - Iter [20550/80000] lr: 1.067e-06, eta: 9:48:46, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0721, decode.acc_seg: 96.3045, aux.loss_ce: 0.0456, aux.acc_seg: 94.7979, loss: 0.1177 2022-05-06 03:37:29,999 - mmseg - INFO - Iter [20600/80000] lr: 1.066e-06, eta: 9:48:15, time: 0.586, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0747, decode.acc_seg: 96.2859, aux.loss_ce: 0.0485, aux.acc_seg: 94.7203, loss: 0.1232 2022-05-06 03:37:56,770 - mmseg - INFO - Iter [20650/80000] lr: 1.065e-06, eta: 9:47:37, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0719, decode.acc_seg: 96.4717, aux.loss_ce: 0.0453, aux.acc_seg: 95.0280, loss: 0.1171 2022-05-06 03:38:23,716 - mmseg - INFO - Iter [20700/80000] lr: 1.064e-06, eta: 9:46:59, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0741, decode.acc_seg: 96.3039, aux.loss_ce: 0.0467, aux.acc_seg: 94.8349, loss: 0.1208 2022-05-06 03:38:50,307 - mmseg - INFO - Iter [20750/80000] lr: 1.063e-06, eta: 9:46:21, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0748, decode.acc_seg: 96.3010, aux.loss_ce: 0.0477, aux.acc_seg: 94.7349, loss: 0.1225 2022-05-06 03:39:16,680 - mmseg - INFO - Iter [20800/80000] lr: 1.063e-06, eta: 9:45:42, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0734, decode.acc_seg: 96.3432, aux.loss_ce: 0.0461, aux.acc_seg: 94.8935, loss: 0.1194 2022-05-06 03:39:43,307 - mmseg - INFO - Iter [20850/80000] lr: 1.062e-06, eta: 9:45:03, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0873, decode.acc_seg: 96.1753, aux.loss_ce: 0.0511, aux.acc_seg: 94.7204, loss: 0.1384 2022-05-06 03:40:10,114 - mmseg - INFO - Iter [20900/80000] lr: 1.061e-06, eta: 9:44:26, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0721, decode.acc_seg: 96.4507, aux.loss_ce: 0.0450, aux.acc_seg: 95.0178, loss: 0.1171 2022-05-06 03:40:39,161 - mmseg - INFO - Iter [20950/80000] lr: 1.060e-06, eta: 9:43:54, time: 0.581, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0765, decode.acc_seg: 96.2597, aux.loss_ce: 0.0472, aux.acc_seg: 94.7607, loss: 0.1237 2022-05-06 03:41:05,766 - mmseg - INFO - Saving checkpoint at 21000 iterations 2022-05-06 03:41:25,650 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 03:41:25,656 - mmseg - INFO - Iter [21000/80000] lr: 1.059e-06, eta: 9:44:11, time: 0.928, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0742, decode.acc_seg: 96.3083, aux.loss_ce: 0.0474, aux.acc_seg: 94.8254, loss: 0.1216 2022-05-06 03:41:52,562 - mmseg - INFO - Iter [21050/80000] lr: 1.058e-06, eta: 9:43:34, time: 0.540, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0690, decode.acc_seg: 96.5403, aux.loss_ce: 0.0438, aux.acc_seg: 95.0912, loss: 0.1128 2022-05-06 03:42:19,188 - mmseg - INFO - Iter [21100/80000] lr: 1.057e-06, eta: 9:42:56, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0709, decode.acc_seg: 96.4950, aux.loss_ce: 0.0443, aux.acc_seg: 95.1914, loss: 0.1152 2022-05-06 03:42:45,771 - mmseg - INFO - Iter [21150/80000] lr: 1.056e-06, eta: 9:42:18, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0682, decode.acc_seg: 96.3988, aux.loss_ce: 0.0438, aux.acc_seg: 94.8589, loss: 0.1121 2022-05-06 03:43:12,406 - mmseg - INFO - Iter [21200/80000] lr: 1.055e-06, eta: 9:41:39, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0797, decode.acc_seg: 96.1055, aux.loss_ce: 0.0503, aux.acc_seg: 94.4689, loss: 0.1300 2022-05-06 03:43:42,065 - mmseg - INFO - Iter [21250/80000] lr: 1.054e-06, eta: 9:41:10, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0802, decode.acc_seg: 95.8747, aux.loss_ce: 0.0500, aux.acc_seg: 94.3016, loss: 0.1301 2022-05-06 03:44:08,534 - mmseg - INFO - Iter [21300/80000] lr: 1.054e-06, eta: 9:40:31, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0755, decode.acc_seg: 96.2803, aux.loss_ce: 0.0467, aux.acc_seg: 94.8364, loss: 0.1222 2022-05-06 03:44:35,185 - mmseg - INFO - Iter [21350/80000] lr: 1.053e-06, eta: 9:39:53, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0721, decode.acc_seg: 96.4028, aux.loss_ce: 0.0458, aux.acc_seg: 94.9114, loss: 0.1178 2022-05-06 03:45:02,106 - mmseg - INFO - Iter [21400/80000] lr: 1.052e-06, eta: 9:39:16, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0711, decode.acc_seg: 96.4076, aux.loss_ce: 0.0454, aux.acc_seg: 94.9276, loss: 0.1164 2022-05-06 03:45:28,804 - mmseg - INFO - Iter [21450/80000] lr: 1.051e-06, eta: 9:38:38, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0721, decode.acc_seg: 96.3750, aux.loss_ce: 0.0457, aux.acc_seg: 94.8275, loss: 0.1178 2022-05-06 03:45:55,307 - mmseg - INFO - Iter [21500/80000] lr: 1.050e-06, eta: 9:38:00, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0685, decode.acc_seg: 96.6063, aux.loss_ce: 0.0432, aux.acc_seg: 95.2929, loss: 0.1116 2022-05-06 03:46:24,671 - mmseg - INFO - Iter [21550/80000] lr: 1.049e-06, eta: 9:37:30, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0767, decode.acc_seg: 96.1536, aux.loss_ce: 0.0470, aux.acc_seg: 94.7623, loss: 0.1237 2022-05-06 03:46:51,819 - mmseg - INFO - Iter [21600/80000] lr: 1.048e-06, eta: 9:36:53, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0728, decode.acc_seg: 96.2605, aux.loss_ce: 0.0446, aux.acc_seg: 94.9139, loss: 0.1175 2022-05-06 03:47:18,742 - mmseg - INFO - Iter [21650/80000] lr: 1.047e-06, eta: 9:36:16, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0756, decode.acc_seg: 96.3213, aux.loss_ce: 0.0476, aux.acc_seg: 94.7075, loss: 0.1232 2022-05-06 03:47:45,305 - mmseg - INFO - Iter [21700/80000] lr: 1.046e-06, eta: 9:35:39, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0786, decode.acc_seg: 96.1477, aux.loss_ce: 0.0473, aux.acc_seg: 94.6297, loss: 0.1259 2022-05-06 03:48:12,369 - mmseg - INFO - Iter [21750/80000] lr: 1.045e-06, eta: 9:35:02, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0691, decode.acc_seg: 96.5889, aux.loss_ce: 0.0434, aux.acc_seg: 95.1039, loss: 0.1124 2022-05-06 03:48:38,909 - mmseg - INFO - Iter [21800/80000] lr: 1.045e-06, eta: 9:34:24, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0661, decode.acc_seg: 96.6701, aux.loss_ce: 0.0431, aux.acc_seg: 95.2047, loss: 0.1092 2022-05-06 03:49:08,712 - mmseg - INFO - Iter [21850/80000] lr: 1.044e-06, eta: 9:33:55, time: 0.594, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0713, decode.acc_seg: 96.3675, aux.loss_ce: 0.0449, aux.acc_seg: 94.8383, loss: 0.1162 2022-05-06 03:49:35,728 - mmseg - INFO - Iter [21900/80000] lr: 1.043e-06, eta: 9:33:19, time: 0.542, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0730, decode.acc_seg: 96.4573, aux.loss_ce: 0.0453, aux.acc_seg: 94.9603, loss: 0.1183 2022-05-06 03:50:02,688 - mmseg - INFO - Iter [21950/80000] lr: 1.042e-06, eta: 9:32:42, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0756, decode.acc_seg: 96.2409, aux.loss_ce: 0.0466, aux.acc_seg: 94.8701, loss: 0.1222 2022-05-06 03:50:29,452 - mmseg - INFO - Saving checkpoint at 22000 iterations 2022-05-06 03:50:49,294 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 03:50:49,305 - mmseg - INFO - Iter [22000/80000] lr: 1.041e-06, eta: 9:32:57, time: 0.929, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0699, decode.acc_seg: 96.5807, aux.loss_ce: 0.0438, aux.acc_seg: 95.2281, loss: 0.1137 2022-05-06 03:51:16,440 - mmseg - INFO - Iter [22050/80000] lr: 1.040e-06, eta: 9:32:21, time: 0.546, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0769, decode.acc_seg: 96.1533, aux.loss_ce: 0.0481, aux.acc_seg: 94.6564, loss: 0.1250 2022-05-06 03:51:43,063 - mmseg - INFO - Iter [22100/80000] lr: 1.039e-06, eta: 9:31:44, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0720, decode.acc_seg: 96.3062, aux.loss_ce: 0.0448, aux.acc_seg: 94.8520, loss: 0.1169 2022-05-06 03:52:10,035 - mmseg - INFO - Iter [22150/80000] lr: 1.038e-06, eta: 9:31:07, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0754, decode.acc_seg: 96.1888, aux.loss_ce: 0.0472, aux.acc_seg: 94.6399, loss: 0.1225 2022-05-06 03:52:39,041 - mmseg - INFO - Iter [22200/80000] lr: 1.037e-06, eta: 9:30:36, time: 0.580, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0709, decode.acc_seg: 96.5827, aux.loss_ce: 0.0426, aux.acc_seg: 95.2160, loss: 0.1135 2022-05-06 03:53:05,596 - mmseg - INFO - Iter [22250/80000] lr: 1.036e-06, eta: 9:29:58, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0788, decode.acc_seg: 96.0512, aux.loss_ce: 0.0486, aux.acc_seg: 94.7031, loss: 0.1274 2022-05-06 03:53:32,401 - mmseg - INFO - Iter [22300/80000] lr: 1.036e-06, eta: 9:29:21, time: 0.536, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0712, decode.acc_seg: 96.4271, aux.loss_ce: 0.0444, aux.acc_seg: 95.0348, loss: 0.1155 2022-05-06 03:53:59,252 - mmseg - INFO - Iter [22350/80000] lr: 1.035e-06, eta: 9:28:45, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0665, decode.acc_seg: 96.5796, aux.loss_ce: 0.0427, aux.acc_seg: 95.0752, loss: 0.1093 2022-05-06 03:54:26,030 - mmseg - INFO - Iter [22400/80000] lr: 1.034e-06, eta: 9:28:08, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0702, decode.acc_seg: 96.3912, aux.loss_ce: 0.0450, aux.acc_seg: 94.7895, loss: 0.1152 2022-05-06 03:54:52,802 - mmseg - INFO - Iter [22450/80000] lr: 1.033e-06, eta: 9:27:31, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0718, decode.acc_seg: 96.4400, aux.loss_ce: 0.0454, aux.acc_seg: 94.9682, loss: 0.1172 2022-05-06 03:55:21,847 - mmseg - INFO - Iter [22500/80000] lr: 1.032e-06, eta: 9:27:00, time: 0.581, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0659, decode.acc_seg: 96.7099, aux.loss_ce: 0.0413, aux.acc_seg: 95.3431, loss: 0.1072 2022-05-06 03:55:48,680 - mmseg - INFO - Iter [22550/80000] lr: 1.031e-06, eta: 9:26:23, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0652, decode.acc_seg: 96.6429, aux.loss_ce: 0.0418, aux.acc_seg: 95.1970, loss: 0.1070 2022-05-06 03:56:15,236 - mmseg - INFO - Iter [22600/80000] lr: 1.030e-06, eta: 9:25:46, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0714, decode.acc_seg: 96.4072, aux.loss_ce: 0.0450, aux.acc_seg: 94.8825, loss: 0.1164 2022-05-06 03:56:41,883 - mmseg - INFO - Iter [22650/80000] lr: 1.029e-06, eta: 9:25:09, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0733, decode.acc_seg: 96.3324, aux.loss_ce: 0.0452, aux.acc_seg: 94.9094, loss: 0.1185 2022-05-06 03:57:08,533 - mmseg - INFO - Iter [22700/80000] lr: 1.028e-06, eta: 9:24:32, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0760, decode.acc_seg: 96.3253, aux.loss_ce: 0.0459, aux.acc_seg: 95.0349, loss: 0.1219 2022-05-06 03:57:35,045 - mmseg - INFO - Iter [22750/80000] lr: 1.028e-06, eta: 9:23:55, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0795, decode.acc_seg: 96.1766, aux.loss_ce: 0.0478, aux.acc_seg: 94.7785, loss: 0.1273 2022-05-06 03:58:04,460 - mmseg - INFO - Iter [22800/80000] lr: 1.027e-06, eta: 9:23:25, time: 0.588, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0717, decode.acc_seg: 96.2165, aux.loss_ce: 0.0444, aux.acc_seg: 94.8270, loss: 0.1161 2022-05-06 03:58:31,158 - mmseg - INFO - Iter [22850/80000] lr: 1.026e-06, eta: 9:22:49, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0805, decode.acc_seg: 96.0420, aux.loss_ce: 0.0483, aux.acc_seg: 94.7045, loss: 0.1288 2022-05-06 03:58:57,606 - mmseg - INFO - Iter [22900/80000] lr: 1.025e-06, eta: 9:22:11, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0701, decode.acc_seg: 96.5178, aux.loss_ce: 0.0430, aux.acc_seg: 95.1531, loss: 0.1130 2022-05-06 03:59:24,458 - mmseg - INFO - Iter [22950/80000] lr: 1.024e-06, eta: 9:21:35, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0655, decode.acc_seg: 96.6877, aux.loss_ce: 0.0412, aux.acc_seg: 95.2944, loss: 0.1067 2022-05-06 03:59:51,398 - mmseg - INFO - Saving checkpoint at 23000 iterations 2022-05-06 04:00:12,671 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:00:12,679 - mmseg - INFO - Iter [23000/80000] lr: 1.023e-06, eta: 9:21:52, time: 0.964, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0737, decode.acc_seg: 96.4162, aux.loss_ce: 0.0443, aux.acc_seg: 95.1280, loss: 0.1180 2022-05-06 04:00:39,791 - mmseg - INFO - Iter [23050/80000] lr: 1.022e-06, eta: 9:21:16, time: 0.544, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0731, decode.acc_seg: 96.2680, aux.loss_ce: 0.0453, aux.acc_seg: 94.7610, loss: 0.1184 2022-05-06 04:01:09,277 - mmseg - INFO - Iter [23100/80000] lr: 1.021e-06, eta: 9:20:46, time: 0.590, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0712, decode.acc_seg: 96.4716, aux.loss_ce: 0.0447, aux.acc_seg: 95.0177, loss: 0.1159 2022-05-06 04:01:35,798 - mmseg - INFO - Iter [23150/80000] lr: 1.020e-06, eta: 9:20:09, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0643, decode.acc_seg: 96.6909, aux.loss_ce: 0.0410, aux.acc_seg: 95.2798, loss: 0.1053 2022-05-06 04:02:02,289 - mmseg - INFO - Iter [23200/80000] lr: 1.019e-06, eta: 9:19:32, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0721, decode.acc_seg: 96.4070, aux.loss_ce: 0.0430, aux.acc_seg: 95.0617, loss: 0.1150 2022-05-06 04:02:28,861 - mmseg - INFO - Iter [23250/80000] lr: 1.019e-06, eta: 9:18:55, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0734, decode.acc_seg: 96.3075, aux.loss_ce: 0.0458, aux.acc_seg: 94.8290, loss: 0.1192 2022-05-06 04:02:55,343 - mmseg - INFO - Iter [23300/80000] lr: 1.018e-06, eta: 9:18:18, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0670, decode.acc_seg: 96.5655, aux.loss_ce: 0.0426, aux.acc_seg: 95.0886, loss: 0.1096 2022-05-06 04:03:21,741 - mmseg - INFO - Iter [23350/80000] lr: 1.017e-06, eta: 9:17:41, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0678, decode.acc_seg: 96.4149, aux.loss_ce: 0.0425, aux.acc_seg: 94.9687, loss: 0.1104 2022-05-06 04:03:48,606 - mmseg - INFO - Iter [23400/80000] lr: 1.016e-06, eta: 9:17:05, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0710, decode.acc_seg: 96.3540, aux.loss_ce: 0.0449, aux.acc_seg: 94.8229, loss: 0.1159 2022-05-06 04:04:18,104 - mmseg - INFO - Iter [23450/80000] lr: 1.015e-06, eta: 9:16:36, time: 0.590, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0705, decode.acc_seg: 96.5472, aux.loss_ce: 0.0434, aux.acc_seg: 95.1959, loss: 0.1138 2022-05-06 04:04:44,728 - mmseg - INFO - Iter [23500/80000] lr: 1.014e-06, eta: 9:15:59, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0733, decode.acc_seg: 96.4387, aux.loss_ce: 0.0444, aux.acc_seg: 95.0754, loss: 0.1177 2022-05-06 04:05:11,545 - mmseg - INFO - Iter [23550/80000] lr: 1.013e-06, eta: 9:15:23, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0747, decode.acc_seg: 96.3490, aux.loss_ce: 0.0468, aux.acc_seg: 94.7669, loss: 0.1215 2022-05-06 04:05:38,223 - mmseg - INFO - Iter [23600/80000] lr: 1.012e-06, eta: 9:14:47, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0686, decode.acc_seg: 96.5518, aux.loss_ce: 0.0436, aux.acc_seg: 95.0680, loss: 0.1122 2022-05-06 04:06:04,946 - mmseg - INFO - Iter [23650/80000] lr: 1.011e-06, eta: 9:14:11, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0675, decode.acc_seg: 96.5356, aux.loss_ce: 0.0424, aux.acc_seg: 95.1231, loss: 0.1099 2022-05-06 04:06:31,780 - mmseg - INFO - Iter [23700/80000] lr: 1.010e-06, eta: 9:13:35, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0661, decode.acc_seg: 96.5687, aux.loss_ce: 0.0415, aux.acc_seg: 95.1668, loss: 0.1076 2022-05-06 04:07:00,983 - mmseg - INFO - Iter [23750/80000] lr: 1.010e-06, eta: 9:13:05, time: 0.584, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0655, decode.acc_seg: 96.6343, aux.loss_ce: 0.0409, aux.acc_seg: 95.2818, loss: 0.1063 2022-05-06 04:07:27,471 - mmseg - INFO - Iter [23800/80000] lr: 1.009e-06, eta: 9:12:28, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0718, decode.acc_seg: 96.3219, aux.loss_ce: 0.0449, aux.acc_seg: 94.9045, loss: 0.1167 2022-05-06 04:07:54,374 - mmseg - INFO - Iter [23850/80000] lr: 1.008e-06, eta: 9:11:53, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0678, decode.acc_seg: 96.6594, aux.loss_ce: 0.0418, aux.acc_seg: 95.3550, loss: 0.1096 2022-05-06 04:08:20,955 - mmseg - INFO - Iter [23900/80000] lr: 1.007e-06, eta: 9:11:16, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0710, decode.acc_seg: 96.4347, aux.loss_ce: 0.0443, aux.acc_seg: 94.9938, loss: 0.1153 2022-05-06 04:08:47,590 - mmseg - INFO - Iter [23950/80000] lr: 1.006e-06, eta: 9:10:40, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0724, decode.acc_seg: 96.3630, aux.loss_ce: 0.0442, aux.acc_seg: 94.9764, loss: 0.1167 2022-05-06 04:09:14,114 - mmseg - INFO - Saving checkpoint at 24000 iterations 2022-05-06 04:09:34,054 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:09:34,063 - mmseg - INFO - Iter [24000/80000] lr: 1.005e-06, eta: 9:10:50, time: 0.927, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0625, decode.acc_seg: 96.8001, aux.loss_ce: 0.0402, aux.acc_seg: 95.3885, loss: 0.1027 2022-05-06 04:13:43,920 - mmseg - INFO - per class results: 2022-05-06 04:13:43,932 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 92.68 | 97.23 | | bag | 50.87 | 61.35 | | bed | 36.61 | 48.68 | | bedclothes | 45.43 | 68.64 | | bench | 32.46 | 43.43 | | bicycle | 83.15 | 93.64 | | bird | 93.74 | 97.79 | | boat | 84.3 | 93.38 | | book | 61.62 | 77.77 | | bottle | 88.34 | 96.76 | | building | 68.03 | 80.9 | | bus | 94.42 | 97.51 | | cabinet | 50.79 | 64.96 | | car | 93.72 | 96.83 | | cat | 93.31 | 98.54 | | ceiling | 60.52 | 76.2 | | chair | 65.21 | 76.44 | | cloth | 28.11 | 37.78 | | computer | 59.8 | 72.99 | | cow | 94.77 | 98.61 | | cup | 46.6 | 62.05 | | curtain | 60.44 | 74.67 | | dog | 91.98 | 97.35 | | door | 32.12 | 42.97 | | fence | 44.9 | 56.56 | | floor | 76.66 | 88.82 | | flower | 35.54 | 47.81 | | food | 37.43 | 43.18 | | grass | 82.84 | 90.95 | | ground | 57.4 | 70.29 | | horse | 94.25 | 98.04 | | keyboard | 89.26 | 94.61 | | light | 57.31 | 74.81 | | motorbike | 90.8 | 96.88 | | mountain | 56.32 | 73.13 | | mouse | 79.37 | 88.36 | | person | 90.76 | 96.54 | | plate | 29.87 | 39.84 | | platform | 60.9 | 78.52 | | pottedplant | 80.95 | 91.14 | | road | 53.62 | 71.95 | | rock | 52.49 | 58.44 | | sheep | 93.76 | 99.11 | | shelves | 36.69 | 51.39 | | sidewalk | 32.48 | 48.48 | | sign | 50.47 | 58.35 | | sky | 94.37 | 97.08 | | snow | 75.07 | 92.28 | | sofa | 62.18 | 72.71 | | table | 73.24 | 87.68 | | track | 71.79 | 85.45 | | train | 93.06 | 97.84 | | tree | 81.94 | 91.5 | | truck | 51.91 | 62.72 | | tvmonitor | 90.62 | 94.14 | | wall | 74.04 | 86.24 | | water | 91.76 | 96.32 | | window | 47.45 | 62.13 | | wood | 26.91 | 35.0 | +-------------+-------+-------+ 2022-05-06 04:13:43,932 - mmseg - INFO - Summary: 2022-05-06 04:13:43,932 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.52 | 66.57 | 76.86 | +-------+-------+-------+ 2022-05-06 04:13:43,934 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_16000.pth was removed 2022-05-06 04:14:03,211 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_24000.pth. 2022-05-06 04:14:03,220 - mmseg - INFO - Best mIoU is 0.6657 at 24000 iter. 2022-05-06 04:14:03,249 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:14:03,249 - mmseg - INFO - Iter(val) [638] aAcc: 0.8652, mIoU: 0.6657, mAcc: 0.7686, IoU.aeroplane: 0.9268, IoU.bag: 0.5087, IoU.bed: 0.3661, IoU.bedclothes: 0.4543, IoU.bench: 0.3246, IoU.bicycle: 0.8315, IoU.bird: 0.9374, IoU.boat: 0.8430, IoU.book: 0.6162, IoU.bottle: 0.8834, IoU.building: 0.6803, IoU.bus: 0.9442, IoU.cabinet: 0.5079, IoU.car: 0.9372, IoU.cat: 0.9331, IoU.ceiling: 0.6052, IoU.chair: 0.6521, IoU.cloth: 0.2811, IoU.computer: 0.5980, IoU.cow: 0.9477, IoU.cup: 0.4660, IoU.curtain: 0.6044, IoU.dog: 0.9198, IoU.door: 0.3212, IoU.fence: 0.4490, IoU.floor: 0.7666, IoU.flower: 0.3554, IoU.food: 0.3743, IoU.grass: 0.8284, IoU.ground: 0.5740, IoU.horse: 0.9425, IoU.keyboard: 0.8926, IoU.light: 0.5731, IoU.motorbike: 0.9080, IoU.mountain: 0.5632, IoU.mouse: 0.7937, IoU.person: 0.9076, IoU.plate: 0.2987, IoU.platform: 0.6090, IoU.pottedplant: 0.8095, IoU.road: 0.5362, IoU.rock: 0.5249, IoU.sheep: 0.9376, IoU.shelves: 0.3669, IoU.sidewalk: 0.3248, IoU.sign: 0.5047, IoU.sky: 0.9437, IoU.snow: 0.7507, IoU.sofa: 0.6218, IoU.table: 0.7324, IoU.track: 0.7179, IoU.train: 0.9306, IoU.tree: 0.8194, IoU.truck: 0.5191, IoU.tvmonitor: 0.9062, IoU.wall: 0.7404, IoU.water: 0.9176, IoU.window: 0.4745, IoU.wood: 0.2691, Acc.aeroplane: 0.9723, Acc.bag: 0.6135, Acc.bed: 0.4868, Acc.bedclothes: 0.6864, Acc.bench: 0.4343, Acc.bicycle: 0.9364, Acc.bird: 0.9779, Acc.boat: 0.9338, Acc.book: 0.7777, Acc.bottle: 0.9676, Acc.building: 0.8090, Acc.bus: 0.9751, Acc.cabinet: 0.6496, Acc.car: 0.9683, Acc.cat: 0.9854, Acc.ceiling: 0.7620, Acc.chair: 0.7644, Acc.cloth: 0.3778, Acc.computer: 0.7299, Acc.cow: 0.9861, Acc.cup: 0.6205, Acc.curtain: 0.7467, Acc.dog: 0.9735, Acc.door: 0.4297, Acc.fence: 0.5656, Acc.floor: 0.8882, Acc.flower: 0.4781, Acc.food: 0.4318, Acc.grass: 0.9095, Acc.ground: 0.7029, Acc.horse: 0.9804, Acc.keyboard: 0.9461, Acc.light: 0.7481, Acc.motorbike: 0.9688, Acc.mountain: 0.7313, Acc.mouse: 0.8836, Acc.person: 0.9654, Acc.plate: 0.3984, Acc.platform: 0.7852, Acc.pottedplant: 0.9114, Acc.road: 0.7195, Acc.rock: 0.5844, Acc.sheep: 0.9911, Acc.shelves: 0.5139, Acc.sidewalk: 0.4848, Acc.sign: 0.5835, Acc.sky: 0.9708, Acc.snow: 0.9228, Acc.sofa: 0.7271, Acc.table: 0.8768, Acc.track: 0.8545, Acc.train: 0.9784, Acc.tree: 0.9150, Acc.truck: 0.6272, Acc.tvmonitor: 0.9414, Acc.wall: 0.8624, Acc.water: 0.9632, Acc.window: 0.6213, Acc.wood: 0.3500 2022-05-06 04:14:32,934 - mmseg - INFO - Iter [24050/80000] lr: 1.004e-06, eta: 9:20:47, time: 5.980, data_time: 5.444, memory: 58091, decode.loss_ce: 0.0638, decode.acc_seg: 96.6249, aux.loss_ce: 0.0403, aux.acc_seg: 95.1983, loss: 0.1041 2022-05-06 04:14:59,844 - mmseg - INFO - Iter [24100/80000] lr: 1.003e-06, eta: 9:20:10, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0681, decode.acc_seg: 96.6608, aux.loss_ce: 0.0424, aux.acc_seg: 95.2928, loss: 0.1105 2022-05-06 04:15:26,939 - mmseg - INFO - Iter [24150/80000] lr: 1.002e-06, eta: 9:19:33, time: 0.542, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0694, decode.acc_seg: 96.4401, aux.loss_ce: 0.0428, aux.acc_seg: 95.0522, loss: 0.1122 2022-05-06 04:15:53,489 - mmseg - INFO - Iter [24200/80000] lr: 1.001e-06, eta: 9:18:55, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0727, decode.acc_seg: 96.4998, aux.loss_ce: 0.0447, aux.acc_seg: 95.1564, loss: 0.1174 2022-05-06 04:16:20,061 - mmseg - INFO - Iter [24250/80000] lr: 1.001e-06, eta: 9:18:17, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0693, decode.acc_seg: 96.4965, aux.loss_ce: 0.0424, aux.acc_seg: 95.1689, loss: 0.1117 2022-05-06 04:16:47,196 - mmseg - INFO - Iter [24300/80000] lr: 9.997e-07, eta: 9:17:40, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0797, decode.acc_seg: 96.2147, aux.loss_ce: 0.0469, aux.acc_seg: 94.8873, loss: 0.1266 2022-05-06 04:17:16,300 - mmseg - INFO - Iter [24350/80000] lr: 9.988e-07, eta: 9:17:08, time: 0.582, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0727, decode.acc_seg: 96.3674, aux.loss_ce: 0.0436, aux.acc_seg: 95.1196, loss: 0.1163 2022-05-06 04:17:43,490 - mmseg - INFO - Iter [24400/80000] lr: 9.979e-07, eta: 9:16:31, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0636, decode.acc_seg: 96.6974, aux.loss_ce: 0.0389, aux.acc_seg: 95.5175, loss: 0.1025 2022-05-06 04:18:10,145 - mmseg - INFO - Iter [24450/80000] lr: 9.970e-07, eta: 9:15:54, time: 0.535, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0683, decode.acc_seg: 96.5674, aux.loss_ce: 0.0423, aux.acc_seg: 95.1383, loss: 0.1106 2022-05-06 04:18:37,418 - mmseg - INFO - Iter [24500/80000] lr: 9.961e-07, eta: 9:15:18, time: 0.545, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0655, decode.acc_seg: 96.6014, aux.loss_ce: 0.0422, aux.acc_seg: 95.0631, loss: 0.1077 2022-05-06 04:19:04,304 - mmseg - INFO - Iter [24550/80000] lr: 9.952e-07, eta: 9:14:40, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0717, decode.acc_seg: 96.4105, aux.loss_ce: 0.0437, aux.acc_seg: 94.9932, loss: 0.1154 2022-05-06 04:19:30,973 - mmseg - INFO - Iter [24600/80000] lr: 9.943e-07, eta: 9:14:03, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0750, decode.acc_seg: 96.3602, aux.loss_ce: 0.0461, aux.acc_seg: 94.8909, loss: 0.1211 2022-05-06 04:20:00,499 - mmseg - INFO - Iter [24650/80000] lr: 9.934e-07, eta: 9:13:32, time: 0.591, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0707, decode.acc_seg: 96.3867, aux.loss_ce: 0.0410, aux.acc_seg: 95.2539, loss: 0.1118 2022-05-06 04:20:27,050 - mmseg - INFO - Iter [24700/80000] lr: 9.925e-07, eta: 9:12:54, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0672, decode.acc_seg: 96.6246, aux.loss_ce: 0.0420, aux.acc_seg: 95.2775, loss: 0.1092 2022-05-06 04:20:53,519 - mmseg - INFO - Iter [24750/80000] lr: 9.916e-07, eta: 9:12:16, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0634, decode.acc_seg: 96.7301, aux.loss_ce: 0.0391, aux.acc_seg: 95.4056, loss: 0.1024 2022-05-06 04:21:20,272 - mmseg - INFO - Iter [24800/80000] lr: 9.907e-07, eta: 9:11:39, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0649, decode.acc_seg: 96.7352, aux.loss_ce: 0.0408, aux.acc_seg: 95.3945, loss: 0.1057 2022-05-06 04:21:47,005 - mmseg - INFO - Iter [24850/80000] lr: 9.898e-07, eta: 9:11:02, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0668, decode.acc_seg: 96.6487, aux.loss_ce: 0.0414, aux.acc_seg: 95.3485, loss: 0.1082 2022-05-06 04:22:13,753 - mmseg - INFO - Iter [24900/80000] lr: 9.889e-07, eta: 9:10:25, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0682, decode.acc_seg: 96.5430, aux.loss_ce: 0.0429, aux.acc_seg: 95.1187, loss: 0.1111 2022-05-06 04:22:40,400 - mmseg - INFO - Iter [24950/80000] lr: 9.880e-07, eta: 9:09:47, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0656, decode.acc_seg: 96.6965, aux.loss_ce: 0.0418, aux.acc_seg: 95.2624, loss: 0.1074 2022-05-06 04:23:09,871 - mmseg - INFO - Saving checkpoint at 25000 iterations 2022-05-06 04:23:30,287 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:23:30,289 - mmseg - INFO - Iter [25000/80000] lr: 9.871e-07, eta: 9:10:01, time: 0.996, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0652, decode.acc_seg: 96.6745, aux.loss_ce: 0.0415, aux.acc_seg: 95.2682, loss: 0.1067 2022-05-06 04:23:57,491 - mmseg - INFO - Iter [25050/80000] lr: 9.862e-07, eta: 9:09:25, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0657, decode.acc_seg: 96.6552, aux.loss_ce: 0.0413, aux.acc_seg: 95.3527, loss: 0.1069 2022-05-06 04:24:24,481 - mmseg - INFO - Iter [25100/80000] lr: 9.853e-07, eta: 9:08:49, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0647, decode.acc_seg: 96.6807, aux.loss_ce: 0.0403, aux.acc_seg: 95.4256, loss: 0.1050 2022-05-06 04:24:51,146 - mmseg - INFO - Iter [25150/80000] lr: 9.844e-07, eta: 9:08:11, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0640, decode.acc_seg: 96.5607, aux.loss_ce: 0.0405, aux.acc_seg: 95.0628, loss: 0.1045 2022-05-06 04:25:17,952 - mmseg - INFO - Iter [25200/80000] lr: 9.835e-07, eta: 9:07:34, time: 0.536, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0654, decode.acc_seg: 96.6901, aux.loss_ce: 0.0412, aux.acc_seg: 95.3385, loss: 0.1067 2022-05-06 04:25:44,856 - mmseg - INFO - Iter [25250/80000] lr: 9.826e-07, eta: 9:06:58, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0608, decode.acc_seg: 96.9474, aux.loss_ce: 0.0387, aux.acc_seg: 95.6590, loss: 0.0995 2022-05-06 04:26:14,154 - mmseg - INFO - Iter [25300/80000] lr: 9.817e-07, eta: 9:06:26, time: 0.588, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0631, decode.acc_seg: 96.6420, aux.loss_ce: 0.0397, aux.acc_seg: 95.2131, loss: 0.1029 2022-05-06 04:26:40,816 - mmseg - INFO - Iter [25350/80000] lr: 9.808e-07, eta: 9:05:49, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0665, decode.acc_seg: 96.6187, aux.loss_ce: 0.0418, aux.acc_seg: 95.2746, loss: 0.1083 2022-05-06 04:27:07,662 - mmseg - INFO - Iter [25400/80000] lr: 9.799e-07, eta: 9:05:13, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0667, decode.acc_seg: 96.5851, aux.loss_ce: 0.0419, aux.acc_seg: 95.1907, loss: 0.1086 2022-05-06 04:27:34,774 - mmseg - INFO - Iter [25450/80000] lr: 9.791e-07, eta: 9:04:37, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0631, decode.acc_seg: 96.7259, aux.loss_ce: 0.0394, aux.acc_seg: 95.3605, loss: 0.1025 2022-05-06 04:28:01,405 - mmseg - INFO - Iter [25500/80000] lr: 9.782e-07, eta: 9:04:00, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0657, decode.acc_seg: 96.7270, aux.loss_ce: 0.0407, aux.acc_seg: 95.2828, loss: 0.1064 2022-05-06 04:28:28,055 - mmseg - INFO - Iter [25550/80000] lr: 9.773e-07, eta: 9:03:23, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0656, decode.acc_seg: 96.7209, aux.loss_ce: 0.0417, aux.acc_seg: 95.2485, loss: 0.1073 2022-05-06 04:28:57,330 - mmseg - INFO - Iter [25600/80000] lr: 9.764e-07, eta: 9:02:51, time: 0.586, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0681, decode.acc_seg: 96.6454, aux.loss_ce: 0.0420, aux.acc_seg: 95.3339, loss: 0.1101 2022-05-06 04:29:23,912 - mmseg - INFO - Iter [25650/80000] lr: 9.755e-07, eta: 9:02:14, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0618, decode.acc_seg: 96.7677, aux.loss_ce: 0.0388, aux.acc_seg: 95.4063, loss: 0.1006 2022-05-06 04:29:50,561 - mmseg - INFO - Iter [25700/80000] lr: 9.746e-07, eta: 9:01:37, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0697, decode.acc_seg: 96.4813, aux.loss_ce: 0.0430, aux.acc_seg: 95.1015, loss: 0.1126 2022-05-06 04:30:17,596 - mmseg - INFO - Iter [25750/80000] lr: 9.737e-07, eta: 9:01:01, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0722, decode.acc_seg: 96.4569, aux.loss_ce: 0.0428, aux.acc_seg: 95.1277, loss: 0.1151 2022-05-06 04:30:44,450 - mmseg - INFO - Iter [25800/80000] lr: 9.728e-07, eta: 9:00:25, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0668, decode.acc_seg: 96.5761, aux.loss_ce: 0.0412, aux.acc_seg: 95.2213, loss: 0.1080 2022-05-06 04:31:11,084 - mmseg - INFO - Iter [25850/80000] lr: 9.719e-07, eta: 8:59:48, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0615, decode.acc_seg: 96.8335, aux.loss_ce: 0.0385, aux.acc_seg: 95.5291, loss: 0.0999 2022-05-06 04:31:40,643 - mmseg - INFO - Iter [25900/80000] lr: 9.710e-07, eta: 8:59:18, time: 0.591, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0678, decode.acc_seg: 96.4781, aux.loss_ce: 0.0410, aux.acc_seg: 95.1456, loss: 0.1089 2022-05-06 04:32:07,428 - mmseg - INFO - Iter [25950/80000] lr: 9.701e-07, eta: 8:58:41, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0670, decode.acc_seg: 96.6583, aux.loss_ce: 0.0421, aux.acc_seg: 95.2389, loss: 0.1091 2022-05-06 04:32:34,398 - mmseg - INFO - Saving checkpoint at 26000 iterations 2022-05-06 04:32:54,678 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:32:54,683 - mmseg - INFO - Iter [26000/80000] lr: 9.692e-07, eta: 8:58:47, time: 0.943, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0664, decode.acc_seg: 96.6860, aux.loss_ce: 0.0405, aux.acc_seg: 95.3698, loss: 0.1070 2022-05-06 04:33:22,341 - mmseg - INFO - Iter [26050/80000] lr: 9.683e-07, eta: 8:58:13, time: 0.556, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0653, decode.acc_seg: 96.6691, aux.loss_ce: 0.0398, aux.acc_seg: 95.4204, loss: 0.1051 2022-05-06 04:33:49,043 - mmseg - INFO - Iter [26100/80000] lr: 9.674e-07, eta: 8:57:36, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0696, decode.acc_seg: 96.4510, aux.loss_ce: 0.0420, aux.acc_seg: 95.1604, loss: 0.1116 2022-05-06 04:34:15,722 - mmseg - INFO - Iter [26150/80000] lr: 9.665e-07, eta: 8:56:59, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0637, decode.acc_seg: 96.8001, aux.loss_ce: 0.0397, aux.acc_seg: 95.5487, loss: 0.1034 2022-05-06 04:34:42,718 - mmseg - INFO - Iter [26200/80000] lr: 9.656e-07, eta: 8:56:23, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0631, decode.acc_seg: 96.7811, aux.loss_ce: 0.0401, aux.acc_seg: 95.3981, loss: 0.1032 2022-05-06 04:35:11,567 - mmseg - INFO - Iter [26250/80000] lr: 9.647e-07, eta: 8:55:51, time: 0.579, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0633, decode.acc_seg: 96.6856, aux.loss_ce: 0.0401, aux.acc_seg: 95.2511, loss: 0.1034 2022-05-06 04:35:38,183 - mmseg - INFO - Iter [26300/80000] lr: 9.638e-07, eta: 8:55:15, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0644, decode.acc_seg: 96.6727, aux.loss_ce: 0.0412, aux.acc_seg: 95.1800, loss: 0.1057 2022-05-06 04:36:04,888 - mmseg - INFO - Iter [26350/80000] lr: 9.629e-07, eta: 8:54:38, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0630, decode.acc_seg: 96.8125, aux.loss_ce: 0.0391, aux.acc_seg: 95.5131, loss: 0.1021 2022-05-06 04:36:31,689 - mmseg - INFO - Iter [26400/80000] lr: 9.620e-07, eta: 8:54:02, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0638, decode.acc_seg: 96.7826, aux.loss_ce: 0.0403, aux.acc_seg: 95.3812, loss: 0.1041 2022-05-06 04:36:58,400 - mmseg - INFO - Iter [26450/80000] lr: 9.611e-07, eta: 8:53:26, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0634, decode.acc_seg: 96.8434, aux.loss_ce: 0.0399, aux.acc_seg: 95.5272, loss: 0.1033 2022-05-06 04:37:24,922 - mmseg - INFO - Iter [26500/80000] lr: 9.602e-07, eta: 8:52:49, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0704, decode.acc_seg: 96.5931, aux.loss_ce: 0.0425, aux.acc_seg: 95.2324, loss: 0.1129 2022-05-06 04:37:53,993 - mmseg - INFO - Iter [26550/80000] lr: 9.593e-07, eta: 8:52:18, time: 0.581, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0643, decode.acc_seg: 96.7360, aux.loss_ce: 0.0396, aux.acc_seg: 95.5006, loss: 0.1039 2022-05-06 04:38:20,683 - mmseg - INFO - Iter [26600/80000] lr: 9.584e-07, eta: 8:51:41, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0636, decode.acc_seg: 96.6884, aux.loss_ce: 0.0402, aux.acc_seg: 95.2922, loss: 0.1038 2022-05-06 04:38:47,276 - mmseg - INFO - Iter [26650/80000] lr: 9.575e-07, eta: 8:51:05, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0652, decode.acc_seg: 96.7234, aux.loss_ce: 0.0404, aux.acc_seg: 95.3414, loss: 0.1056 2022-05-06 04:39:14,196 - mmseg - INFO - Iter [26700/80000] lr: 9.566e-07, eta: 8:50:29, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0660, decode.acc_seg: 96.6235, aux.loss_ce: 0.0399, aux.acc_seg: 95.4192, loss: 0.1060 2022-05-06 04:39:41,101 - mmseg - INFO - Iter [26750/80000] lr: 9.557e-07, eta: 8:49:53, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0623, decode.acc_seg: 96.7107, aux.loss_ce: 0.0394, aux.acc_seg: 95.3072, loss: 0.1017 2022-05-06 04:40:08,003 - mmseg - INFO - Iter [26800/80000] lr: 9.548e-07, eta: 8:49:18, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0630, decode.acc_seg: 96.7189, aux.loss_ce: 0.0396, aux.acc_seg: 95.3562, loss: 0.1027 2022-05-06 04:40:37,168 - mmseg - INFO - Iter [26850/80000] lr: 9.539e-07, eta: 8:48:47, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0672, decode.acc_seg: 96.6122, aux.loss_ce: 0.0410, aux.acc_seg: 95.2636, loss: 0.1082 2022-05-06 04:41:04,497 - mmseg - INFO - Iter [26900/80000] lr: 9.530e-07, eta: 8:48:12, time: 0.547, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0634, decode.acc_seg: 96.7246, aux.loss_ce: 0.0396, aux.acc_seg: 95.3242, loss: 0.1030 2022-05-06 04:41:31,051 - mmseg - INFO - Iter [26950/80000] lr: 9.521e-07, eta: 8:47:35, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0617, decode.acc_seg: 96.8397, aux.loss_ce: 0.0380, aux.acc_seg: 95.6134, loss: 0.0996 2022-05-06 04:41:57,507 - mmseg - INFO - Saving checkpoint at 27000 iterations 2022-05-06 04:42:18,627 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:42:18,634 - mmseg - INFO - Iter [27000/80000] lr: 9.512e-07, eta: 8:47:40, time: 0.948, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0636, decode.acc_seg: 96.7586, aux.loss_ce: 0.0393, aux.acc_seg: 95.4609, loss: 0.1029 2022-05-06 04:42:45,724 - mmseg - INFO - Iter [27050/80000] lr: 9.503e-07, eta: 8:47:05, time: 0.545, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0639, decode.acc_seg: 96.8058, aux.loss_ce: 0.0394, aux.acc_seg: 95.5071, loss: 0.1033 2022-05-06 04:43:12,305 - mmseg - INFO - Iter [27100/80000] lr: 9.494e-07, eta: 8:46:29, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0609, decode.acc_seg: 96.8401, aux.loss_ce: 0.0392, aux.acc_seg: 95.3060, loss: 0.1001 2022-05-06 04:43:41,458 - mmseg - INFO - Iter [27150/80000] lr: 9.485e-07, eta: 8:45:58, time: 0.583, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0736, decode.acc_seg: 96.3366, aux.loss_ce: 0.0449, aux.acc_seg: 94.9316, loss: 0.1184 2022-05-06 04:44:08,338 - mmseg - INFO - Iter [27200/80000] lr: 9.476e-07, eta: 8:45:22, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0651, decode.acc_seg: 96.7729, aux.loss_ce: 0.0406, aux.acc_seg: 95.4612, loss: 0.1057 2022-05-06 04:44:35,056 - mmseg - INFO - Iter [27250/80000] lr: 9.467e-07, eta: 8:44:46, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0615, decode.acc_seg: 96.9172, aux.loss_ce: 0.0385, aux.acc_seg: 95.6203, loss: 0.1000 2022-05-06 04:45:02,242 - mmseg - INFO - Iter [27300/80000] lr: 9.458e-07, eta: 8:44:11, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0651, decode.acc_seg: 96.7573, aux.loss_ce: 0.0398, aux.acc_seg: 95.5634, loss: 0.1049 2022-05-06 04:45:29,044 - mmseg - INFO - Iter [27350/80000] lr: 9.450e-07, eta: 8:43:35, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0609, decode.acc_seg: 96.8448, aux.loss_ce: 0.0387, aux.acc_seg: 95.5449, loss: 0.0996 2022-05-06 04:45:55,727 - mmseg - INFO - Iter [27400/80000] lr: 9.441e-07, eta: 8:43:00, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0675, decode.acc_seg: 96.5399, aux.loss_ce: 0.0413, aux.acc_seg: 95.1692, loss: 0.1088 2022-05-06 04:46:22,441 - mmseg - INFO - Iter [27450/80000] lr: 9.432e-07, eta: 8:42:24, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0628, decode.acc_seg: 96.8378, aux.loss_ce: 0.0387, aux.acc_seg: 95.5377, loss: 0.1015 2022-05-06 04:46:51,601 - mmseg - INFO - Iter [27500/80000] lr: 9.423e-07, eta: 8:41:53, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0598, decode.acc_seg: 96.9615, aux.loss_ce: 0.0374, aux.acc_seg: 95.6513, loss: 0.0972 2022-05-06 04:47:18,526 - mmseg - INFO - Iter [27550/80000] lr: 9.414e-07, eta: 8:41:17, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0596, decode.acc_seg: 96.9368, aux.loss_ce: 0.0380, aux.acc_seg: 95.5594, loss: 0.0976 2022-05-06 04:47:45,463 - mmseg - INFO - Iter [27600/80000] lr: 9.405e-07, eta: 8:40:42, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0585, decode.acc_seg: 96.9818, aux.loss_ce: 0.0367, aux.acc_seg: 95.6462, loss: 0.0952 2022-05-06 04:48:12,142 - mmseg - INFO - Iter [27650/80000] lr: 9.396e-07, eta: 8:40:06, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0638, decode.acc_seg: 96.7658, aux.loss_ce: 0.0390, aux.acc_seg: 95.5198, loss: 0.1028 2022-05-06 04:48:38,936 - mmseg - INFO - Iter [27700/80000] lr: 9.387e-07, eta: 8:39:31, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0655, decode.acc_seg: 96.7195, aux.loss_ce: 0.0395, aux.acc_seg: 95.4404, loss: 0.1049 2022-05-06 04:49:05,700 - mmseg - INFO - Iter [27750/80000] lr: 9.378e-07, eta: 8:38:55, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0665, decode.acc_seg: 96.5481, aux.loss_ce: 0.0415, aux.acc_seg: 95.1128, loss: 0.1080 2022-05-06 04:49:34,953 - mmseg - INFO - Iter [27800/80000] lr: 9.369e-07, eta: 8:38:24, time: 0.585, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0600, decode.acc_seg: 96.9438, aux.loss_ce: 0.0379, aux.acc_seg: 95.5949, loss: 0.0979 2022-05-06 04:50:01,637 - mmseg - INFO - Iter [27850/80000] lr: 9.360e-07, eta: 8:37:49, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0596, decode.acc_seg: 96.9070, aux.loss_ce: 0.0386, aux.acc_seg: 95.4382, loss: 0.0982 2022-05-06 04:50:28,280 - mmseg - INFO - Iter [27900/80000] lr: 9.351e-07, eta: 8:37:13, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0609, decode.acc_seg: 96.8050, aux.loss_ce: 0.0383, aux.acc_seg: 95.5442, loss: 0.0992 2022-05-06 04:50:55,080 - mmseg - INFO - Iter [27950/80000] lr: 9.342e-07, eta: 8:36:38, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0627, decode.acc_seg: 96.7890, aux.loss_ce: 0.0394, aux.acc_seg: 95.4132, loss: 0.1021 2022-05-06 04:51:21,603 - mmseg - INFO - Saving checkpoint at 28000 iterations 2022-05-06 04:51:41,741 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 04:51:41,744 - mmseg - INFO - Iter [28000/80000] lr: 9.333e-07, eta: 8:36:39, time: 0.931, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0695, decode.acc_seg: 96.4930, aux.loss_ce: 0.0412, aux.acc_seg: 95.2786, loss: 0.1107 2022-05-06 04:52:09,123 - mmseg - INFO - Iter [28050/80000] lr: 9.324e-07, eta: 8:36:05, time: 0.549, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0615, decode.acc_seg: 96.7499, aux.loss_ce: 0.0382, aux.acc_seg: 95.4444, loss: 0.0997 2022-05-06 04:52:38,596 - mmseg - INFO - Iter [28100/80000] lr: 9.315e-07, eta: 8:35:35, time: 0.589, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0599, decode.acc_seg: 96.9010, aux.loss_ce: 0.0376, aux.acc_seg: 95.5867, loss: 0.0975 2022-05-06 04:53:05,650 - mmseg - INFO - Iter [28150/80000] lr: 9.306e-07, eta: 8:35:00, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0682, decode.acc_seg: 96.6049, aux.loss_ce: 0.0417, aux.acc_seg: 95.2762, loss: 0.1099 2022-05-06 04:53:32,298 - mmseg - INFO - Iter [28200/80000] lr: 9.297e-07, eta: 8:34:24, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0580, decode.acc_seg: 96.9933, aux.loss_ce: 0.0372, aux.acc_seg: 95.6572, loss: 0.0952 2022-05-06 04:53:58,890 - mmseg - INFO - Iter [28250/80000] lr: 9.288e-07, eta: 8:33:49, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0613, decode.acc_seg: 96.7381, aux.loss_ce: 0.0386, aux.acc_seg: 95.3328, loss: 0.0999 2022-05-06 04:54:25,552 - mmseg - INFO - Iter [28300/80000] lr: 9.279e-07, eta: 8:33:13, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0629, decode.acc_seg: 96.8328, aux.loss_ce: 0.0391, aux.acc_seg: 95.5642, loss: 0.1020 2022-05-06 04:54:52,597 - mmseg - INFO - Iter [28350/80000] lr: 9.270e-07, eta: 8:32:38, time: 0.540, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0642, decode.acc_seg: 96.7014, aux.loss_ce: 0.0399, aux.acc_seg: 95.4311, loss: 0.1041 2022-05-06 04:55:21,759 - mmseg - INFO - Iter [28400/80000] lr: 9.261e-07, eta: 8:32:07, time: 0.584, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0573, decode.acc_seg: 96.9424, aux.loss_ce: 0.0365, aux.acc_seg: 95.6003, loss: 0.0937 2022-05-06 04:55:48,389 - mmseg - INFO - Iter [28450/80000] lr: 9.252e-07, eta: 8:31:32, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0619, decode.acc_seg: 96.9410, aux.loss_ce: 0.0384, aux.acc_seg: 95.6285, loss: 0.1002 2022-05-06 04:56:15,217 - mmseg - INFO - Iter [28500/80000] lr: 9.243e-07, eta: 8:30:57, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0649, decode.acc_seg: 96.7660, aux.loss_ce: 0.0397, aux.acc_seg: 95.5287, loss: 0.1046 2022-05-06 04:56:41,734 - mmseg - INFO - Iter [28550/80000] lr: 9.234e-07, eta: 8:30:21, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0669, decode.acc_seg: 96.7211, aux.loss_ce: 0.0395, aux.acc_seg: 95.4628, loss: 0.1064 2022-05-06 04:57:08,387 - mmseg - INFO - Iter [28600/80000] lr: 9.225e-07, eta: 8:29:46, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0667, decode.acc_seg: 96.7149, aux.loss_ce: 0.0393, aux.acc_seg: 95.5090, loss: 0.1060 2022-05-06 04:57:34,860 - mmseg - INFO - Iter [28650/80000] lr: 9.216e-07, eta: 8:29:10, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0605, decode.acc_seg: 96.7388, aux.loss_ce: 0.0377, aux.acc_seg: 95.3730, loss: 0.0982 2022-05-06 04:58:01,702 - mmseg - INFO - Iter [28700/80000] lr: 9.207e-07, eta: 8:28:35, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0640, decode.acc_seg: 96.7711, aux.loss_ce: 0.0394, aux.acc_seg: 95.4806, loss: 0.1034 2022-05-06 04:58:30,998 - mmseg - INFO - Iter [28750/80000] lr: 9.198e-07, eta: 8:28:05, time: 0.586, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0636, decode.acc_seg: 96.8322, aux.loss_ce: 0.0397, aux.acc_seg: 95.4848, loss: 0.1033 2022-05-06 04:58:57,640 - mmseg - INFO - Iter [28800/80000] lr: 9.189e-07, eta: 8:27:30, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0568, decode.acc_seg: 97.0615, aux.loss_ce: 0.0363, aux.acc_seg: 95.7089, loss: 0.0931 2022-05-06 04:59:24,743 - mmseg - INFO - Iter [28850/80000] lr: 9.180e-07, eta: 8:26:55, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0617, decode.acc_seg: 96.7251, aux.loss_ce: 0.0383, aux.acc_seg: 95.4392, loss: 0.0999 2022-05-06 04:59:51,332 - mmseg - INFO - Iter [28900/80000] lr: 9.171e-07, eta: 8:26:20, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0665, decode.acc_seg: 96.7024, aux.loss_ce: 0.0399, aux.acc_seg: 95.4503, loss: 0.1064 2022-05-06 05:00:17,995 - mmseg - INFO - Iter [28950/80000] lr: 9.162e-07, eta: 8:25:45, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0683, decode.acc_seg: 96.5926, aux.loss_ce: 0.0405, aux.acc_seg: 95.4102, loss: 0.1087 2022-05-06 05:00:44,710 - mmseg - INFO - Saving checkpoint at 29000 iterations 2022-05-06 05:01:06,246 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:01:06,248 - mmseg - INFO - Iter [29000/80000] lr: 9.153e-07, eta: 8:25:47, time: 0.963, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0640, decode.acc_seg: 96.6581, aux.loss_ce: 0.0401, aux.acc_seg: 95.3238, loss: 0.1041 2022-05-06 05:01:35,709 - mmseg - INFO - Iter [29050/80000] lr: 9.144e-07, eta: 8:25:17, time: 0.591, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0609, decode.acc_seg: 96.8995, aux.loss_ce: 0.0389, aux.acc_seg: 95.5335, loss: 0.0998 2022-05-06 05:02:02,404 - mmseg - INFO - Iter [29100/80000] lr: 9.135e-07, eta: 8:24:42, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0600, decode.acc_seg: 97.0221, aux.loss_ce: 0.0378, aux.acc_seg: 95.7594, loss: 0.0978 2022-05-06 05:02:28,943 - mmseg - INFO - Iter [29150/80000] lr: 9.126e-07, eta: 8:24:07, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0599, decode.acc_seg: 96.9382, aux.loss_ce: 0.0391, aux.acc_seg: 95.4628, loss: 0.0990 2022-05-06 05:02:55,569 - mmseg - INFO - Iter [29200/80000] lr: 9.117e-07, eta: 8:23:32, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0608, decode.acc_seg: 96.8107, aux.loss_ce: 0.0385, aux.acc_seg: 95.4575, loss: 0.0993 2022-05-06 05:03:22,147 - mmseg - INFO - Iter [29250/80000] lr: 9.109e-07, eta: 8:22:56, time: 0.533, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0588, decode.acc_seg: 96.9245, aux.loss_ce: 0.0370, aux.acc_seg: 95.5888, loss: 0.0958 2022-05-06 05:03:48,699 - mmseg - INFO - Iter [29300/80000] lr: 9.100e-07, eta: 8:22:21, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0561, decode.acc_seg: 97.0793, aux.loss_ce: 0.0359, aux.acc_seg: 95.7959, loss: 0.0919 2022-05-06 05:04:18,361 - mmseg - INFO - Iter [29350/80000] lr: 9.091e-07, eta: 8:21:51, time: 0.591, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0605, decode.acc_seg: 96.9569, aux.loss_ce: 0.0384, aux.acc_seg: 95.5966, loss: 0.0990 2022-05-06 05:04:44,933 - mmseg - INFO - Iter [29400/80000] lr: 9.082e-07, eta: 8:21:16, time: 0.533, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0582, decode.acc_seg: 97.0278, aux.loss_ce: 0.0375, aux.acc_seg: 95.6411, loss: 0.0958 2022-05-06 05:05:11,557 - mmseg - INFO - Iter [29450/80000] lr: 9.073e-07, eta: 8:20:41, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0602, decode.acc_seg: 96.9679, aux.loss_ce: 0.0371, aux.acc_seg: 95.7250, loss: 0.0973 2022-05-06 05:05:38,136 - mmseg - INFO - Iter [29500/80000] lr: 9.064e-07, eta: 8:20:06, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0599, decode.acc_seg: 96.8324, aux.loss_ce: 0.0376, aux.acc_seg: 95.4296, loss: 0.0975 2022-05-06 05:06:04,559 - mmseg - INFO - Iter [29550/80000] lr: 9.055e-07, eta: 8:19:31, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0620, decode.acc_seg: 96.7598, aux.loss_ce: 0.0386, aux.acc_seg: 95.4715, loss: 0.1007 2022-05-06 05:06:31,249 - mmseg - INFO - Iter [29600/80000] lr: 9.046e-07, eta: 8:18:56, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0576, decode.acc_seg: 97.0528, aux.loss_ce: 0.0364, aux.acc_seg: 95.7775, loss: 0.0940 2022-05-06 05:07:00,475 - mmseg - INFO - Iter [29650/80000] lr: 9.037e-07, eta: 8:18:25, time: 0.585, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0575, decode.acc_seg: 97.0238, aux.loss_ce: 0.0373, aux.acc_seg: 95.6440, loss: 0.0948 2022-05-06 05:07:27,272 - mmseg - INFO - Iter [29700/80000] lr: 9.028e-07, eta: 8:17:51, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0619, decode.acc_seg: 96.8105, aux.loss_ce: 0.0382, aux.acc_seg: 95.5430, loss: 0.1001 2022-05-06 05:07:54,242 - mmseg - INFO - Iter [29750/80000] lr: 9.019e-07, eta: 8:17:17, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0588, decode.acc_seg: 96.9339, aux.loss_ce: 0.0364, aux.acc_seg: 95.7187, loss: 0.0952 2022-05-06 05:08:20,653 - mmseg - INFO - Iter [29800/80000] lr: 9.010e-07, eta: 8:16:41, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0573, decode.acc_seg: 97.0517, aux.loss_ce: 0.0359, aux.acc_seg: 95.8025, loss: 0.0932 2022-05-06 05:08:47,502 - mmseg - INFO - Iter [29850/80000] lr: 9.001e-07, eta: 8:16:07, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0553, decode.acc_seg: 97.1359, aux.loss_ce: 0.0356, aux.acc_seg: 95.8474, loss: 0.0909 2022-05-06 05:09:13,967 - mmseg - INFO - Iter [29900/80000] lr: 8.992e-07, eta: 8:15:32, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0627, decode.acc_seg: 96.8421, aux.loss_ce: 0.0387, aux.acc_seg: 95.5836, loss: 0.1014 2022-05-06 05:09:40,526 - mmseg - INFO - Iter [29950/80000] lr: 8.983e-07, eta: 8:14:57, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0574, decode.acc_seg: 96.9952, aux.loss_ce: 0.0361, aux.acc_seg: 95.6534, loss: 0.0934 2022-05-06 05:10:09,588 - mmseg - INFO - Saving checkpoint at 30000 iterations 2022-05-06 05:10:30,717 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:10:30,736 - mmseg - INFO - Iter [30000/80000] lr: 8.974e-07, eta: 8:15:01, time: 1.001, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0593, decode.acc_seg: 96.9764, aux.loss_ce: 0.0378, aux.acc_seg: 95.6887, loss: 0.0970 2022-05-06 05:10:57,811 - mmseg - INFO - Iter [30050/80000] lr: 8.965e-07, eta: 8:14:27, time: 0.545, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0595, decode.acc_seg: 96.9556, aux.loss_ce: 0.0372, aux.acc_seg: 95.7569, loss: 0.0967 2022-05-06 05:11:24,414 - mmseg - INFO - Iter [30100/80000] lr: 8.956e-07, eta: 8:13:53, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0561, decode.acc_seg: 97.1784, aux.loss_ce: 0.0353, aux.acc_seg: 95.9165, loss: 0.0914 2022-05-06 05:11:51,244 - mmseg - INFO - Iter [30150/80000] lr: 8.947e-07, eta: 8:13:18, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0590, decode.acc_seg: 96.8164, aux.loss_ce: 0.0372, aux.acc_seg: 95.4617, loss: 0.0962 2022-05-06 05:12:17,890 - mmseg - INFO - Iter [30200/80000] lr: 8.938e-07, eta: 8:12:43, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0591, decode.acc_seg: 96.9517, aux.loss_ce: 0.0367, aux.acc_seg: 95.6159, loss: 0.0959 2022-05-06 05:12:44,309 - mmseg - INFO - Iter [30250/80000] lr: 8.929e-07, eta: 8:12:08, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0653, decode.acc_seg: 96.6650, aux.loss_ce: 0.0391, aux.acc_seg: 95.4832, loss: 0.1044 2022-05-06 05:13:13,668 - mmseg - INFO - Iter [30300/80000] lr: 8.920e-07, eta: 8:11:38, time: 0.587, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0567, decode.acc_seg: 97.0172, aux.loss_ce: 0.0356, aux.acc_seg: 95.6925, loss: 0.0923 2022-05-06 05:13:40,368 - mmseg - INFO - Iter [30350/80000] lr: 8.911e-07, eta: 8:11:04, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0574, decode.acc_seg: 97.0152, aux.loss_ce: 0.0359, aux.acc_seg: 95.7793, loss: 0.0933 2022-05-06 05:14:07,169 - mmseg - INFO - Iter [30400/80000] lr: 8.902e-07, eta: 8:10:29, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0591, decode.acc_seg: 96.9528, aux.loss_ce: 0.0379, aux.acc_seg: 95.5801, loss: 0.0970 2022-05-06 05:14:33,909 - mmseg - INFO - Iter [30450/80000] lr: 8.893e-07, eta: 8:09:55, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0613, decode.acc_seg: 96.9170, aux.loss_ce: 0.0389, aux.acc_seg: 95.6025, loss: 0.1002 2022-05-06 05:15:00,763 - mmseg - INFO - Iter [30500/80000] lr: 8.884e-07, eta: 8:09:21, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0585, decode.acc_seg: 96.8627, aux.loss_ce: 0.0359, aux.acc_seg: 95.5961, loss: 0.0944 2022-05-06 05:15:27,350 - mmseg - INFO - Iter [30550/80000] lr: 8.875e-07, eta: 8:08:46, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0603, decode.acc_seg: 96.8582, aux.loss_ce: 0.0377, aux.acc_seg: 95.5528, loss: 0.0980 2022-05-06 05:15:56,495 - mmseg - INFO - Iter [30600/80000] lr: 8.866e-07, eta: 8:08:16, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0615, decode.acc_seg: 96.7849, aux.loss_ce: 0.0368, aux.acc_seg: 95.5432, loss: 0.0983 2022-05-06 05:16:22,964 - mmseg - INFO - Iter [30650/80000] lr: 8.857e-07, eta: 8:07:41, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0590, decode.acc_seg: 96.9882, aux.loss_ce: 0.0362, aux.acc_seg: 95.7743, loss: 0.0952 2022-05-06 05:16:49,569 - mmseg - INFO - Iter [30700/80000] lr: 8.848e-07, eta: 8:07:06, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0620, decode.acc_seg: 96.7970, aux.loss_ce: 0.0376, aux.acc_seg: 95.4848, loss: 0.0996 2022-05-06 05:17:16,244 - mmseg - INFO - Iter [30750/80000] lr: 8.839e-07, eta: 8:06:32, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0639, decode.acc_seg: 96.8493, aux.loss_ce: 0.0386, aux.acc_seg: 95.5581, loss: 0.1025 2022-05-06 05:17:42,993 - mmseg - INFO - Iter [30800/80000] lr: 8.830e-07, eta: 8:05:58, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0636, decode.acc_seg: 96.7532, aux.loss_ce: 0.0387, aux.acc_seg: 95.4145, loss: 0.1023 2022-05-06 05:18:09,671 - mmseg - INFO - Iter [30850/80000] lr: 8.821e-07, eta: 8:05:23, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0565, decode.acc_seg: 97.1140, aux.loss_ce: 0.0349, aux.acc_seg: 95.8527, loss: 0.0914 2022-05-06 05:18:38,842 - mmseg - INFO - Iter [30900/80000] lr: 8.812e-07, eta: 8:04:53, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0691, decode.acc_seg: 96.6066, aux.loss_ce: 0.0393, aux.acc_seg: 95.4357, loss: 0.1084 2022-05-06 05:19:05,782 - mmseg - INFO - Iter [30950/80000] lr: 8.803e-07, eta: 8:04:19, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0591, decode.acc_seg: 96.9204, aux.loss_ce: 0.0368, aux.acc_seg: 95.6059, loss: 0.0958 2022-05-06 05:19:32,579 - mmseg - INFO - Saving checkpoint at 31000 iterations 2022-05-06 05:19:52,977 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:19:52,980 - mmseg - INFO - Iter [31000/80000] lr: 8.794e-07, eta: 8:04:17, time: 0.940, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0627, decode.acc_seg: 96.8580, aux.loss_ce: 0.0389, aux.acc_seg: 95.5816, loss: 0.1016 2022-05-06 05:20:20,261 - mmseg - INFO - Iter [31050/80000] lr: 8.785e-07, eta: 8:03:44, time: 0.549, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0583, decode.acc_seg: 96.9870, aux.loss_ce: 0.0368, aux.acc_seg: 95.6223, loss: 0.0952 2022-05-06 05:20:46,945 - mmseg - INFO - Iter [31100/80000] lr: 8.776e-07, eta: 8:03:10, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0600, decode.acc_seg: 96.9180, aux.loss_ce: 0.0370, aux.acc_seg: 95.6520, loss: 0.0971 2022-05-06 05:21:13,518 - mmseg - INFO - Iter [31150/80000] lr: 8.768e-07, eta: 8:02:35, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0605, decode.acc_seg: 96.8667, aux.loss_ce: 0.0369, aux.acc_seg: 95.6452, loss: 0.0973 2022-05-06 05:21:40,291 - mmseg - INFO - Iter [31200/80000] lr: 8.759e-07, eta: 8:02:01, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0619, decode.acc_seg: 96.7201, aux.loss_ce: 0.0389, aux.acc_seg: 95.2580, loss: 0.1008 2022-05-06 05:22:09,597 - mmseg - INFO - Iter [31250/80000] lr: 8.750e-07, eta: 8:01:31, time: 0.586, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0589, decode.acc_seg: 96.9220, aux.loss_ce: 0.0368, aux.acc_seg: 95.6221, loss: 0.0957 2022-05-06 05:22:36,164 - mmseg - INFO - Iter [31300/80000] lr: 8.741e-07, eta: 8:00:56, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0611, decode.acc_seg: 96.8822, aux.loss_ce: 0.0377, aux.acc_seg: 95.6380, loss: 0.0988 2022-05-06 05:23:02,869 - mmseg - INFO - Iter [31350/80000] lr: 8.732e-07, eta: 8:00:22, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0596, decode.acc_seg: 96.8386, aux.loss_ce: 0.0364, aux.acc_seg: 95.5787, loss: 0.0961 2022-05-06 05:23:29,450 - mmseg - INFO - Iter [31400/80000] lr: 8.723e-07, eta: 7:59:48, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0585, decode.acc_seg: 96.9893, aux.loss_ce: 0.0365, aux.acc_seg: 95.7189, loss: 0.0950 2022-05-06 05:23:56,087 - mmseg - INFO - Iter [31450/80000] lr: 8.714e-07, eta: 7:59:14, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0548, decode.acc_seg: 97.1144, aux.loss_ce: 0.0345, aux.acc_seg: 95.8831, loss: 0.0893 2022-05-06 05:24:22,827 - mmseg - INFO - Iter [31500/80000] lr: 8.705e-07, eta: 7:58:40, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0597, decode.acc_seg: 96.8158, aux.loss_ce: 0.0365, aux.acc_seg: 95.5828, loss: 0.0962 2022-05-06 05:24:52,216 - mmseg - INFO - Iter [31550/80000] lr: 8.696e-07, eta: 7:58:10, time: 0.588, data_time: 0.058, memory: 58091, decode.loss_ce: 0.0577, decode.acc_seg: 97.0866, aux.loss_ce: 0.0360, aux.acc_seg: 95.8420, loss: 0.0936 2022-05-06 05:25:19,250 - mmseg - INFO - Iter [31600/80000] lr: 8.687e-07, eta: 7:57:36, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0575, decode.acc_seg: 96.8255, aux.loss_ce: 0.0356, aux.acc_seg: 95.5259, loss: 0.0931 2022-05-06 05:25:45,950 - mmseg - INFO - Iter [31650/80000] lr: 8.678e-07, eta: 7:57:02, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0593, decode.acc_seg: 97.0086, aux.loss_ce: 0.0370, aux.acc_seg: 95.7542, loss: 0.0963 2022-05-06 05:26:12,842 - mmseg - INFO - Iter [31700/80000] lr: 8.669e-07, eta: 7:56:28, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0605, decode.acc_seg: 96.9271, aux.loss_ce: 0.0370, aux.acc_seg: 95.6491, loss: 0.0975 2022-05-06 05:26:39,492 - mmseg - INFO - Iter [31750/80000] lr: 8.660e-07, eta: 7:55:54, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0564, decode.acc_seg: 97.0241, aux.loss_ce: 0.0353, aux.acc_seg: 95.7230, loss: 0.0918 2022-05-06 05:27:06,471 - mmseg - INFO - Iter [31800/80000] lr: 8.651e-07, eta: 7:55:21, time: 0.541, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0542, decode.acc_seg: 97.2556, aux.loss_ce: 0.0349, aux.acc_seg: 95.9136, loss: 0.0891 2022-05-06 05:27:35,603 - mmseg - INFO - Iter [31850/80000] lr: 8.642e-07, eta: 7:54:51, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0597, decode.acc_seg: 96.9711, aux.loss_ce: 0.0368, aux.acc_seg: 95.6572, loss: 0.0965 2022-05-06 05:28:02,404 - mmseg - INFO - Iter [31900/80000] lr: 8.633e-07, eta: 7:54:17, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0547, decode.acc_seg: 97.1365, aux.loss_ce: 0.0343, aux.acc_seg: 95.9421, loss: 0.0890 2022-05-06 05:28:29,247 - mmseg - INFO - Iter [31950/80000] lr: 8.624e-07, eta: 7:53:43, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0565, decode.acc_seg: 97.1415, aux.loss_ce: 0.0355, aux.acc_seg: 95.9179, loss: 0.0920 2022-05-06 05:28:55,949 - mmseg - INFO - Saving checkpoint at 32000 iterations 2022-05-06 05:29:16,540 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:29:16,543 - mmseg - INFO - Iter [32000/80000] lr: 8.615e-07, eta: 7:53:40, time: 0.946, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0546, decode.acc_seg: 97.0866, aux.loss_ce: 0.0343, aux.acc_seg: 95.8404, loss: 0.0889 2022-05-06 05:33:25,534 - mmseg - INFO - per class results: 2022-05-06 05:33:25,540 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 93.11 | 97.3 | | bag | 47.8 | 62.39 | | bed | 35.56 | 48.2 | | bedclothes | 43.59 | 62.97 | | bench | 30.23 | 37.1 | | bicycle | 83.5 | 93.35 | | bird | 94.37 | 97.99 | | boat | 85.79 | 91.9 | | book | 61.03 | 75.27 | | bottle | 89.21 | 96.75 | | building | 67.91 | 80.06 | | bus | 94.58 | 97.26 | | cabinet | 50.62 | 65.12 | | car | 93.9 | 96.69 | | cat | 93.79 | 97.94 | | ceiling | 58.7 | 75.25 | | chair | 65.18 | 78.98 | | cloth | 24.28 | 30.97 | | computer | 62.88 | 72.93 | | cow | 95.37 | 98.39 | | cup | 45.27 | 62.56 | | curtain | 59.0 | 72.92 | | dog | 92.25 | 97.99 | | door | 34.85 | 48.52 | | fence | 45.82 | 59.2 | | floor | 76.34 | 88.57 | | flower | 33.28 | 43.72 | | food | 42.38 | 52.74 | | grass | 83.4 | 92.77 | | ground | 57.77 | 72.34 | | horse | 94.46 | 97.86 | | keyboard | 89.54 | 95.41 | | light | 59.23 | 75.3 | | motorbike | 90.8 | 96.8 | | mountain | 59.08 | 73.72 | | mouse | 82.55 | 90.78 | | person | 90.45 | 96.59 | | plate | 29.83 | 41.4 | | platform | 59.36 | 71.84 | | pottedplant | 82.14 | 90.4 | | road | 53.99 | 71.24 | | rock | 54.91 | 62.37 | | sheep | 94.42 | 98.93 | | shelves | 31.69 | 37.23 | | sidewalk | 31.58 | 44.08 | | sign | 52.57 | 59.46 | | sky | 94.78 | 96.96 | | snow | 77.72 | 90.28 | | sofa | 61.5 | 72.07 | | table | 73.51 | 84.73 | | track | 72.43 | 82.54 | | train | 93.07 | 97.49 | | tree | 82.12 | 91.26 | | truck | 50.81 | 57.23 | | tvmonitor | 90.43 | 93.94 | | wall | 73.65 | 87.85 | | water | 91.89 | 96.0 | | window | 47.08 | 61.74 | | wood | 25.37 | 32.8 | +-------------+-------+-------+ 2022-05-06 05:33:25,541 - mmseg - INFO - Summary: 2022-05-06 05:33:25,541 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.59 | 66.66 | 76.21 | +-------+-------+-------+ 2022-05-06 05:33:25,543 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_24000.pth was removed 2022-05-06 05:33:45,219 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_32000.pth. 2022-05-06 05:33:45,230 - mmseg - INFO - Best mIoU is 0.6666 at 32000 iter. 2022-05-06 05:33:45,256 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:33:45,256 - mmseg - INFO - Iter(val) [638] aAcc: 0.8659, mIoU: 0.6666, mAcc: 0.7621, IoU.aeroplane: 0.9311, IoU.bag: 0.4780, IoU.bed: 0.3556, IoU.bedclothes: 0.4359, IoU.bench: 0.3023, IoU.bicycle: 0.8350, IoU.bird: 0.9437, IoU.boat: 0.8579, IoU.book: 0.6103, IoU.bottle: 0.8921, IoU.building: 0.6791, IoU.bus: 0.9458, IoU.cabinet: 0.5062, IoU.car: 0.9390, IoU.cat: 0.9379, IoU.ceiling: 0.5870, IoU.chair: 0.6518, IoU.cloth: 0.2428, IoU.computer: 0.6288, IoU.cow: 0.9537, IoU.cup: 0.4527, IoU.curtain: 0.5900, IoU.dog: 0.9225, IoU.door: 0.3485, IoU.fence: 0.4582, IoU.floor: 0.7634, IoU.flower: 0.3328, IoU.food: 0.4238, IoU.grass: 0.8340, IoU.ground: 0.5777, IoU.horse: 0.9446, IoU.keyboard: 0.8954, IoU.light: 0.5923, IoU.motorbike: 0.9080, IoU.mountain: 0.5908, IoU.mouse: 0.8255, IoU.person: 0.9045, IoU.plate: 0.2983, IoU.platform: 0.5936, IoU.pottedplant: 0.8214, IoU.road: 0.5399, IoU.rock: 0.5491, IoU.sheep: 0.9442, IoU.shelves: 0.3169, IoU.sidewalk: 0.3158, IoU.sign: 0.5257, IoU.sky: 0.9478, IoU.snow: 0.7772, IoU.sofa: 0.6150, IoU.table: 0.7351, IoU.track: 0.7243, IoU.train: 0.9307, IoU.tree: 0.8212, IoU.truck: 0.5081, IoU.tvmonitor: 0.9043, IoU.wall: 0.7365, IoU.water: 0.9189, IoU.window: 0.4708, IoU.wood: 0.2537, Acc.aeroplane: 0.9730, Acc.bag: 0.6239, Acc.bed: 0.4820, Acc.bedclothes: 0.6297, Acc.bench: 0.3710, Acc.bicycle: 0.9335, Acc.bird: 0.9799, Acc.boat: 0.9190, Acc.book: 0.7527, Acc.bottle: 0.9675, Acc.building: 0.8006, Acc.bus: 0.9726, Acc.cabinet: 0.6512, Acc.car: 0.9669, Acc.cat: 0.9794, Acc.ceiling: 0.7525, Acc.chair: 0.7898, Acc.cloth: 0.3097, Acc.computer: 0.7293, Acc.cow: 0.9839, Acc.cup: 0.6256, Acc.curtain: 0.7292, Acc.dog: 0.9799, Acc.door: 0.4852, Acc.fence: 0.5920, Acc.floor: 0.8857, Acc.flower: 0.4372, Acc.food: 0.5274, Acc.grass: 0.9277, Acc.ground: 0.7234, Acc.horse: 0.9786, Acc.keyboard: 0.9541, Acc.light: 0.7530, Acc.motorbike: 0.9680, Acc.mountain: 0.7372, Acc.mouse: 0.9078, Acc.person: 0.9659, Acc.plate: 0.4140, Acc.platform: 0.7184, Acc.pottedplant: 0.9040, Acc.road: 0.7124, Acc.rock: 0.6237, Acc.sheep: 0.9893, Acc.shelves: 0.3723, Acc.sidewalk: 0.4408, Acc.sign: 0.5946, Acc.sky: 0.9696, Acc.snow: 0.9028, Acc.sofa: 0.7207, Acc.table: 0.8473, Acc.track: 0.8254, Acc.train: 0.9749, Acc.tree: 0.9126, Acc.truck: 0.5723, Acc.tvmonitor: 0.9394, Acc.wall: 0.8785, Acc.water: 0.9600, Acc.window: 0.6174, Acc.wood: 0.3280 2022-05-06 05:34:12,361 - mmseg - INFO - Iter [32050/80000] lr: 8.606e-07, eta: 7:59:49, time: 5.918, data_time: 5.381, memory: 58091, decode.loss_ce: 0.0520, decode.acc_seg: 97.3037, aux.loss_ce: 0.0329, aux.acc_seg: 96.1136, loss: 0.0849 2022-05-06 05:34:39,216 - mmseg - INFO - Iter [32100/80000] lr: 8.597e-07, eta: 7:59:14, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0557, decode.acc_seg: 97.0308, aux.loss_ce: 0.0355, aux.acc_seg: 95.6808, loss: 0.0912 2022-05-06 05:35:08,465 - mmseg - INFO - Iter [32150/80000] lr: 8.588e-07, eta: 7:58:43, time: 0.587, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0610, decode.acc_seg: 96.9651, aux.loss_ce: 0.0376, aux.acc_seg: 95.7639, loss: 0.0986 2022-05-06 05:35:35,186 - mmseg - INFO - Iter [32200/80000] lr: 8.579e-07, eta: 7:58:08, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0555, decode.acc_seg: 97.0230, aux.loss_ce: 0.0349, aux.acc_seg: 95.7287, loss: 0.0904 2022-05-06 05:36:01,864 - mmseg - INFO - Iter [32250/80000] lr: 8.570e-07, eta: 7:57:33, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0602, decode.acc_seg: 96.9299, aux.loss_ce: 0.0371, aux.acc_seg: 95.6461, loss: 0.0973 2022-05-06 05:36:28,589 - mmseg - INFO - Iter [32300/80000] lr: 8.561e-07, eta: 7:56:58, time: 0.535, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0566, decode.acc_seg: 97.0870, aux.loss_ce: 0.0350, aux.acc_seg: 95.9019, loss: 0.0916 2022-05-06 05:36:55,388 - mmseg - INFO - Iter [32350/80000] lr: 8.552e-07, eta: 7:56:23, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0558, decode.acc_seg: 97.0201, aux.loss_ce: 0.0352, aux.acc_seg: 95.7400, loss: 0.0910 2022-05-06 05:37:22,637 - mmseg - INFO - Iter [32400/80000] lr: 8.543e-07, eta: 7:55:49, time: 0.545, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0622, decode.acc_seg: 96.8067, aux.loss_ce: 0.0381, aux.acc_seg: 95.4346, loss: 0.1002 2022-05-06 05:37:51,791 - mmseg - INFO - Iter [32450/80000] lr: 8.534e-07, eta: 7:55:18, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0700, decode.acc_seg: 96.7862, aux.loss_ce: 0.0394, aux.acc_seg: 95.5537, loss: 0.1094 2022-05-06 05:38:18,627 - mmseg - INFO - Iter [32500/80000] lr: 8.525e-07, eta: 7:54:44, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0603, decode.acc_seg: 96.9272, aux.loss_ce: 0.0374, aux.acc_seg: 95.5902, loss: 0.0977 2022-05-06 05:38:45,330 - mmseg - INFO - Iter [32550/80000] lr: 8.516e-07, eta: 7:54:09, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0601, decode.acc_seg: 96.9601, aux.loss_ce: 0.0364, aux.acc_seg: 95.7214, loss: 0.0965 2022-05-06 05:39:12,180 - mmseg - INFO - Iter [32600/80000] lr: 8.507e-07, eta: 7:53:34, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0583, decode.acc_seg: 96.9753, aux.loss_ce: 0.0365, aux.acc_seg: 95.6984, loss: 0.0948 2022-05-06 05:39:38,752 - mmseg - INFO - Iter [32650/80000] lr: 8.498e-07, eta: 7:52:59, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0582, decode.acc_seg: 97.0080, aux.loss_ce: 0.0357, aux.acc_seg: 95.7627, loss: 0.0939 2022-05-06 05:40:05,398 - mmseg - INFO - Iter [32700/80000] lr: 8.489e-07, eta: 7:52:25, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0530, decode.acc_seg: 97.2130, aux.loss_ce: 0.0333, aux.acc_seg: 95.9932, loss: 0.0863 2022-05-06 05:40:32,124 - mmseg - INFO - Iter [32750/80000] lr: 8.480e-07, eta: 7:51:50, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0561, decode.acc_seg: 97.0532, aux.loss_ce: 0.0349, aux.acc_seg: 95.7853, loss: 0.0910 2022-05-06 05:41:01,533 - mmseg - INFO - Iter [32800/80000] lr: 8.471e-07, eta: 7:51:19, time: 0.588, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0554, decode.acc_seg: 97.1750, aux.loss_ce: 0.0352, aux.acc_seg: 95.8967, loss: 0.0907 2022-05-06 05:41:28,084 - mmseg - INFO - Iter [32850/80000] lr: 8.462e-07, eta: 7:50:44, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0569, decode.acc_seg: 96.9306, aux.loss_ce: 0.0358, aux.acc_seg: 95.6988, loss: 0.0927 2022-05-06 05:41:54,757 - mmseg - INFO - Iter [32900/80000] lr: 8.453e-07, eta: 7:50:10, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0601, decode.acc_seg: 96.9517, aux.loss_ce: 0.0377, aux.acc_seg: 95.6381, loss: 0.0978 2022-05-06 05:42:21,303 - mmseg - INFO - Iter [32950/80000] lr: 8.444e-07, eta: 7:49:35, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0607, decode.acc_seg: 96.9502, aux.loss_ce: 0.0374, aux.acc_seg: 95.7312, loss: 0.0982 2022-05-06 05:42:47,988 - mmseg - INFO - Saving checkpoint at 33000 iterations 2022-05-06 05:43:08,457 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:43:08,461 - mmseg - INFO - Iter [33000/80000] lr: 8.435e-07, eta: 7:49:29, time: 0.941, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0558, decode.acc_seg: 97.0544, aux.loss_ce: 0.0351, aux.acc_seg: 95.7419, loss: 0.0909 2022-05-06 05:43:35,663 - mmseg - INFO - Iter [33050/80000] lr: 8.427e-07, eta: 7:48:56, time: 0.546, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0519, decode.acc_seg: 97.3423, aux.loss_ce: 0.0329, aux.acc_seg: 96.1725, loss: 0.0848 2022-05-06 05:44:05,423 - mmseg - INFO - Iter [33100/80000] lr: 8.418e-07, eta: 7:48:25, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.2765, aux.loss_ce: 0.0326, aux.acc_seg: 96.0107, loss: 0.0833 2022-05-06 05:44:32,284 - mmseg - INFO - Iter [33150/80000] lr: 8.409e-07, eta: 7:47:51, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0599, decode.acc_seg: 96.9862, aux.loss_ce: 0.0372, aux.acc_seg: 95.7254, loss: 0.0970 2022-05-06 05:44:58,936 - mmseg - INFO - Iter [33200/80000] lr: 8.400e-07, eta: 7:47:16, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0587, decode.acc_seg: 96.8984, aux.loss_ce: 0.0349, aux.acc_seg: 95.8200, loss: 0.0937 2022-05-06 05:45:25,757 - mmseg - INFO - Iter [33250/80000] lr: 8.391e-07, eta: 7:46:42, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0627, decode.acc_seg: 96.8746, aux.loss_ce: 0.0377, aux.acc_seg: 95.5715, loss: 0.1004 2022-05-06 05:45:52,555 - mmseg - INFO - Iter [33300/80000] lr: 8.382e-07, eta: 7:46:08, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0542, decode.acc_seg: 97.1247, aux.loss_ce: 0.0341, aux.acc_seg: 95.9003, loss: 0.0883 2022-05-06 05:46:19,310 - mmseg - INFO - Iter [33350/80000] lr: 8.373e-07, eta: 7:45:33, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0572, decode.acc_seg: 97.0028, aux.loss_ce: 0.0351, aux.acc_seg: 95.8184, loss: 0.0923 2022-05-06 05:46:48,437 - mmseg - INFO - Iter [33400/80000] lr: 8.364e-07, eta: 7:45:02, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0510, decode.acc_seg: 97.2562, aux.loss_ce: 0.0329, aux.acc_seg: 95.9330, loss: 0.0839 2022-05-06 05:47:15,003 - mmseg - INFO - Iter [33450/80000] lr: 8.355e-07, eta: 7:44:28, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0529, decode.acc_seg: 97.2471, aux.loss_ce: 0.0339, aux.acc_seg: 95.9529, loss: 0.0868 2022-05-06 05:47:41,487 - mmseg - INFO - Iter [33500/80000] lr: 8.346e-07, eta: 7:43:53, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0573, decode.acc_seg: 97.0581, aux.loss_ce: 0.0357, aux.acc_seg: 95.8258, loss: 0.0930 2022-05-06 05:48:08,015 - mmseg - INFO - Iter [33550/80000] lr: 8.337e-07, eta: 7:43:18, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0600, decode.acc_seg: 96.9785, aux.loss_ce: 0.0368, aux.acc_seg: 95.6902, loss: 0.0968 2022-05-06 05:48:34,769 - mmseg - INFO - Iter [33600/80000] lr: 8.328e-07, eta: 7:42:44, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0506, decode.acc_seg: 97.2842, aux.loss_ce: 0.0319, aux.acc_seg: 96.1421, loss: 0.0826 2022-05-06 05:49:01,590 - mmseg - INFO - Iter [33650/80000] lr: 8.319e-07, eta: 7:42:10, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0526, decode.acc_seg: 97.2121, aux.loss_ce: 0.0332, aux.acc_seg: 96.0360, loss: 0.0858 2022-05-06 05:49:30,626 - mmseg - INFO - Iter [33700/80000] lr: 8.310e-07, eta: 7:41:39, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0572, decode.acc_seg: 96.9579, aux.loss_ce: 0.0361, aux.acc_seg: 95.6448, loss: 0.0934 2022-05-06 05:49:57,393 - mmseg - INFO - Iter [33750/80000] lr: 8.301e-07, eta: 7:41:04, time: 0.535, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0582, decode.acc_seg: 97.0392, aux.loss_ce: 0.0360, aux.acc_seg: 95.7377, loss: 0.0943 2022-05-06 05:50:24,007 - mmseg - INFO - Iter [33800/80000] lr: 8.292e-07, eta: 7:40:30, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0554, decode.acc_seg: 97.0038, aux.loss_ce: 0.0346, aux.acc_seg: 95.7280, loss: 0.0901 2022-05-06 05:50:50,846 - mmseg - INFO - Iter [33850/80000] lr: 8.283e-07, eta: 7:39:56, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0543, decode.acc_seg: 97.2370, aux.loss_ce: 0.0349, aux.acc_seg: 95.9956, loss: 0.0892 2022-05-06 05:51:17,818 - mmseg - INFO - Iter [33900/80000] lr: 8.274e-07, eta: 7:39:22, time: 0.541, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0512, decode.acc_seg: 97.2806, aux.loss_ce: 0.0340, aux.acc_seg: 95.9567, loss: 0.0852 2022-05-06 05:51:44,757 - mmseg - INFO - Iter [33950/80000] lr: 8.265e-07, eta: 7:38:48, time: 0.539, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0612, decode.acc_seg: 97.0333, aux.loss_ce: 0.0369, aux.acc_seg: 95.7674, loss: 0.0981 2022-05-06 05:52:11,391 - mmseg - INFO - Saving checkpoint at 34000 iterations 2022-05-06 05:52:31,964 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 05:52:31,972 - mmseg - INFO - Iter [34000/80000] lr: 8.256e-07, eta: 7:38:41, time: 0.942, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0539, decode.acc_seg: 97.2413, aux.loss_ce: 0.0340, aux.acc_seg: 96.0496, loss: 0.0879 2022-05-06 05:53:01,284 - mmseg - INFO - Iter [34050/80000] lr: 8.247e-07, eta: 7:38:11, time: 0.589, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0552, decode.acc_seg: 97.1053, aux.loss_ce: 0.0350, aux.acc_seg: 95.8516, loss: 0.0902 2022-05-06 05:53:27,972 - mmseg - INFO - Iter [34100/80000] lr: 8.238e-07, eta: 7:37:37, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0557, decode.acc_seg: 97.0402, aux.loss_ce: 0.0351, aux.acc_seg: 95.7084, loss: 0.0908 2022-05-06 05:53:54,967 - mmseg - INFO - Iter [34150/80000] lr: 8.229e-07, eta: 7:37:03, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0596, decode.acc_seg: 96.8775, aux.loss_ce: 0.0372, aux.acc_seg: 95.6484, loss: 0.0968 2022-05-06 05:54:22,069 - mmseg - INFO - Iter [34200/80000] lr: 8.220e-07, eta: 7:36:29, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0525, decode.acc_seg: 97.1174, aux.loss_ce: 0.0330, aux.acc_seg: 95.8580, loss: 0.0855 2022-05-06 05:54:49,194 - mmseg - INFO - Iter [34250/80000] lr: 8.211e-07, eta: 7:35:56, time: 0.543, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.1736, aux.loss_ce: 0.0339, aux.acc_seg: 95.9433, loss: 0.0873 2022-05-06 05:55:16,200 - mmseg - INFO - Iter [34300/80000] lr: 8.202e-07, eta: 7:35:22, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0541, decode.acc_seg: 97.0680, aux.loss_ce: 0.0341, aux.acc_seg: 95.7708, loss: 0.0882 2022-05-06 05:55:45,350 - mmseg - INFO - Iter [34350/80000] lr: 8.193e-07, eta: 7:34:51, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0532, decode.acc_seg: 97.2537, aux.loss_ce: 0.0336, aux.acc_seg: 96.0160, loss: 0.0869 2022-05-06 05:56:12,163 - mmseg - INFO - Iter [34400/80000] lr: 8.184e-07, eta: 7:34:17, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0550, decode.acc_seg: 97.1869, aux.loss_ce: 0.0350, aux.acc_seg: 95.9256, loss: 0.0900 2022-05-06 05:56:39,007 - mmseg - INFO - Iter [34450/80000] lr: 8.175e-07, eta: 7:33:43, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0526, decode.acc_seg: 97.2339, aux.loss_ce: 0.0337, aux.acc_seg: 95.9278, loss: 0.0863 2022-05-06 05:57:05,913 - mmseg - INFO - Iter [34500/80000] lr: 8.166e-07, eta: 7:33:09, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0525, decode.acc_seg: 97.1990, aux.loss_ce: 0.0331, aux.acc_seg: 96.0005, loss: 0.0856 2022-05-06 05:57:32,739 - mmseg - INFO - Iter [34550/80000] lr: 8.157e-07, eta: 7:32:35, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0563, decode.acc_seg: 97.0955, aux.loss_ce: 0.0355, aux.acc_seg: 95.7975, loss: 0.0918 2022-05-06 05:57:59,386 - mmseg - INFO - Iter [34600/80000] lr: 8.148e-07, eta: 7:32:01, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0599, decode.acc_seg: 97.1003, aux.loss_ce: 0.0355, aux.acc_seg: 95.8507, loss: 0.0955 2022-05-06 05:58:28,271 - mmseg - INFO - Iter [34650/80000] lr: 8.139e-07, eta: 7:31:30, time: 0.578, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0529, decode.acc_seg: 97.2162, aux.loss_ce: 0.0331, aux.acc_seg: 96.0070, loss: 0.0860 2022-05-06 05:58:55,293 - mmseg - INFO - Iter [34700/80000] lr: 8.130e-07, eta: 7:30:56, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0645, decode.acc_seg: 96.6822, aux.loss_ce: 0.0386, aux.acc_seg: 95.4949, loss: 0.1031 2022-05-06 05:59:22,193 - mmseg - INFO - Iter [34750/80000] lr: 8.121e-07, eta: 7:30:23, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0540, decode.acc_seg: 97.1236, aux.loss_ce: 0.0337, aux.acc_seg: 95.9042, loss: 0.0877 2022-05-06 05:59:48,857 - mmseg - INFO - Iter [34800/80000] lr: 8.112e-07, eta: 7:29:49, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0566, decode.acc_seg: 97.1712, aux.loss_ce: 0.0347, aux.acc_seg: 96.0229, loss: 0.0913 2022-05-06 06:00:17,422 - mmseg - INFO - Iter [34850/80000] lr: 8.103e-07, eta: 7:29:17, time: 0.570, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0531, decode.acc_seg: 97.1894, aux.loss_ce: 0.0334, aux.acc_seg: 95.8813, loss: 0.0865 2022-05-06 06:00:44,239 - mmseg - INFO - Iter [34900/80000] lr: 8.094e-07, eta: 7:28:43, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0562, decode.acc_seg: 97.0701, aux.loss_ce: 0.0352, aux.acc_seg: 95.8255, loss: 0.0914 2022-05-06 06:01:13,806 - mmseg - INFO - Iter [34950/80000] lr: 8.086e-07, eta: 7:28:13, time: 0.591, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0527, decode.acc_seg: 97.2806, aux.loss_ce: 0.0331, aux.acc_seg: 96.0619, loss: 0.0858 2022-05-06 06:01:40,471 - mmseg - INFO - Saving checkpoint at 35000 iterations 2022-05-06 06:02:00,881 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:02:00,891 - mmseg - INFO - Iter [35000/80000] lr: 8.077e-07, eta: 7:28:05, time: 0.939, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0554, decode.acc_seg: 97.1052, aux.loss_ce: 0.0336, aux.acc_seg: 95.9246, loss: 0.0890 2022-05-06 06:02:27,904 - mmseg - INFO - Iter [35050/80000] lr: 8.068e-07, eta: 7:27:32, time: 0.543, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0571, decode.acc_seg: 97.0725, aux.loss_ce: 0.0354, aux.acc_seg: 95.8110, loss: 0.0925 2022-05-06 06:02:54,771 - mmseg - INFO - Iter [35100/80000] lr: 8.059e-07, eta: 7:26:58, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.1636, aux.loss_ce: 0.0337, aux.acc_seg: 95.9099, loss: 0.0871 2022-05-06 06:03:21,549 - mmseg - INFO - Iter [35150/80000] lr: 8.050e-07, eta: 7:26:24, time: 0.536, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0572, decode.acc_seg: 97.0163, aux.loss_ce: 0.0358, aux.acc_seg: 95.6915, loss: 0.0930 2022-05-06 06:03:48,169 - mmseg - INFO - Iter [35200/80000] lr: 8.041e-07, eta: 7:25:50, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0586, decode.acc_seg: 96.9132, aux.loss_ce: 0.0364, aux.acc_seg: 95.6926, loss: 0.0950 2022-05-06 06:04:14,749 - mmseg - INFO - Iter [35250/80000] lr: 8.032e-07, eta: 7:25:16, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0512, decode.acc_seg: 97.3415, aux.loss_ce: 0.0322, aux.acc_seg: 96.1480, loss: 0.0834 2022-05-06 06:04:44,787 - mmseg - INFO - Iter [35300/80000] lr: 8.023e-07, eta: 7:24:47, time: 0.601, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0563, decode.acc_seg: 97.1534, aux.loss_ce: 0.0344, aux.acc_seg: 95.9885, loss: 0.0907 2022-05-06 06:05:11,253 - mmseg - INFO - Iter [35350/80000] lr: 8.014e-07, eta: 7:24:13, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.2123, aux.loss_ce: 0.0343, aux.acc_seg: 95.9660, loss: 0.0877 2022-05-06 06:05:37,784 - mmseg - INFO - Iter [35400/80000] lr: 8.005e-07, eta: 7:23:39, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0542, decode.acc_seg: 97.1856, aux.loss_ce: 0.0344, aux.acc_seg: 95.8711, loss: 0.0887 2022-05-06 06:06:04,912 - mmseg - INFO - Iter [35450/80000] lr: 7.996e-07, eta: 7:23:05, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0512, decode.acc_seg: 97.3102, aux.loss_ce: 0.0318, aux.acc_seg: 96.1546, loss: 0.0830 2022-05-06 06:06:31,883 - mmseg - INFO - Iter [35500/80000] lr: 7.987e-07, eta: 7:22:32, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0559, decode.acc_seg: 97.1385, aux.loss_ce: 0.0347, aux.acc_seg: 95.8772, loss: 0.0906 2022-05-06 06:06:58,630 - mmseg - INFO - Iter [35550/80000] lr: 7.978e-07, eta: 7:21:58, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0515, decode.acc_seg: 97.1991, aux.loss_ce: 0.0329, aux.acc_seg: 95.9108, loss: 0.0844 2022-05-06 06:07:27,960 - mmseg - INFO - Iter [35600/80000] lr: 7.969e-07, eta: 7:21:28, time: 0.587, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.1927, aux.loss_ce: 0.0342, aux.acc_seg: 95.8870, loss: 0.0876 2022-05-06 06:07:54,569 - mmseg - INFO - Iter [35650/80000] lr: 7.960e-07, eta: 7:20:54, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0544, decode.acc_seg: 97.1428, aux.loss_ce: 0.0342, aux.acc_seg: 95.9124, loss: 0.0886 2022-05-06 06:08:21,587 - mmseg - INFO - Iter [35700/80000] lr: 7.951e-07, eta: 7:20:21, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0522, decode.acc_seg: 97.1850, aux.loss_ce: 0.0327, aux.acc_seg: 95.9749, loss: 0.0849 2022-05-06 06:08:48,149 - mmseg - INFO - Iter [35750/80000] lr: 7.942e-07, eta: 7:19:47, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0536, decode.acc_seg: 97.2331, aux.loss_ce: 0.0337, aux.acc_seg: 95.9925, loss: 0.0874 2022-05-06 06:09:14,840 - mmseg - INFO - Iter [35800/80000] lr: 7.933e-07, eta: 7:19:13, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0520, decode.acc_seg: 97.2619, aux.loss_ce: 0.0326, aux.acc_seg: 96.0387, loss: 0.0846 2022-05-06 06:09:41,752 - mmseg - INFO - Iter [35850/80000] lr: 7.924e-07, eta: 7:18:40, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0567, decode.acc_seg: 97.1480, aux.loss_ce: 0.0357, aux.acc_seg: 95.9089, loss: 0.0924 2022-05-06 06:10:10,852 - mmseg - INFO - Iter [35900/80000] lr: 7.915e-07, eta: 7:18:09, time: 0.582, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0573, decode.acc_seg: 96.9619, aux.loss_ce: 0.0360, aux.acc_seg: 95.6438, loss: 0.0932 2022-05-06 06:10:37,592 - mmseg - INFO - Iter [35950/80000] lr: 7.906e-07, eta: 7:17:36, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0525, decode.acc_seg: 97.2983, aux.loss_ce: 0.0331, aux.acc_seg: 96.0639, loss: 0.0857 2022-05-06 06:11:04,291 - mmseg - INFO - Saving checkpoint at 36000 iterations 2022-05-06 06:11:24,957 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:11:24,967 - mmseg - INFO - Iter [36000/80000] lr: 7.897e-07, eta: 7:17:27, time: 0.945, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0515, decode.acc_seg: 97.3286, aux.loss_ce: 0.0324, aux.acc_seg: 96.1556, loss: 0.0840 2022-05-06 06:11:51,886 - mmseg - INFO - Iter [36050/80000] lr: 7.888e-07, eta: 7:16:54, time: 0.541, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.1354, aux.loss_ce: 0.0338, aux.acc_seg: 95.8606, loss: 0.0872 2022-05-06 06:12:18,647 - mmseg - INFO - Iter [36100/80000] lr: 7.879e-07, eta: 7:16:20, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0612, decode.acc_seg: 96.9899, aux.loss_ce: 0.0374, aux.acc_seg: 95.6939, loss: 0.0986 2022-05-06 06:12:45,435 - mmseg - INFO - Iter [36150/80000] lr: 7.870e-07, eta: 7:15:47, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0565, decode.acc_seg: 96.9935, aux.loss_ce: 0.0347, aux.acc_seg: 95.7785, loss: 0.0911 2022-05-06 06:13:14,595 - mmseg - INFO - Iter [36200/80000] lr: 7.861e-07, eta: 7:15:16, time: 0.583, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0527, decode.acc_seg: 97.2842, aux.loss_ce: 0.0330, aux.acc_seg: 96.1157, loss: 0.0857 2022-05-06 06:13:41,123 - mmseg - INFO - Iter [36250/80000] lr: 7.852e-07, eta: 7:14:42, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.3815, aux.loss_ce: 0.0319, aux.acc_seg: 96.2110, loss: 0.0826 2022-05-06 06:14:07,938 - mmseg - INFO - Iter [36300/80000] lr: 7.843e-07, eta: 7:14:09, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0519, decode.acc_seg: 97.2716, aux.loss_ce: 0.0327, aux.acc_seg: 96.0822, loss: 0.0846 2022-05-06 06:14:34,782 - mmseg - INFO - Iter [36350/80000] lr: 7.834e-07, eta: 7:13:36, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.4161, aux.loss_ce: 0.0318, aux.acc_seg: 96.2349, loss: 0.0825 2022-05-06 06:15:01,536 - mmseg - INFO - Iter [36400/80000] lr: 7.825e-07, eta: 7:13:02, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.2722, aux.loss_ce: 0.0337, aux.acc_seg: 96.0511, loss: 0.0871 2022-05-06 06:15:28,130 - mmseg - INFO - Iter [36450/80000] lr: 7.816e-07, eta: 7:12:29, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0520, decode.acc_seg: 97.2551, aux.loss_ce: 0.0331, aux.acc_seg: 96.0115, loss: 0.0851 2022-05-06 06:15:54,747 - mmseg - INFO - Iter [36500/80000] lr: 7.807e-07, eta: 7:11:55, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0548, decode.acc_seg: 97.1598, aux.loss_ce: 0.0353, aux.acc_seg: 95.7802, loss: 0.0901 2022-05-06 06:16:23,840 - mmseg - INFO - Iter [36550/80000] lr: 7.798e-07, eta: 7:11:24, time: 0.582, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0513, decode.acc_seg: 97.2149, aux.loss_ce: 0.0329, aux.acc_seg: 95.9493, loss: 0.0842 2022-05-06 06:16:50,413 - mmseg - INFO - Iter [36600/80000] lr: 7.789e-07, eta: 7:10:51, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0510, decode.acc_seg: 97.2921, aux.loss_ce: 0.0324, aux.acc_seg: 96.0508, loss: 0.0834 2022-05-06 06:17:17,074 - mmseg - INFO - Iter [36650/80000] lr: 7.780e-07, eta: 7:10:17, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0524, decode.acc_seg: 97.2241, aux.loss_ce: 0.0336, aux.acc_seg: 95.9231, loss: 0.0859 2022-05-06 06:17:43,861 - mmseg - INFO - Iter [36700/80000] lr: 7.771e-07, eta: 7:09:44, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0521, decode.acc_seg: 97.3132, aux.loss_ce: 0.0339, aux.acc_seg: 95.9561, loss: 0.0860 2022-05-06 06:18:10,611 - mmseg - INFO - Iter [36750/80000] lr: 7.762e-07, eta: 7:09:11, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0487, decode.acc_seg: 97.3824, aux.loss_ce: 0.0305, aux.acc_seg: 96.2496, loss: 0.0792 2022-05-06 06:18:37,266 - mmseg - INFO - Iter [36800/80000] lr: 7.753e-07, eta: 7:08:37, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0532, decode.acc_seg: 97.2043, aux.loss_ce: 0.0331, aux.acc_seg: 95.9808, loss: 0.0862 2022-05-06 06:19:06,536 - mmseg - INFO - Iter [36850/80000] lr: 7.745e-07, eta: 7:08:07, time: 0.586, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0538, decode.acc_seg: 97.1678, aux.loss_ce: 0.0333, aux.acc_seg: 95.9628, loss: 0.0871 2022-05-06 06:19:33,368 - mmseg - INFO - Iter [36900/80000] lr: 7.736e-07, eta: 7:07:34, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0639, decode.acc_seg: 96.8099, aux.loss_ce: 0.0372, aux.acc_seg: 95.6343, loss: 0.1011 2022-05-06 06:19:59,902 - mmseg - INFO - Iter [36950/80000] lr: 7.727e-07, eta: 7:07:00, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0548, decode.acc_seg: 97.1392, aux.loss_ce: 0.0340, aux.acc_seg: 95.9325, loss: 0.0888 2022-05-06 06:20:26,417 - mmseg - INFO - Saving checkpoint at 37000 iterations 2022-05-06 06:20:49,566 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:20:49,577 - mmseg - INFO - Iter [37000/80000] lr: 7.718e-07, eta: 7:06:53, time: 0.990, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0558, decode.acc_seg: 97.0602, aux.loss_ce: 0.0343, aux.acc_seg: 95.8985, loss: 0.0901 2022-05-06 06:21:16,755 - mmseg - INFO - Iter [37050/80000] lr: 7.709e-07, eta: 7:06:21, time: 0.546, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.2351, aux.loss_ce: 0.0338, aux.acc_seg: 95.9665, loss: 0.0872 2022-05-06 06:21:43,889 - mmseg - INFO - Iter [37100/80000] lr: 7.700e-07, eta: 7:05:48, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0543, decode.acc_seg: 97.1722, aux.loss_ce: 0.0339, aux.acc_seg: 95.9396, loss: 0.0882 2022-05-06 06:22:13,001 - mmseg - INFO - Iter [37150/80000] lr: 7.691e-07, eta: 7:05:17, time: 0.582, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0525, decode.acc_seg: 97.2678, aux.loss_ce: 0.0326, aux.acc_seg: 96.0649, loss: 0.0851 2022-05-06 06:22:39,494 - mmseg - INFO - Iter [37200/80000] lr: 7.682e-07, eta: 7:04:44, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0514, decode.acc_seg: 97.3375, aux.loss_ce: 0.0325, aux.acc_seg: 96.1532, loss: 0.0839 2022-05-06 06:23:06,098 - mmseg - INFO - Iter [37250/80000] lr: 7.673e-07, eta: 7:04:10, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0553, decode.acc_seg: 97.0718, aux.loss_ce: 0.0336, aux.acc_seg: 95.8923, loss: 0.0890 2022-05-06 06:23:32,837 - mmseg - INFO - Iter [37300/80000] lr: 7.664e-07, eta: 7:03:37, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0554, decode.acc_seg: 97.1381, aux.loss_ce: 0.0340, aux.acc_seg: 95.9396, loss: 0.0894 2022-05-06 06:23:59,386 - mmseg - INFO - Iter [37350/80000] lr: 7.655e-07, eta: 7:03:04, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0511, decode.acc_seg: 97.2379, aux.loss_ce: 0.0325, aux.acc_seg: 96.0300, loss: 0.0836 2022-05-06 06:24:26,152 - mmseg - INFO - Iter [37400/80000] lr: 7.646e-07, eta: 7:02:31, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0513, decode.acc_seg: 97.3368, aux.loss_ce: 0.0325, aux.acc_seg: 96.1862, loss: 0.0838 2022-05-06 06:24:55,150 - mmseg - INFO - Iter [37450/80000] lr: 7.637e-07, eta: 7:02:00, time: 0.580, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0555, decode.acc_seg: 97.1046, aux.loss_ce: 0.0342, aux.acc_seg: 95.8643, loss: 0.0897 2022-05-06 06:25:21,820 - mmseg - INFO - Iter [37500/80000] lr: 7.628e-07, eta: 7:01:27, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0521, decode.acc_seg: 97.2508, aux.loss_ce: 0.0333, aux.acc_seg: 96.0145, loss: 0.0854 2022-05-06 06:25:48,403 - mmseg - INFO - Iter [37550/80000] lr: 7.619e-07, eta: 7:00:53, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0491, decode.acc_seg: 97.4692, aux.loss_ce: 0.0310, aux.acc_seg: 96.3223, loss: 0.0801 2022-05-06 06:26:14,934 - mmseg - INFO - Iter [37600/80000] lr: 7.610e-07, eta: 7:00:20, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0522, decode.acc_seg: 97.2294, aux.loss_ce: 0.0319, aux.acc_seg: 96.0346, loss: 0.0840 2022-05-06 06:26:41,877 - mmseg - INFO - Iter [37650/80000] lr: 7.601e-07, eta: 6:59:47, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0531, decode.acc_seg: 97.2831, aux.loss_ce: 0.0339, aux.acc_seg: 96.0509, loss: 0.0870 2022-05-06 06:27:08,514 - mmseg - INFO - Iter [37700/80000] lr: 7.592e-07, eta: 6:59:14, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0576, decode.acc_seg: 97.0529, aux.loss_ce: 0.0363, aux.acc_seg: 95.8080, loss: 0.0939 2022-05-06 06:27:34,868 - mmseg - INFO - Iter [37750/80000] lr: 7.583e-07, eta: 6:58:40, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0584, decode.acc_seg: 97.0681, aux.loss_ce: 0.0348, aux.acc_seg: 95.7829, loss: 0.0931 2022-05-06 06:28:03,909 - mmseg - INFO - Iter [37800/80000] lr: 7.574e-07, eta: 6:58:10, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0590, decode.acc_seg: 97.0240, aux.loss_ce: 0.0357, aux.acc_seg: 95.8606, loss: 0.0947 2022-05-06 06:28:30,439 - mmseg - INFO - Iter [37850/80000] lr: 7.565e-07, eta: 6:57:37, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0509, decode.acc_seg: 97.3184, aux.loss_ce: 0.0320, aux.acc_seg: 96.1411, loss: 0.0830 2022-05-06 06:28:56,939 - mmseg - INFO - Iter [37900/80000] lr: 7.556e-07, eta: 6:57:03, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0525, decode.acc_seg: 97.2055, aux.loss_ce: 0.0326, aux.acc_seg: 95.9519, loss: 0.0851 2022-05-06 06:29:23,586 - mmseg - INFO - Iter [37950/80000] lr: 7.547e-07, eta: 6:56:30, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0522, decode.acc_seg: 97.3208, aux.loss_ce: 0.0325, aux.acc_seg: 96.1011, loss: 0.0847 2022-05-06 06:29:50,248 - mmseg - INFO - Saving checkpoint at 38000 iterations 2022-05-06 06:30:11,689 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:30:11,692 - mmseg - INFO - Iter [38000/80000] lr: 7.538e-07, eta: 6:56:21, time: 0.959, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0523, decode.acc_seg: 97.3064, aux.loss_ce: 0.0336, aux.acc_seg: 96.0703, loss: 0.0860 2022-05-06 06:30:38,993 - mmseg - INFO - Iter [38050/80000] lr: 7.529e-07, eta: 6:55:48, time: 0.549, data_time: 0.009, memory: 58091, decode.loss_ce: 0.0526, decode.acc_seg: 97.2218, aux.loss_ce: 0.0331, aux.acc_seg: 96.0200, loss: 0.0857 2022-05-06 06:31:08,258 - mmseg - INFO - Iter [38100/80000] lr: 7.520e-07, eta: 6:55:18, time: 0.585, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0512, decode.acc_seg: 97.3087, aux.loss_ce: 0.0324, aux.acc_seg: 96.0401, loss: 0.0836 2022-05-06 06:31:35,310 - mmseg - INFO - Iter [38150/80000] lr: 7.511e-07, eta: 6:54:45, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0517, decode.acc_seg: 97.2614, aux.loss_ce: 0.0331, aux.acc_seg: 95.9964, loss: 0.0849 2022-05-06 06:32:01,908 - mmseg - INFO - Iter [38200/80000] lr: 7.502e-07, eta: 6:54:12, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0547, decode.acc_seg: 97.0980, aux.loss_ce: 0.0348, aux.acc_seg: 95.7340, loss: 0.0895 2022-05-06 06:32:28,548 - mmseg - INFO - Iter [38250/80000] lr: 7.493e-07, eta: 6:53:39, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0518, decode.acc_seg: 97.2987, aux.loss_ce: 0.0323, aux.acc_seg: 96.1156, loss: 0.0841 2022-05-06 06:32:54,982 - mmseg - INFO - Iter [38300/80000] lr: 7.484e-07, eta: 6:53:06, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0516, decode.acc_seg: 97.3199, aux.loss_ce: 0.0331, aux.acc_seg: 96.0786, loss: 0.0847 2022-05-06 06:33:21,698 - mmseg - INFO - Iter [38350/80000] lr: 7.475e-07, eta: 6:52:33, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0565, decode.acc_seg: 97.2013, aux.loss_ce: 0.0354, aux.acc_seg: 95.9492, loss: 0.0920 2022-05-06 06:33:50,919 - mmseg - INFO - Iter [38400/80000] lr: 7.466e-07, eta: 6:52:03, time: 0.584, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0531, decode.acc_seg: 97.1926, aux.loss_ce: 0.0329, aux.acc_seg: 95.9931, loss: 0.0860 2022-05-06 06:34:17,953 - mmseg - INFO - Iter [38450/80000] lr: 7.457e-07, eta: 6:51:30, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0563, decode.acc_seg: 97.1506, aux.loss_ce: 0.0346, aux.acc_seg: 95.9413, loss: 0.0909 2022-05-06 06:34:44,497 - mmseg - INFO - Iter [38500/80000] lr: 7.448e-07, eta: 6:50:57, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0559, decode.acc_seg: 97.1907, aux.loss_ce: 0.0331, aux.acc_seg: 96.1278, loss: 0.0891 2022-05-06 06:35:11,203 - mmseg - INFO - Iter [38550/80000] lr: 7.439e-07, eta: 6:50:24, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0567, decode.acc_seg: 97.0704, aux.loss_ce: 0.0353, aux.acc_seg: 95.8324, loss: 0.0919 2022-05-06 06:35:37,787 - mmseg - INFO - Iter [38600/80000] lr: 7.430e-07, eta: 6:49:51, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0531, decode.acc_seg: 97.0642, aux.loss_ce: 0.0336, aux.acc_seg: 95.7643, loss: 0.0867 2022-05-06 06:36:04,636 - mmseg - INFO - Iter [38650/80000] lr: 7.421e-07, eta: 6:49:18, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0542, decode.acc_seg: 97.1580, aux.loss_ce: 0.0341, aux.acc_seg: 95.9358, loss: 0.0883 2022-05-06 06:36:33,753 - mmseg - INFO - Iter [38700/80000] lr: 7.412e-07, eta: 6:48:48, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0546, decode.acc_seg: 97.1709, aux.loss_ce: 0.0344, aux.acc_seg: 95.8873, loss: 0.0890 2022-05-06 06:37:00,475 - mmseg - INFO - Iter [38750/80000] lr: 7.404e-07, eta: 6:48:15, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0522, decode.acc_seg: 97.2087, aux.loss_ce: 0.0320, aux.acc_seg: 96.0595, loss: 0.0842 2022-05-06 06:37:27,105 - mmseg - INFO - Iter [38800/80000] lr: 7.395e-07, eta: 6:47:42, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0487, decode.acc_seg: 97.4237, aux.loss_ce: 0.0306, aux.acc_seg: 96.2716, loss: 0.0793 2022-05-06 06:37:53,769 - mmseg - INFO - Iter [38850/80000] lr: 7.386e-07, eta: 6:47:09, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0535, decode.acc_seg: 97.2507, aux.loss_ce: 0.0340, aux.acc_seg: 95.9592, loss: 0.0875 2022-05-06 06:38:20,223 - mmseg - INFO - Iter [38900/80000] lr: 7.377e-07, eta: 6:46:36, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0521, decode.acc_seg: 97.2295, aux.loss_ce: 0.0326, aux.acc_seg: 95.9494, loss: 0.0847 2022-05-06 06:38:47,044 - mmseg - INFO - Iter [38950/80000] lr: 7.368e-07, eta: 6:46:03, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0520, decode.acc_seg: 97.3170, aux.loss_ce: 0.0327, aux.acc_seg: 96.1281, loss: 0.0847 2022-05-06 06:39:13,453 - mmseg - INFO - Saving checkpoint at 39000 iterations 2022-05-06 06:39:33,988 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:39:33,996 - mmseg - INFO - Iter [39000/80000] lr: 7.359e-07, eta: 6:45:52, time: 0.935, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0500, decode.acc_seg: 97.3871, aux.loss_ce: 0.0322, aux.acc_seg: 96.1222, loss: 0.0822 2022-05-06 06:40:03,355 - mmseg - INFO - Iter [39050/80000] lr: 7.350e-07, eta: 6:45:22, time: 0.591, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0497, decode.acc_seg: 97.3431, aux.loss_ce: 0.0321, aux.acc_seg: 96.0683, loss: 0.0819 2022-05-06 06:40:29,923 - mmseg - INFO - Iter [39100/80000] lr: 7.341e-07, eta: 6:44:49, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0477, decode.acc_seg: 97.4531, aux.loss_ce: 0.0308, aux.acc_seg: 96.2554, loss: 0.0786 2022-05-06 06:40:57,135 - mmseg - INFO - Iter [39150/80000] lr: 7.332e-07, eta: 6:44:17, time: 0.544, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0573, decode.acc_seg: 97.1573, aux.loss_ce: 0.0337, aux.acc_seg: 95.9805, loss: 0.0910 2022-05-06 06:41:23,664 - mmseg - INFO - Iter [39200/80000] lr: 7.323e-07, eta: 6:43:44, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.3713, aux.loss_ce: 0.0308, aux.acc_seg: 96.2148, loss: 0.0800 2022-05-06 06:41:50,317 - mmseg - INFO - Iter [39250/80000] lr: 7.314e-07, eta: 6:43:11, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0495, decode.acc_seg: 97.4014, aux.loss_ce: 0.0318, aux.acc_seg: 96.1510, loss: 0.0813 2022-05-06 06:42:16,875 - mmseg - INFO - Iter [39300/80000] lr: 7.305e-07, eta: 6:42:38, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0565, decode.acc_seg: 97.1898, aux.loss_ce: 0.0342, aux.acc_seg: 95.9782, loss: 0.0906 2022-05-06 06:42:45,990 - mmseg - INFO - Iter [39350/80000] lr: 7.296e-07, eta: 6:42:08, time: 0.583, data_time: 0.050, memory: 58091, decode.loss_ce: 0.0569, decode.acc_seg: 97.1285, aux.loss_ce: 0.0349, aux.acc_seg: 95.8354, loss: 0.0917 2022-05-06 06:43:12,659 - mmseg - INFO - Iter [39400/80000] lr: 7.287e-07, eta: 6:41:35, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0491, decode.acc_seg: 97.4003, aux.loss_ce: 0.0316, aux.acc_seg: 96.1459, loss: 0.0807 2022-05-06 06:43:39,727 - mmseg - INFO - Iter [39450/80000] lr: 7.278e-07, eta: 6:41:02, time: 0.541, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0505, decode.acc_seg: 97.2946, aux.loss_ce: 0.0316, aux.acc_seg: 96.1128, loss: 0.0820 2022-05-06 06:44:06,464 - mmseg - INFO - Iter [39500/80000] lr: 7.269e-07, eta: 6:40:30, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0529, decode.acc_seg: 97.2378, aux.loss_ce: 0.0326, aux.acc_seg: 96.0525, loss: 0.0855 2022-05-06 06:44:33,338 - mmseg - INFO - Iter [39550/80000] lr: 7.260e-07, eta: 6:39:57, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0524, decode.acc_seg: 97.3059, aux.loss_ce: 0.0329, aux.acc_seg: 96.1158, loss: 0.0853 2022-05-06 06:45:00,078 - mmseg - INFO - Iter [39600/80000] lr: 7.251e-07, eta: 6:39:25, time: 0.535, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0480, decode.acc_seg: 97.4159, aux.loss_ce: 0.0305, aux.acc_seg: 96.2786, loss: 0.0785 2022-05-06 06:45:29,304 - mmseg - INFO - Iter [39650/80000] lr: 7.242e-07, eta: 6:38:54, time: 0.585, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0513, decode.acc_seg: 97.3914, aux.loss_ce: 0.0330, aux.acc_seg: 96.1677, loss: 0.0843 2022-05-06 06:45:55,740 - mmseg - INFO - Iter [39700/80000] lr: 7.233e-07, eta: 6:38:22, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0473, decode.acc_seg: 97.4542, aux.loss_ce: 0.0306, aux.acc_seg: 96.2094, loss: 0.0780 2022-05-06 06:46:22,459 - mmseg - INFO - Iter [39750/80000] lr: 7.224e-07, eta: 6:37:49, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0489, decode.acc_seg: 97.3980, aux.loss_ce: 0.0310, aux.acc_seg: 96.2034, loss: 0.0799 2022-05-06 06:46:49,520 - mmseg - INFO - Iter [39800/80000] lr: 7.215e-07, eta: 6:37:17, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0516, decode.acc_seg: 97.4121, aux.loss_ce: 0.0320, aux.acc_seg: 96.3056, loss: 0.0836 2022-05-06 06:47:16,034 - mmseg - INFO - Iter [39850/80000] lr: 7.206e-07, eta: 6:36:44, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0544, decode.acc_seg: 97.1967, aux.loss_ce: 0.0347, aux.acc_seg: 95.9494, loss: 0.0891 2022-05-06 06:47:42,840 - mmseg - INFO - Iter [39900/80000] lr: 7.197e-07, eta: 6:36:11, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0486, decode.acc_seg: 97.4649, aux.loss_ce: 0.0315, aux.acc_seg: 96.2110, loss: 0.0800 2022-05-06 06:48:12,114 - mmseg - INFO - Iter [39950/80000] lr: 7.188e-07, eta: 6:35:41, time: 0.586, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0542, decode.acc_seg: 97.1747, aux.loss_ce: 0.0338, aux.acc_seg: 95.9359, loss: 0.0880 2022-05-06 06:48:39,289 - mmseg - INFO - Saving checkpoint at 40000 iterations 2022-05-06 06:48:59,753 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:48:59,763 - mmseg - INFO - Iter [40000/80000] lr: 7.179e-07, eta: 6:35:30, time: 0.950, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0537, decode.acc_seg: 97.2369, aux.loss_ce: 0.0335, aux.acc_seg: 95.9389, loss: 0.0872 2022-05-06 06:53:08,726 - mmseg - INFO - per class results: 2022-05-06 06:53:08,732 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 93.06 | 97.04 | | bag | 46.25 | 60.73 | | bed | 33.54 | 49.45 | | bedclothes | 45.13 | 65.54 | | bench | 29.43 | 36.76 | | bicycle | 83.52 | 93.62 | | bird | 93.87 | 98.08 | | boat | 85.57 | 92.64 | | book | 61.78 | 75.18 | | bottle | 89.25 | 96.63 | | building | 67.96 | 78.79 | | bus | 94.46 | 97.61 | | cabinet | 50.89 | 66.05 | | car | 93.84 | 96.97 | | cat | 93.93 | 98.31 | | ceiling | 59.61 | 79.46 | | chair | 65.81 | 80.79 | | cloth | 27.0 | 35.06 | | computer | 62.18 | 69.67 | | cow | 95.44 | 98.5 | | cup | 47.45 | 68.77 | | curtain | 59.11 | 73.03 | | dog | 92.14 | 97.69 | | door | 37.48 | 51.02 | | fence | 45.68 | 59.21 | | floor | 75.94 | 90.14 | | flower | 33.87 | 43.99 | | food | 42.04 | 50.99 | | grass | 83.05 | 92.41 | | ground | 58.47 | 73.17 | | horse | 94.41 | 97.98 | | keyboard | 89.15 | 95.36 | | light | 59.13 | 75.23 | | motorbike | 90.57 | 97.06 | | mountain | 57.87 | 71.85 | | mouse | 82.55 | 92.57 | | person | 90.61 | 96.98 | | plate | 30.55 | 41.06 | | platform | 58.65 | 70.27 | | pottedplant | 80.6 | 91.4 | | road | 53.71 | 67.97 | | rock | 45.66 | 50.43 | | sheep | 94.79 | 98.46 | | shelves | 35.06 | 43.39 | | sidewalk | 31.91 | 48.7 | | sign | 52.47 | 60.61 | | sky | 95.05 | 97.41 | | snow | 76.29 | 91.72 | | sofa | 60.77 | 68.88 | | table | 72.98 | 83.77 | | track | 73.02 | 84.03 | | train | 93.06 | 97.37 | | tree | 81.0 | 91.25 | | truck | 51.51 | 58.02 | | tvmonitor | 90.08 | 94.77 | | wall | 73.99 | 87.14 | | water | 92.18 | 96.13 | | window | 46.72 | 60.71 | | wood | 23.84 | 30.48 | +-------------+-------+-------+ 2022-05-06 06:53:08,732 - mmseg - INFO - Summary: 2022-05-06 06:53:08,733 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.58 | 66.54 | 76.41 | +-------+-------+-------+ 2022-05-06 06:53:08,745 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 06:53:08,746 - mmseg - INFO - Iter(val) [638] aAcc: 0.8658, mIoU: 0.6654, mAcc: 0.7641, IoU.aeroplane: 0.9306, IoU.bag: 0.4625, IoU.bed: 0.3354, IoU.bedclothes: 0.4513, IoU.bench: 0.2943, IoU.bicycle: 0.8352, IoU.bird: 0.9387, IoU.boat: 0.8557, IoU.book: 0.6178, IoU.bottle: 0.8925, IoU.building: 0.6796, IoU.bus: 0.9446, IoU.cabinet: 0.5089, IoU.car: 0.9384, IoU.cat: 0.9393, IoU.ceiling: 0.5961, IoU.chair: 0.6581, IoU.cloth: 0.2700, IoU.computer: 0.6218, IoU.cow: 0.9544, IoU.cup: 0.4745, IoU.curtain: 0.5911, IoU.dog: 0.9214, IoU.door: 0.3748, IoU.fence: 0.4568, IoU.floor: 0.7594, IoU.flower: 0.3387, IoU.food: 0.4204, IoU.grass: 0.8305, IoU.ground: 0.5847, IoU.horse: 0.9441, IoU.keyboard: 0.8915, IoU.light: 0.5913, IoU.motorbike: 0.9057, IoU.mountain: 0.5787, IoU.mouse: 0.8255, IoU.person: 0.9061, IoU.plate: 0.3055, IoU.platform: 0.5865, IoU.pottedplant: 0.8060, IoU.road: 0.5371, IoU.rock: 0.4566, IoU.sheep: 0.9479, IoU.shelves: 0.3506, IoU.sidewalk: 0.3191, IoU.sign: 0.5247, IoU.sky: 0.9505, IoU.snow: 0.7629, IoU.sofa: 0.6077, IoU.table: 0.7298, IoU.track: 0.7302, IoU.train: 0.9306, IoU.tree: 0.8100, IoU.truck: 0.5151, IoU.tvmonitor: 0.9008, IoU.wall: 0.7399, IoU.water: 0.9218, IoU.window: 0.4672, IoU.wood: 0.2384, Acc.aeroplane: 0.9704, Acc.bag: 0.6073, Acc.bed: 0.4945, Acc.bedclothes: 0.6554, Acc.bench: 0.3676, Acc.bicycle: 0.9362, Acc.bird: 0.9808, Acc.boat: 0.9264, Acc.book: 0.7518, Acc.bottle: 0.9663, Acc.building: 0.7879, Acc.bus: 0.9761, Acc.cabinet: 0.6605, Acc.car: 0.9697, Acc.cat: 0.9831, Acc.ceiling: 0.7946, Acc.chair: 0.8079, Acc.cloth: 0.3506, Acc.computer: 0.6967, Acc.cow: 0.9850, Acc.cup: 0.6877, Acc.curtain: 0.7303, Acc.dog: 0.9769, Acc.door: 0.5102, Acc.fence: 0.5921, Acc.floor: 0.9014, Acc.flower: 0.4399, Acc.food: 0.5099, Acc.grass: 0.9241, Acc.ground: 0.7317, Acc.horse: 0.9798, Acc.keyboard: 0.9536, Acc.light: 0.7523, Acc.motorbike: 0.9706, Acc.mountain: 0.7185, Acc.mouse: 0.9257, Acc.person: 0.9698, Acc.plate: 0.4106, Acc.platform: 0.7027, Acc.pottedplant: 0.9140, Acc.road: 0.6797, Acc.rock: 0.5043, Acc.sheep: 0.9846, Acc.shelves: 0.4339, Acc.sidewalk: 0.4870, Acc.sign: 0.6061, Acc.sky: 0.9741, Acc.snow: 0.9172, Acc.sofa: 0.6888, Acc.table: 0.8377, Acc.track: 0.8403, Acc.train: 0.9737, Acc.tree: 0.9125, Acc.truck: 0.5802, Acc.tvmonitor: 0.9477, Acc.wall: 0.8714, Acc.water: 0.9613, Acc.window: 0.6071, Acc.wood: 0.3048 2022-05-06 06:53:35,300 - mmseg - INFO - Iter [40050/80000] lr: 7.170e-07, eta: 6:39:05, time: 5.514, data_time: 4.986, memory: 58091, decode.loss_ce: 0.0542, decode.acc_seg: 97.2503, aux.loss_ce: 0.0326, aux.acc_seg: 96.0500, loss: 0.0868 2022-05-06 06:54:01,902 - mmseg - INFO - Iter [40100/80000] lr: 7.161e-07, eta: 6:38:32, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0489, decode.acc_seg: 97.4397, aux.loss_ce: 0.0306, aux.acc_seg: 96.2903, loss: 0.0795 2022-05-06 06:54:28,542 - mmseg - INFO - Iter [40150/80000] lr: 7.152e-07, eta: 6:37:59, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0532, decode.acc_seg: 97.1852, aux.loss_ce: 0.0334, aux.acc_seg: 95.9614, loss: 0.0865 2022-05-06 06:54:55,225 - mmseg - INFO - Iter [40200/80000] lr: 7.143e-07, eta: 6:37:25, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0565, decode.acc_seg: 97.1834, aux.loss_ce: 0.0336, aux.acc_seg: 96.0532, loss: 0.0901 2022-05-06 06:55:24,349 - mmseg - INFO - Iter [40250/80000] lr: 7.134e-07, eta: 6:36:55, time: 0.583, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0502, decode.acc_seg: 97.3510, aux.loss_ce: 0.0308, aux.acc_seg: 96.2570, loss: 0.0811 2022-05-06 06:55:51,334 - mmseg - INFO - Iter [40300/80000] lr: 7.125e-07, eta: 6:36:22, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0488, decode.acc_seg: 97.4735, aux.loss_ce: 0.0311, aux.acc_seg: 96.3149, loss: 0.0799 2022-05-06 06:56:18,239 - mmseg - INFO - Iter [40350/80000] lr: 7.116e-07, eta: 6:35:49, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0524, decode.acc_seg: 97.3378, aux.loss_ce: 0.0333, aux.acc_seg: 96.1000, loss: 0.0856 2022-05-06 06:56:45,252 - mmseg - INFO - Iter [40400/80000] lr: 7.107e-07, eta: 6:35:16, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0501, decode.acc_seg: 97.3867, aux.loss_ce: 0.0315, aux.acc_seg: 96.2468, loss: 0.0816 2022-05-06 06:57:11,773 - mmseg - INFO - Iter [40450/80000] lr: 7.098e-07, eta: 6:34:43, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0515, decode.acc_seg: 97.3294, aux.loss_ce: 0.0322, aux.acc_seg: 96.1712, loss: 0.0836 2022-05-06 06:57:38,715 - mmseg - INFO - Iter [40500/80000] lr: 7.089e-07, eta: 6:34:10, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0494, decode.acc_seg: 97.3474, aux.loss_ce: 0.0315, aux.acc_seg: 96.1091, loss: 0.0810 2022-05-06 06:58:05,098 - mmseg - INFO - Iter [40550/80000] lr: 7.080e-07, eta: 6:33:36, time: 0.530, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0496, decode.acc_seg: 97.3976, aux.loss_ce: 0.0312, aux.acc_seg: 96.2316, loss: 0.0808 2022-05-06 06:58:34,169 - mmseg - INFO - Iter [40600/80000] lr: 7.071e-07, eta: 6:33:06, time: 0.581, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0528, decode.acc_seg: 97.3044, aux.loss_ce: 0.0336, aux.acc_seg: 96.1207, loss: 0.0864 2022-05-06 06:59:00,623 - mmseg - INFO - Iter [40650/80000] lr: 7.063e-07, eta: 6:32:32, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0504, decode.acc_seg: 97.3570, aux.loss_ce: 0.0322, aux.acc_seg: 96.1547, loss: 0.0827 2022-05-06 06:59:27,322 - mmseg - INFO - Iter [40700/80000] lr: 7.054e-07, eta: 6:31:59, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0462, decode.acc_seg: 97.5372, aux.loss_ce: 0.0292, aux.acc_seg: 96.4422, loss: 0.0755 2022-05-06 06:59:53,841 - mmseg - INFO - Iter [40750/80000] lr: 7.045e-07, eta: 6:31:26, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0502, decode.acc_seg: 97.3672, aux.loss_ce: 0.0324, aux.acc_seg: 96.0821, loss: 0.0826 2022-05-06 07:00:20,227 - mmseg - INFO - Iter [40800/80000] lr: 7.036e-07, eta: 6:30:53, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0500, decode.acc_seg: 97.3581, aux.loss_ce: 0.0322, aux.acc_seg: 96.0720, loss: 0.0822 2022-05-06 07:00:47,013 - mmseg - INFO - Iter [40850/80000] lr: 7.027e-07, eta: 6:30:20, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0483, decode.acc_seg: 97.4351, aux.loss_ce: 0.0311, aux.acc_seg: 96.2661, loss: 0.0793 2022-05-06 07:01:16,085 - mmseg - INFO - Iter [40900/80000] lr: 7.018e-07, eta: 6:29:49, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0516, decode.acc_seg: 97.2530, aux.loss_ce: 0.0326, aux.acc_seg: 96.0694, loss: 0.0842 2022-05-06 07:01:42,619 - mmseg - INFO - Iter [40950/80000] lr: 7.009e-07, eta: 6:29:16, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0481, decode.acc_seg: 97.3722, aux.loss_ce: 0.0308, aux.acc_seg: 96.0918, loss: 0.0789 2022-05-06 07:02:09,476 - mmseg - INFO - Saving checkpoint at 41000 iterations 2022-05-06 07:02:29,250 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:02:29,257 - mmseg - INFO - Iter [41000/80000] lr: 7.000e-07, eta: 6:29:02, time: 0.931, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0516, decode.acc_seg: 97.4180, aux.loss_ce: 0.0322, aux.acc_seg: 96.2242, loss: 0.0838 2022-05-06 07:02:56,471 - mmseg - INFO - Iter [41050/80000] lr: 6.991e-07, eta: 6:28:30, time: 0.544, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0484, decode.acc_seg: 97.3354, aux.loss_ce: 0.0305, aux.acc_seg: 96.1019, loss: 0.0789 2022-05-06 07:03:23,039 - mmseg - INFO - Iter [41100/80000] lr: 6.982e-07, eta: 6:27:57, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0493, decode.acc_seg: 97.3708, aux.loss_ce: 0.0322, aux.acc_seg: 96.0981, loss: 0.0815 2022-05-06 07:03:49,768 - mmseg - INFO - Iter [41150/80000] lr: 6.973e-07, eta: 6:27:24, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0529, decode.acc_seg: 97.2532, aux.loss_ce: 0.0323, aux.acc_seg: 96.1408, loss: 0.0853 2022-05-06 07:04:18,821 - mmseg - INFO - Iter [41200/80000] lr: 6.964e-07, eta: 6:26:53, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0502, decode.acc_seg: 97.3739, aux.loss_ce: 0.0315, aux.acc_seg: 96.2896, loss: 0.0817 2022-05-06 07:04:45,840 - mmseg - INFO - Iter [41250/80000] lr: 6.955e-07, eta: 6:26:20, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0533, decode.acc_seg: 97.1803, aux.loss_ce: 0.0333, aux.acc_seg: 96.0007, loss: 0.0866 2022-05-06 07:05:12,483 - mmseg - INFO - Iter [41300/80000] lr: 6.946e-07, eta: 6:25:47, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0551, decode.acc_seg: 97.1272, aux.loss_ce: 0.0327, aux.acc_seg: 95.9780, loss: 0.0878 2022-05-06 07:05:39,646 - mmseg - INFO - Iter [41350/80000] lr: 6.937e-07, eta: 6:25:15, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.2862, aux.loss_ce: 0.0324, aux.acc_seg: 95.9671, loss: 0.0831 2022-05-06 07:06:06,204 - mmseg - INFO - Iter [41400/80000] lr: 6.928e-07, eta: 6:24:42, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0479, decode.acc_seg: 97.4730, aux.loss_ce: 0.0304, aux.acc_seg: 96.2946, loss: 0.0783 2022-05-06 07:06:32,888 - mmseg - INFO - Iter [41450/80000] lr: 6.919e-07, eta: 6:24:09, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0513, decode.acc_seg: 97.4036, aux.loss_ce: 0.0318, aux.acc_seg: 96.2339, loss: 0.0831 2022-05-06 07:07:02,227 - mmseg - INFO - Iter [41500/80000] lr: 6.910e-07, eta: 6:23:38, time: 0.585, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0503, decode.acc_seg: 97.2348, aux.loss_ce: 0.0317, aux.acc_seg: 95.9994, loss: 0.0821 2022-05-06 07:07:28,850 - mmseg - INFO - Iter [41550/80000] lr: 6.901e-07, eta: 6:23:06, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0547, decode.acc_seg: 97.1774, aux.loss_ce: 0.0330, aux.acc_seg: 96.0437, loss: 0.0877 2022-05-06 07:07:55,341 - mmseg - INFO - Iter [41600/80000] lr: 6.892e-07, eta: 6:22:32, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0517, decode.acc_seg: 97.3514, aux.loss_ce: 0.0329, aux.acc_seg: 96.0989, loss: 0.0846 2022-05-06 07:08:22,117 - mmseg - INFO - Iter [41650/80000] lr: 6.883e-07, eta: 6:22:00, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0479, decode.acc_seg: 97.4034, aux.loss_ce: 0.0304, aux.acc_seg: 96.2431, loss: 0.0783 2022-05-06 07:08:48,833 - mmseg - INFO - Iter [41700/80000] lr: 6.874e-07, eta: 6:21:27, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0508, decode.acc_seg: 97.2709, aux.loss_ce: 0.0325, aux.acc_seg: 96.0378, loss: 0.0833 2022-05-06 07:09:15,987 - mmseg - INFO - Iter [41750/80000] lr: 6.865e-07, eta: 6:20:55, time: 0.543, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0467, decode.acc_seg: 97.5397, aux.loss_ce: 0.0296, aux.acc_seg: 96.4204, loss: 0.0762 2022-05-06 07:09:42,643 - mmseg - INFO - Iter [41800/80000] lr: 6.856e-07, eta: 6:20:22, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0487, decode.acc_seg: 97.4243, aux.loss_ce: 0.0305, aux.acc_seg: 96.2593, loss: 0.0792 2022-05-06 07:10:11,744 - mmseg - INFO - Iter [41850/80000] lr: 6.847e-07, eta: 6:19:51, time: 0.582, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0482, decode.acc_seg: 97.5423, aux.loss_ce: 0.0304, aux.acc_seg: 96.4439, loss: 0.0786 2022-05-06 07:10:38,574 - mmseg - INFO - Iter [41900/80000] lr: 6.838e-07, eta: 6:19:19, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.4301, aux.loss_ce: 0.0313, aux.acc_seg: 96.2292, loss: 0.0805 2022-05-06 07:11:05,164 - mmseg - INFO - Iter [41950/80000] lr: 6.829e-07, eta: 6:18:46, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0495, decode.acc_seg: 97.3863, aux.loss_ce: 0.0314, aux.acc_seg: 96.1795, loss: 0.0809 2022-05-06 07:11:31,876 - mmseg - INFO - Saving checkpoint at 42000 iterations 2022-05-06 07:11:53,007 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:11:53,010 - mmseg - INFO - Iter [42000/80000] lr: 6.820e-07, eta: 6:18:32, time: 0.955, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0496, decode.acc_seg: 97.3568, aux.loss_ce: 0.0313, aux.acc_seg: 96.1321, loss: 0.0808 2022-05-06 07:12:20,022 - mmseg - INFO - Iter [42050/80000] lr: 6.811e-07, eta: 6:18:00, time: 0.541, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0480, decode.acc_seg: 97.5171, aux.loss_ce: 0.0299, aux.acc_seg: 96.4243, loss: 0.0779 2022-05-06 07:12:46,826 - mmseg - INFO - Iter [42100/80000] lr: 6.802e-07, eta: 6:17:27, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0536, decode.acc_seg: 97.2994, aux.loss_ce: 0.0329, aux.acc_seg: 96.1534, loss: 0.0865 2022-05-06 07:13:16,126 - mmseg - INFO - Iter [42150/80000] lr: 6.793e-07, eta: 6:16:57, time: 0.586, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0508, decode.acc_seg: 97.3805, aux.loss_ce: 0.0321, aux.acc_seg: 96.2037, loss: 0.0829 2022-05-06 07:13:42,648 - mmseg - INFO - Iter [42200/80000] lr: 6.784e-07, eta: 6:16:24, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0508, decode.acc_seg: 97.3267, aux.loss_ce: 0.0327, aux.acc_seg: 96.0465, loss: 0.0836 2022-05-06 07:14:09,426 - mmseg - INFO - Iter [42250/80000] lr: 6.775e-07, eta: 6:15:51, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0483, decode.acc_seg: 97.4012, aux.loss_ce: 0.0311, aux.acc_seg: 96.1841, loss: 0.0794 2022-05-06 07:14:36,489 - mmseg - INFO - Iter [42300/80000] lr: 6.766e-07, eta: 6:15:19, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0482, decode.acc_seg: 97.4135, aux.loss_ce: 0.0305, aux.acc_seg: 96.2308, loss: 0.0786 2022-05-06 07:15:03,206 - mmseg - INFO - Iter [42350/80000] lr: 6.757e-07, eta: 6:14:46, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0469, decode.acc_seg: 97.4847, aux.loss_ce: 0.0301, aux.acc_seg: 96.2974, loss: 0.0770 2022-05-06 07:15:29,737 - mmseg - INFO - Iter [42400/80000] lr: 6.748e-07, eta: 6:14:13, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0479, decode.acc_seg: 97.4250, aux.loss_ce: 0.0309, aux.acc_seg: 96.1750, loss: 0.0788 2022-05-06 07:15:59,068 - mmseg - INFO - Iter [42450/80000] lr: 6.739e-07, eta: 6:13:43, time: 0.587, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0503, decode.acc_seg: 97.3831, aux.loss_ce: 0.0319, aux.acc_seg: 96.1580, loss: 0.0823 2022-05-06 07:16:25,764 - mmseg - INFO - Iter [42500/80000] lr: 6.730e-07, eta: 6:13:10, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0524, decode.acc_seg: 97.2534, aux.loss_ce: 0.0324, aux.acc_seg: 96.1245, loss: 0.0848 2022-05-06 07:16:52,308 - mmseg - INFO - Iter [42550/80000] lr: 6.721e-07, eta: 6:12:37, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0479, decode.acc_seg: 97.4936, aux.loss_ce: 0.0299, aux.acc_seg: 96.4265, loss: 0.0778 2022-05-06 07:17:18,969 - mmseg - INFO - Iter [42600/80000] lr: 6.713e-07, eta: 6:12:05, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0502, decode.acc_seg: 97.4003, aux.loss_ce: 0.0320, aux.acc_seg: 96.2054, loss: 0.0822 2022-05-06 07:17:45,657 - mmseg - INFO - Iter [42650/80000] lr: 6.704e-07, eta: 6:11:32, time: 0.536, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0519, decode.acc_seg: 97.2653, aux.loss_ce: 0.0328, aux.acc_seg: 96.0225, loss: 0.0847 2022-05-06 07:18:12,601 - mmseg - INFO - Iter [42700/80000] lr: 6.695e-07, eta: 6:11:00, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0495, decode.acc_seg: 97.3910, aux.loss_ce: 0.0316, aux.acc_seg: 96.1850, loss: 0.0811 2022-05-06 07:18:41,715 - mmseg - INFO - Iter [42750/80000] lr: 6.686e-07, eta: 6:10:29, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0469, decode.acc_seg: 97.4605, aux.loss_ce: 0.0306, aux.acc_seg: 96.2458, loss: 0.0774 2022-05-06 07:19:08,436 - mmseg - INFO - Iter [42800/80000] lr: 6.677e-07, eta: 6:09:57, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0566, decode.acc_seg: 96.8887, aux.loss_ce: 0.0340, aux.acc_seg: 95.7273, loss: 0.0906 2022-05-06 07:19:35,097 - mmseg - INFO - Iter [42850/80000] lr: 6.668e-07, eta: 6:09:24, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0534, decode.acc_seg: 97.1893, aux.loss_ce: 0.0323, aux.acc_seg: 96.0438, loss: 0.0857 2022-05-06 07:20:01,889 - mmseg - INFO - Iter [42900/80000] lr: 6.659e-07, eta: 6:08:52, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0508, decode.acc_seg: 97.3303, aux.loss_ce: 0.0320, aux.acc_seg: 96.0683, loss: 0.0828 2022-05-06 07:20:28,863 - mmseg - INFO - Iter [42950/80000] lr: 6.650e-07, eta: 6:08:19, time: 0.541, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.3617, aux.loss_ce: 0.0318, aux.acc_seg: 96.0161, loss: 0.0810 2022-05-06 07:20:55,329 - mmseg - INFO - Saving checkpoint at 43000 iterations 2022-05-06 07:21:16,951 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:21:16,958 - mmseg - INFO - Iter [43000/80000] lr: 6.641e-07, eta: 6:08:05, time: 0.960, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0476, decode.acc_seg: 97.4811, aux.loss_ce: 0.0304, aux.acc_seg: 96.2898, loss: 0.0781 2022-05-06 07:21:44,211 - mmseg - INFO - Iter [43050/80000] lr: 6.632e-07, eta: 6:07:33, time: 0.545, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.3753, aux.loss_ce: 0.0313, aux.acc_seg: 96.1680, loss: 0.0805 2022-05-06 07:22:13,741 - mmseg - INFO - Iter [43100/80000] lr: 6.623e-07, eta: 6:07:03, time: 0.593, data_time: 0.058, memory: 58091, decode.loss_ce: 0.0498, decode.acc_seg: 97.3156, aux.loss_ce: 0.0320, aux.acc_seg: 96.1146, loss: 0.0818 2022-05-06 07:22:40,221 - mmseg - INFO - Iter [43150/80000] lr: 6.614e-07, eta: 6:06:30, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.2905, aux.loss_ce: 0.0321, aux.acc_seg: 96.0580, loss: 0.0828 2022-05-06 07:23:06,806 - mmseg - INFO - Iter [43200/80000] lr: 6.605e-07, eta: 6:05:58, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0481, decode.acc_seg: 97.4738, aux.loss_ce: 0.0313, aux.acc_seg: 96.1958, loss: 0.0794 2022-05-06 07:23:33,638 - mmseg - INFO - Iter [43250/80000] lr: 6.596e-07, eta: 6:05:25, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0456, decode.acc_seg: 97.5821, aux.loss_ce: 0.0288, aux.acc_seg: 96.4694, loss: 0.0744 2022-05-06 07:24:00,152 - mmseg - INFO - Iter [43300/80000] lr: 6.587e-07, eta: 6:04:53, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0463, decode.acc_seg: 97.5242, aux.loss_ce: 0.0294, aux.acc_seg: 96.3361, loss: 0.0757 2022-05-06 07:24:26,987 - mmseg - INFO - Iter [43350/80000] lr: 6.578e-07, eta: 6:04:20, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0496, decode.acc_seg: 97.3361, aux.loss_ce: 0.0320, aux.acc_seg: 96.0646, loss: 0.0816 2022-05-06 07:24:56,567 - mmseg - INFO - Iter [43400/80000] lr: 6.569e-07, eta: 6:03:50, time: 0.590, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0487, decode.acc_seg: 97.4865, aux.loss_ce: 0.0303, aux.acc_seg: 96.3041, loss: 0.0790 2022-05-06 07:25:23,090 - mmseg - INFO - Iter [43450/80000] lr: 6.560e-07, eta: 6:03:18, time: 0.532, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.3987, aux.loss_ce: 0.0307, aux.acc_seg: 96.2463, loss: 0.0799 2022-05-06 07:25:50,214 - mmseg - INFO - Iter [43500/80000] lr: 6.551e-07, eta: 6:02:46, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0531, decode.acc_seg: 97.1442, aux.loss_ce: 0.0343, aux.acc_seg: 95.8093, loss: 0.0874 2022-05-06 07:26:16,929 - mmseg - INFO - Iter [43550/80000] lr: 6.542e-07, eta: 6:02:13, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0516, decode.acc_seg: 97.1778, aux.loss_ce: 0.0321, aux.acc_seg: 95.9643, loss: 0.0837 2022-05-06 07:26:43,347 - mmseg - INFO - Iter [43600/80000] lr: 6.533e-07, eta: 6:01:41, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0461, decode.acc_seg: 97.5214, aux.loss_ce: 0.0298, aux.acc_seg: 96.3186, loss: 0.0759 2022-05-06 07:27:09,920 - mmseg - INFO - Iter [43650/80000] lr: 6.524e-07, eta: 6:01:08, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0486, decode.acc_seg: 97.4475, aux.loss_ce: 0.0302, aux.acc_seg: 96.3329, loss: 0.0788 2022-05-06 07:27:38,963 - mmseg - INFO - Iter [43700/80000] lr: 6.515e-07, eta: 6:00:38, time: 0.580, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.3558, aux.loss_ce: 0.0305, aux.acc_seg: 96.2639, loss: 0.0797 2022-05-06 07:28:05,443 - mmseg - INFO - Iter [43750/80000] lr: 6.506e-07, eta: 6:00:05, time: 0.530, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0485, decode.acc_seg: 97.3916, aux.loss_ce: 0.0306, aux.acc_seg: 96.2279, loss: 0.0791 2022-05-06 07:28:32,258 - mmseg - INFO - Iter [43800/80000] lr: 6.497e-07, eta: 5:59:33, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0464, decode.acc_seg: 97.5522, aux.loss_ce: 0.0295, aux.acc_seg: 96.4445, loss: 0.0760 2022-05-06 07:28:58,975 - mmseg - INFO - Iter [43850/80000] lr: 6.488e-07, eta: 5:59:01, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0498, decode.acc_seg: 97.4108, aux.loss_ce: 0.0313, aux.acc_seg: 96.2905, loss: 0.0811 2022-05-06 07:29:25,590 - mmseg - INFO - Iter [43900/80000] lr: 6.479e-07, eta: 5:58:28, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.3015, aux.loss_ce: 0.0321, aux.acc_seg: 96.0789, loss: 0.0828 2022-05-06 07:29:52,181 - mmseg - INFO - Iter [43950/80000] lr: 6.470e-07, eta: 5:57:56, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0456, decode.acc_seg: 97.5774, aux.loss_ce: 0.0301, aux.acc_seg: 96.3344, loss: 0.0758 2022-05-06 07:30:21,341 - mmseg - INFO - Saving checkpoint at 44000 iterations 2022-05-06 07:30:42,818 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:30:42,827 - mmseg - INFO - Iter [44000/80000] lr: 6.461e-07, eta: 5:57:43, time: 1.010, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0481, decode.acc_seg: 97.3584, aux.loss_ce: 0.0308, aux.acc_seg: 96.1593, loss: 0.0789 2022-05-06 07:31:09,820 - mmseg - INFO - Iter [44050/80000] lr: 6.452e-07, eta: 5:57:11, time: 0.542, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0488, decode.acc_seg: 97.3968, aux.loss_ce: 0.0308, aux.acc_seg: 96.2322, loss: 0.0797 2022-05-06 07:31:36,432 - mmseg - INFO - Iter [44100/80000] lr: 6.443e-07, eta: 5:56:39, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0494, decode.acc_seg: 97.3718, aux.loss_ce: 0.0316, aux.acc_seg: 96.1721, loss: 0.0811 2022-05-06 07:32:03,011 - mmseg - INFO - Iter [44150/80000] lr: 6.434e-07, eta: 5:56:06, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0487, decode.acc_seg: 97.3848, aux.loss_ce: 0.0311, aux.acc_seg: 96.1372, loss: 0.0798 2022-05-06 07:32:29,710 - mmseg - INFO - Iter [44200/80000] lr: 6.425e-07, eta: 5:55:34, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.5344, aux.loss_ce: 0.0286, aux.acc_seg: 96.3803, loss: 0.0740 2022-05-06 07:32:56,312 - mmseg - INFO - Iter [44250/80000] lr: 6.416e-07, eta: 5:55:01, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0511, decode.acc_seg: 97.2992, aux.loss_ce: 0.0319, aux.acc_seg: 96.1347, loss: 0.0829 2022-05-06 07:33:22,918 - mmseg - INFO - Iter [44300/80000] lr: 6.407e-07, eta: 5:54:29, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5266, aux.loss_ce: 0.0288, aux.acc_seg: 96.4194, loss: 0.0746 2022-05-06 07:33:52,048 - mmseg - INFO - Iter [44350/80000] lr: 6.398e-07, eta: 5:53:59, time: 0.582, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0489, decode.acc_seg: 97.3672, aux.loss_ce: 0.0318, aux.acc_seg: 96.0946, loss: 0.0808 2022-05-06 07:34:18,858 - mmseg - INFO - Iter [44400/80000] lr: 6.389e-07, eta: 5:53:27, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0470, decode.acc_seg: 97.4211, aux.loss_ce: 0.0298, aux.acc_seg: 96.2327, loss: 0.0767 2022-05-06 07:34:45,614 - mmseg - INFO - Iter [44450/80000] lr: 6.380e-07, eta: 5:52:54, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.5197, aux.loss_ce: 0.0288, aux.acc_seg: 96.3728, loss: 0.0739 2022-05-06 07:35:12,058 - mmseg - INFO - Iter [44500/80000] lr: 6.372e-07, eta: 5:52:22, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.5600, aux.loss_ce: 0.0292, aux.acc_seg: 96.3162, loss: 0.0739 2022-05-06 07:35:38,753 - mmseg - INFO - Iter [44550/80000] lr: 6.363e-07, eta: 5:51:50, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0483, decode.acc_seg: 97.4507, aux.loss_ce: 0.0313, aux.acc_seg: 96.1758, loss: 0.0796 2022-05-06 07:36:05,290 - mmseg - INFO - Iter [44600/80000] lr: 6.354e-07, eta: 5:51:17, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0494, decode.acc_seg: 97.4226, aux.loss_ce: 0.0304, aux.acc_seg: 96.4089, loss: 0.0798 2022-05-06 07:36:34,392 - mmseg - INFO - Iter [44650/80000] lr: 6.345e-07, eta: 5:50:47, time: 0.582, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0452, decode.acc_seg: 97.5912, aux.loss_ce: 0.0288, aux.acc_seg: 96.4640, loss: 0.0740 2022-05-06 07:37:01,394 - mmseg - INFO - Iter [44700/80000] lr: 6.336e-07, eta: 5:50:15, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.6083, aux.loss_ce: 0.0285, aux.acc_seg: 96.4586, loss: 0.0726 2022-05-06 07:37:27,930 - mmseg - INFO - Iter [44750/80000] lr: 6.327e-07, eta: 5:49:43, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0495, decode.acc_seg: 97.4318, aux.loss_ce: 0.0318, aux.acc_seg: 96.1877, loss: 0.0813 2022-05-06 07:37:54,656 - mmseg - INFO - Iter [44800/80000] lr: 6.318e-07, eta: 5:49:11, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0459, decode.acc_seg: 97.5200, aux.loss_ce: 0.0296, aux.acc_seg: 96.3225, loss: 0.0755 2022-05-06 07:38:21,146 - mmseg - INFO - Iter [44850/80000] lr: 6.309e-07, eta: 5:48:38, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5132, aux.loss_ce: 0.0287, aux.acc_seg: 96.4288, loss: 0.0745 2022-05-06 07:38:47,564 - mmseg - INFO - Iter [44900/80000] lr: 6.300e-07, eta: 5:48:06, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0512, decode.acc_seg: 97.3065, aux.loss_ce: 0.0326, aux.acc_seg: 96.0346, loss: 0.0838 2022-05-06 07:39:16,691 - mmseg - INFO - Iter [44950/80000] lr: 6.291e-07, eta: 5:47:36, time: 0.582, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0499, decode.acc_seg: 97.2944, aux.loss_ce: 0.0312, aux.acc_seg: 96.0589, loss: 0.0811 2022-05-06 07:39:44,035 - mmseg - INFO - Saving checkpoint at 45000 iterations 2022-05-06 07:40:04,602 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:40:04,609 - mmseg - INFO - Iter [45000/80000] lr: 6.282e-07, eta: 5:47:20, time: 0.956, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0490, decode.acc_seg: 97.3851, aux.loss_ce: 0.0307, aux.acc_seg: 96.2715, loss: 0.0797 2022-05-06 07:40:31,457 - mmseg - INFO - Iter [45050/80000] lr: 6.273e-07, eta: 5:46:48, time: 0.539, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0474, decode.acc_seg: 97.5041, aux.loss_ce: 0.0297, aux.acc_seg: 96.4076, loss: 0.0770 2022-05-06 07:40:57,957 - mmseg - INFO - Iter [45100/80000] lr: 6.264e-07, eta: 5:46:16, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.4413, aux.loss_ce: 0.0311, aux.acc_seg: 96.3154, loss: 0.0803 2022-05-06 07:41:24,615 - mmseg - INFO - Iter [45150/80000] lr: 6.255e-07, eta: 5:45:44, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0492, decode.acc_seg: 97.3891, aux.loss_ce: 0.0307, aux.acc_seg: 96.2539, loss: 0.0799 2022-05-06 07:41:51,329 - mmseg - INFO - Iter [45200/80000] lr: 6.246e-07, eta: 5:45:11, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0496, decode.acc_seg: 97.3773, aux.loss_ce: 0.0321, aux.acc_seg: 96.1168, loss: 0.0817 2022-05-06 07:42:20,420 - mmseg - INFO - Iter [45250/80000] lr: 6.237e-07, eta: 5:44:41, time: 0.582, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0468, decode.acc_seg: 97.5029, aux.loss_ce: 0.0299, aux.acc_seg: 96.3320, loss: 0.0767 2022-05-06 07:42:47,356 - mmseg - INFO - Iter [45300/80000] lr: 6.228e-07, eta: 5:44:09, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5200, aux.loss_ce: 0.0291, aux.acc_seg: 96.3722, loss: 0.0749 2022-05-06 07:43:14,229 - mmseg - INFO - Iter [45350/80000] lr: 6.219e-07, eta: 5:43:37, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0475, decode.acc_seg: 97.4701, aux.loss_ce: 0.0302, aux.acc_seg: 96.3236, loss: 0.0777 2022-05-06 07:43:40,860 - mmseg - INFO - Iter [45400/80000] lr: 6.210e-07, eta: 5:43:05, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0455, decode.acc_seg: 97.5977, aux.loss_ce: 0.0292, aux.acc_seg: 96.5043, loss: 0.0747 2022-05-06 07:44:07,610 - mmseg - INFO - Iter [45450/80000] lr: 6.201e-07, eta: 5:42:33, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.5917, aux.loss_ce: 0.0286, aux.acc_seg: 96.4879, loss: 0.0740 2022-05-06 07:44:34,247 - mmseg - INFO - Iter [45500/80000] lr: 6.192e-07, eta: 5:42:01, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0466, decode.acc_seg: 97.4739, aux.loss_ce: 0.0290, aux.acc_seg: 96.3524, loss: 0.0756 2022-05-06 07:45:00,826 - mmseg - INFO - Iter [45550/80000] lr: 6.183e-07, eta: 5:41:29, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0491, decode.acc_seg: 97.3631, aux.loss_ce: 0.0302, aux.acc_seg: 96.2530, loss: 0.0793 2022-05-06 07:45:29,901 - mmseg - INFO - Iter [45600/80000] lr: 6.174e-07, eta: 5:40:59, time: 0.582, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0462, decode.acc_seg: 97.4968, aux.loss_ce: 0.0299, aux.acc_seg: 96.3236, loss: 0.0761 2022-05-06 07:45:56,790 - mmseg - INFO - Iter [45650/80000] lr: 6.165e-07, eta: 5:40:27, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.5873, aux.loss_ce: 0.0287, aux.acc_seg: 96.3823, loss: 0.0728 2022-05-06 07:46:23,440 - mmseg - INFO - Iter [45700/80000] lr: 6.156e-07, eta: 5:39:55, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0483, decode.acc_seg: 97.4172, aux.loss_ce: 0.0305, aux.acc_seg: 96.2441, loss: 0.0788 2022-05-06 07:46:50,093 - mmseg - INFO - Iter [45750/80000] lr: 6.147e-07, eta: 5:39:23, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0471, decode.acc_seg: 97.4287, aux.loss_ce: 0.0301, aux.acc_seg: 96.1954, loss: 0.0772 2022-05-06 07:47:16,750 - mmseg - INFO - Iter [45800/80000] lr: 6.138e-07, eta: 5:38:51, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5739, aux.loss_ce: 0.0291, aux.acc_seg: 96.4163, loss: 0.0749 2022-05-06 07:47:43,284 - mmseg - INFO - Iter [45850/80000] lr: 6.129e-07, eta: 5:38:19, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0516, decode.acc_seg: 97.2456, aux.loss_ce: 0.0331, aux.acc_seg: 95.9711, loss: 0.0846 2022-05-06 07:48:12,260 - mmseg - INFO - Iter [45900/80000] lr: 6.120e-07, eta: 5:37:48, time: 0.579, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0530, decode.acc_seg: 97.2719, aux.loss_ce: 0.0316, aux.acc_seg: 96.0688, loss: 0.0846 2022-05-06 07:48:38,837 - mmseg - INFO - Iter [45950/80000] lr: 6.111e-07, eta: 5:37:16, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0471, decode.acc_seg: 97.5442, aux.loss_ce: 0.0301, aux.acc_seg: 96.3689, loss: 0.0772 2022-05-06 07:49:05,400 - mmseg - INFO - Saving checkpoint at 46000 iterations 2022-05-06 07:49:26,806 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:49:26,810 - mmseg - INFO - Iter [46000/80000] lr: 6.102e-07, eta: 5:37:00, time: 0.957, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0471, decode.acc_seg: 97.4816, aux.loss_ce: 0.0302, aux.acc_seg: 96.3262, loss: 0.0773 2022-05-06 07:49:53,733 - mmseg - INFO - Iter [46050/80000] lr: 6.093e-07, eta: 5:36:28, time: 0.539, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0496, decode.acc_seg: 97.4060, aux.loss_ce: 0.0314, aux.acc_seg: 96.1940, loss: 0.0809 2022-05-06 07:50:20,304 - mmseg - INFO - Iter [46100/80000] lr: 6.084e-07, eta: 5:35:56, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0464, decode.acc_seg: 97.5723, aux.loss_ce: 0.0291, aux.acc_seg: 96.4623, loss: 0.0755 2022-05-06 07:50:46,969 - mmseg - INFO - Iter [46150/80000] lr: 6.075e-07, eta: 5:35:24, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0477, decode.acc_seg: 97.4223, aux.loss_ce: 0.0304, aux.acc_seg: 96.2284, loss: 0.0781 2022-05-06 07:51:16,264 - mmseg - INFO - Iter [46200/80000] lr: 6.066e-07, eta: 5:34:54, time: 0.584, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0489, decode.acc_seg: 97.4362, aux.loss_ce: 0.0314, aux.acc_seg: 96.2079, loss: 0.0804 2022-05-06 07:51:42,855 - mmseg - INFO - Iter [46250/80000] lr: 6.057e-07, eta: 5:34:22, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0446, decode.acc_seg: 97.5210, aux.loss_ce: 0.0286, aux.acc_seg: 96.3373, loss: 0.0732 2022-05-06 07:52:09,671 - mmseg - INFO - Iter [46300/80000] lr: 6.048e-07, eta: 5:33:50, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0473, decode.acc_seg: 97.4021, aux.loss_ce: 0.0296, aux.acc_seg: 96.2381, loss: 0.0769 2022-05-06 07:52:36,374 - mmseg - INFO - Iter [46350/80000] lr: 6.039e-07, eta: 5:33:18, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0481, decode.acc_seg: 97.4420, aux.loss_ce: 0.0312, aux.acc_seg: 96.2234, loss: 0.0793 2022-05-06 07:53:03,069 - mmseg - INFO - Iter [46400/80000] lr: 6.031e-07, eta: 5:32:46, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0439, decode.acc_seg: 97.6365, aux.loss_ce: 0.0287, aux.acc_seg: 96.4375, loss: 0.0726 2022-05-06 07:53:29,517 - mmseg - INFO - Iter [46450/80000] lr: 6.022e-07, eta: 5:32:14, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0469, decode.acc_seg: 97.5006, aux.loss_ce: 0.0295, aux.acc_seg: 96.3620, loss: 0.0764 2022-05-06 07:53:59,171 - mmseg - INFO - Iter [46500/80000] lr: 6.013e-07, eta: 5:31:45, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0424, decode.acc_seg: 97.7045, aux.loss_ce: 0.0274, aux.acc_seg: 96.5516, loss: 0.0698 2022-05-06 07:54:25,860 - mmseg - INFO - Iter [46550/80000] lr: 6.004e-07, eta: 5:31:13, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0474, decode.acc_seg: 97.5137, aux.loss_ce: 0.0299, aux.acc_seg: 96.3953, loss: 0.0773 2022-05-06 07:54:52,773 - mmseg - INFO - Iter [46600/80000] lr: 5.995e-07, eta: 5:30:41, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0444, decode.acc_seg: 97.5128, aux.loss_ce: 0.0283, aux.acc_seg: 96.3384, loss: 0.0727 2022-05-06 07:55:19,568 - mmseg - INFO - Iter [46650/80000] lr: 5.986e-07, eta: 5:30:09, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0481, decode.acc_seg: 97.4563, aux.loss_ce: 0.0307, aux.acc_seg: 96.2585, loss: 0.0788 2022-05-06 07:55:46,179 - mmseg - INFO - Iter [46700/80000] lr: 5.977e-07, eta: 5:29:37, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0471, decode.acc_seg: 97.4761, aux.loss_ce: 0.0302, aux.acc_seg: 96.2839, loss: 0.0773 2022-05-06 07:56:12,926 - mmseg - INFO - Iter [46750/80000] lr: 5.968e-07, eta: 5:29:06, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0470, decode.acc_seg: 97.5608, aux.loss_ce: 0.0308, aux.acc_seg: 96.3023, loss: 0.0778 2022-05-06 07:56:39,265 - mmseg - INFO - Iter [46800/80000] lr: 5.959e-07, eta: 5:28:34, time: 0.529, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.6924, aux.loss_ce: 0.0280, aux.acc_seg: 96.6413, loss: 0.0721 2022-05-06 07:57:08,606 - mmseg - INFO - Iter [46850/80000] lr: 5.950e-07, eta: 5:28:04, time: 0.587, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0486, decode.acc_seg: 97.4663, aux.loss_ce: 0.0310, aux.acc_seg: 96.2770, loss: 0.0796 2022-05-06 07:57:35,207 - mmseg - INFO - Iter [46900/80000] lr: 5.941e-07, eta: 5:27:32, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0478, decode.acc_seg: 97.4801, aux.loss_ce: 0.0299, aux.acc_seg: 96.2958, loss: 0.0777 2022-05-06 07:58:01,825 - mmseg - INFO - Iter [46950/80000] lr: 5.932e-07, eta: 5:27:00, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0484, decode.acc_seg: 97.4810, aux.loss_ce: 0.0310, aux.acc_seg: 96.2817, loss: 0.0794 2022-05-06 07:58:28,585 - mmseg - INFO - Saving checkpoint at 47000 iterations 2022-05-06 07:58:49,959 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 07:58:49,966 - mmseg - INFO - Iter [47000/80000] lr: 5.923e-07, eta: 5:26:43, time: 0.961, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0448, decode.acc_seg: 97.5804, aux.loss_ce: 0.0290, aux.acc_seg: 96.3841, loss: 0.0738 2022-05-06 07:59:17,386 - mmseg - INFO - Iter [47050/80000] lr: 5.914e-07, eta: 5:26:12, time: 0.548, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0461, decode.acc_seg: 97.5618, aux.loss_ce: 0.0294, aux.acc_seg: 96.3813, loss: 0.0755 2022-05-06 07:59:44,188 - mmseg - INFO - Iter [47100/80000] lr: 5.905e-07, eta: 5:25:40, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0460, decode.acc_seg: 97.4569, aux.loss_ce: 0.0296, aux.acc_seg: 96.2547, loss: 0.0756 2022-05-06 08:00:13,488 - mmseg - INFO - Iter [47150/80000] lr: 5.896e-07, eta: 5:25:10, time: 0.585, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0489, decode.acc_seg: 97.3881, aux.loss_ce: 0.0310, aux.acc_seg: 96.2025, loss: 0.0798 2022-05-06 08:00:40,129 - mmseg - INFO - Iter [47200/80000] lr: 5.887e-07, eta: 5:24:38, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0457, decode.acc_seg: 97.5468, aux.loss_ce: 0.0296, aux.acc_seg: 96.4039, loss: 0.0753 2022-05-06 08:01:06,652 - mmseg - INFO - Iter [47250/80000] lr: 5.878e-07, eta: 5:24:06, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0483, decode.acc_seg: 97.5290, aux.loss_ce: 0.0308, aux.acc_seg: 96.3710, loss: 0.0791 2022-05-06 08:01:33,551 - mmseg - INFO - Iter [47300/80000] lr: 5.869e-07, eta: 5:23:35, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0462, decode.acc_seg: 97.4984, aux.loss_ce: 0.0298, aux.acc_seg: 96.3105, loss: 0.0760 2022-05-06 08:02:00,296 - mmseg - INFO - Iter [47350/80000] lr: 5.860e-07, eta: 5:23:03, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0464, decode.acc_seg: 97.5395, aux.loss_ce: 0.0294, aux.acc_seg: 96.4240, loss: 0.0758 2022-05-06 08:02:26,760 - mmseg - INFO - Iter [47400/80000] lr: 5.851e-07, eta: 5:22:31, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6868, aux.loss_ce: 0.0276, aux.acc_seg: 96.5947, loss: 0.0708 2022-05-06 08:02:55,725 - mmseg - INFO - Iter [47450/80000] lr: 5.842e-07, eta: 5:22:01, time: 0.579, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0468, decode.acc_seg: 97.5397, aux.loss_ce: 0.0299, aux.acc_seg: 96.3492, loss: 0.0768 2022-05-06 08:03:22,601 - mmseg - INFO - Iter [47500/80000] lr: 5.833e-07, eta: 5:21:29, time: 0.537, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.5795, aux.loss_ce: 0.0291, aux.acc_seg: 96.4262, loss: 0.0744 2022-05-06 08:03:49,271 - mmseg - INFO - Iter [47550/80000] lr: 5.824e-07, eta: 5:20:58, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0430, decode.acc_seg: 97.6564, aux.loss_ce: 0.0279, aux.acc_seg: 96.5354, loss: 0.0708 2022-05-06 08:04:15,809 - mmseg - INFO - Iter [47600/80000] lr: 5.815e-07, eta: 5:20:26, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0445, decode.acc_seg: 97.5759, aux.loss_ce: 0.0286, aux.acc_seg: 96.3767, loss: 0.0731 2022-05-06 08:04:42,269 - mmseg - INFO - Iter [47650/80000] lr: 5.806e-07, eta: 5:19:54, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0444, decode.acc_seg: 97.6559, aux.loss_ce: 0.0300, aux.acc_seg: 96.3711, loss: 0.0744 2022-05-06 08:05:08,758 - mmseg - INFO - Iter [47700/80000] lr: 5.797e-07, eta: 5:19:22, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.5428, aux.loss_ce: 0.0281, aux.acc_seg: 96.4046, loss: 0.0727 2022-05-06 08:05:38,048 - mmseg - INFO - Iter [47750/80000] lr: 5.788e-07, eta: 5:18:52, time: 0.586, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.6095, aux.loss_ce: 0.0292, aux.acc_seg: 96.4172, loss: 0.0743 2022-05-06 08:06:04,846 - mmseg - INFO - Iter [47800/80000] lr: 5.779e-07, eta: 5:18:21, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0457, decode.acc_seg: 97.4662, aux.loss_ce: 0.0297, aux.acc_seg: 96.2271, loss: 0.0754 2022-05-06 08:06:31,438 - mmseg - INFO - Iter [47850/80000] lr: 5.770e-07, eta: 5:17:49, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.6244, aux.loss_ce: 0.0288, aux.acc_seg: 96.4468, loss: 0.0739 2022-05-06 08:06:58,266 - mmseg - INFO - Iter [47900/80000] lr: 5.761e-07, eta: 5:17:17, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0477, decode.acc_seg: 97.4342, aux.loss_ce: 0.0307, aux.acc_seg: 96.2147, loss: 0.0784 2022-05-06 08:07:24,981 - mmseg - INFO - Iter [47950/80000] lr: 5.752e-07, eta: 5:16:46, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.6709, aux.loss_ce: 0.0281, aux.acc_seg: 96.5499, loss: 0.0723 2022-05-06 08:07:51,457 - mmseg - INFO - Saving checkpoint at 48000 iterations 2022-05-06 08:08:11,895 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:08:11,907 - mmseg - INFO - Iter [48000/80000] lr: 5.743e-07, eta: 5:16:28, time: 0.937, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0437, decode.acc_seg: 97.5986, aux.loss_ce: 0.0287, aux.acc_seg: 96.4070, loss: 0.0725 2022-05-06 08:12:21,066 - mmseg - INFO - per class results: 2022-05-06 08:12:21,071 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 93.05 | 96.98 | | bag | 43.46 | 57.15 | | bed | 37.18 | 46.81 | | bedclothes | 46.19 | 68.5 | | bench | 32.4 | 40.63 | | bicycle | 84.08 | 92.56 | | bird | 94.15 | 97.92 | | boat | 85.73 | 92.08 | | book | 61.26 | 73.93 | | bottle | 89.3 | 96.47 | | building | 68.36 | 80.49 | | bus | 94.43 | 97.66 | | cabinet | 51.54 | 67.43 | | car | 93.82 | 96.92 | | cat | 93.75 | 98.31 | | ceiling | 60.74 | 77.45 | | chair | 65.74 | 78.52 | | cloth | 26.05 | 33.64 | | computer | 61.6 | 71.75 | | cow | 95.69 | 98.71 | | cup | 47.49 | 62.66 | | curtain | 59.96 | 75.86 | | dog | 92.15 | 98.05 | | door | 36.0 | 48.76 | | fence | 46.56 | 60.45 | | floor | 76.86 | 89.22 | | flower | 32.65 | 43.62 | | food | 41.62 | 53.38 | | grass | 83.3 | 92.6 | | ground | 57.56 | 71.25 | | horse | 94.55 | 97.79 | | keyboard | 90.83 | 94.69 | | light | 59.15 | 74.34 | | motorbike | 90.36 | 96.91 | | mountain | 58.45 | 73.76 | | mouse | 78.76 | 93.37 | | person | 90.45 | 96.52 | | plate | 28.97 | 38.11 | | platform | 57.88 | 70.0 | | pottedplant | 80.32 | 92.65 | | road | 53.45 | 71.24 | | rock | 57.44 | 67.22 | | sheep | 95.04 | 98.27 | | shelves | 35.36 | 46.12 | | sidewalk | 33.24 | 47.69 | | sign | 50.87 | 57.38 | | sky | 95.07 | 97.36 | | snow | 76.52 | 90.48 | | sofa | 60.35 | 71.27 | | table | 73.62 | 86.11 | | track | 72.98 | 84.24 | | train | 93.42 | 97.52 | | tree | 81.51 | 90.44 | | truck | 52.07 | 59.38 | | tvmonitor | 90.9 | 94.44 | | wall | 74.1 | 86.47 | | water | 92.09 | 96.55 | | window | 46.43 | 60.19 | | wood | 25.46 | 33.68 | +-------------+-------+-------+ 2022-05-06 08:12:21,071 - mmseg - INFO - Summary: 2022-05-06 08:12:21,072 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.66 | 66.82 | 76.68 | +-------+-------+-------+ 2022-05-06 08:12:21,074 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_32000.pth was removed 2022-05-06 08:12:42,370 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_48000.pth. 2022-05-06 08:12:42,382 - mmseg - INFO - Best mIoU is 0.6682 at 48000 iter. 2022-05-06 08:12:42,406 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:12:42,406 - mmseg - INFO - Iter(val) [638] aAcc: 0.8666, mIoU: 0.6682, mAcc: 0.7668, IoU.aeroplane: 0.9305, IoU.bag: 0.4346, IoU.bed: 0.3718, IoU.bedclothes: 0.4619, IoU.bench: 0.3240, IoU.bicycle: 0.8408, IoU.bird: 0.9415, IoU.boat: 0.8573, IoU.book: 0.6126, IoU.bottle: 0.8930, IoU.building: 0.6836, IoU.bus: 0.9443, IoU.cabinet: 0.5154, IoU.car: 0.9382, IoU.cat: 0.9375, IoU.ceiling: 0.6074, IoU.chair: 0.6574, IoU.cloth: 0.2605, IoU.computer: 0.6160, IoU.cow: 0.9569, IoU.cup: 0.4749, IoU.curtain: 0.5996, IoU.dog: 0.9215, IoU.door: 0.3600, IoU.fence: 0.4656, IoU.floor: 0.7686, IoU.flower: 0.3265, IoU.food: 0.4162, IoU.grass: 0.8330, IoU.ground: 0.5756, IoU.horse: 0.9455, IoU.keyboard: 0.9083, IoU.light: 0.5915, IoU.motorbike: 0.9036, IoU.mountain: 0.5845, IoU.mouse: 0.7876, IoU.person: 0.9045, IoU.plate: 0.2897, IoU.platform: 0.5788, IoU.pottedplant: 0.8032, IoU.road: 0.5345, IoU.rock: 0.5744, IoU.sheep: 0.9504, IoU.shelves: 0.3536, IoU.sidewalk: 0.3324, IoU.sign: 0.5087, IoU.sky: 0.9507, IoU.snow: 0.7652, IoU.sofa: 0.6035, IoU.table: 0.7362, IoU.track: 0.7298, IoU.train: 0.9342, IoU.tree: 0.8151, IoU.truck: 0.5207, IoU.tvmonitor: 0.9090, IoU.wall: 0.7410, IoU.water: 0.9209, IoU.window: 0.4643, IoU.wood: 0.2546, Acc.aeroplane: 0.9698, Acc.bag: 0.5715, Acc.bed: 0.4681, Acc.bedclothes: 0.6850, Acc.bench: 0.4063, Acc.bicycle: 0.9256, Acc.bird: 0.9792, Acc.boat: 0.9208, Acc.book: 0.7393, Acc.bottle: 0.9647, Acc.building: 0.8049, Acc.bus: 0.9766, Acc.cabinet: 0.6743, Acc.car: 0.9692, Acc.cat: 0.9831, Acc.ceiling: 0.7745, Acc.chair: 0.7852, Acc.cloth: 0.3364, Acc.computer: 0.7175, Acc.cow: 0.9871, Acc.cup: 0.6266, Acc.curtain: 0.7586, Acc.dog: 0.9805, Acc.door: 0.4876, Acc.fence: 0.6045, Acc.floor: 0.8922, Acc.flower: 0.4362, Acc.food: 0.5338, Acc.grass: 0.9260, Acc.ground: 0.7125, Acc.horse: 0.9779, Acc.keyboard: 0.9469, Acc.light: 0.7434, Acc.motorbike: 0.9691, Acc.mountain: 0.7376, Acc.mouse: 0.9337, Acc.person: 0.9652, Acc.plate: 0.3811, Acc.platform: 0.7000, Acc.pottedplant: 0.9265, Acc.road: 0.7124, Acc.rock: 0.6722, Acc.sheep: 0.9827, Acc.shelves: 0.4612, Acc.sidewalk: 0.4769, Acc.sign: 0.5738, Acc.sky: 0.9736, Acc.snow: 0.9048, Acc.sofa: 0.7127, Acc.table: 0.8611, Acc.track: 0.8424, Acc.train: 0.9752, Acc.tree: 0.9044, Acc.truck: 0.5938, Acc.tvmonitor: 0.9444, Acc.wall: 0.8647, Acc.water: 0.9655, Acc.window: 0.6019, Acc.wood: 0.3368 2022-05-06 08:13:12,303 - mmseg - INFO - Iter [48050/80000] lr: 5.734e-07, eta: 5:18:58, time: 6.009, data_time: 5.465, memory: 58091, decode.loss_ce: 0.0461, decode.acc_seg: 97.5350, aux.loss_ce: 0.0298, aux.acc_seg: 96.3364, loss: 0.0760 2022-05-06 08:13:38,928 - mmseg - INFO - Iter [48100/80000] lr: 5.725e-07, eta: 5:18:26, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.6281, aux.loss_ce: 0.0292, aux.acc_seg: 96.4381, loss: 0.0738 2022-05-06 08:14:05,613 - mmseg - INFO - Iter [48150/80000] lr: 5.716e-07, eta: 5:17:54, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0448, decode.acc_seg: 97.5095, aux.loss_ce: 0.0290, aux.acc_seg: 96.3014, loss: 0.0738 2022-05-06 08:14:32,019 - mmseg - INFO - Iter [48200/80000] lr: 5.707e-07, eta: 5:17:21, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0456, decode.acc_seg: 97.5792, aux.loss_ce: 0.0291, aux.acc_seg: 96.4279, loss: 0.0747 2022-05-06 08:14:58,876 - mmseg - INFO - Iter [48250/80000] lr: 5.698e-07, eta: 5:16:49, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.6042, aux.loss_ce: 0.0283, aux.acc_seg: 96.5956, loss: 0.0736 2022-05-06 08:15:25,370 - mmseg - INFO - Iter [48300/80000] lr: 5.690e-07, eta: 5:16:17, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0456, decode.acc_seg: 97.5351, aux.loss_ce: 0.0288, aux.acc_seg: 96.3821, loss: 0.0744 2022-05-06 08:15:51,997 - mmseg - INFO - Iter [48350/80000] lr: 5.681e-07, eta: 5:15:45, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.5633, aux.loss_ce: 0.0282, aux.acc_seg: 96.4357, loss: 0.0724 2022-05-06 08:16:21,137 - mmseg - INFO - Iter [48400/80000] lr: 5.672e-07, eta: 5:15:15, time: 0.583, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0507, decode.acc_seg: 97.3998, aux.loss_ce: 0.0301, aux.acc_seg: 96.2831, loss: 0.0808 2022-05-06 08:16:47,857 - mmseg - INFO - Iter [48450/80000] lr: 5.663e-07, eta: 5:14:43, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.4643, aux.loss_ce: 0.0286, aux.acc_seg: 96.2930, loss: 0.0739 2022-05-06 08:17:14,679 - mmseg - INFO - Iter [48500/80000] lr: 5.654e-07, eta: 5:14:11, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0468, decode.acc_seg: 97.4794, aux.loss_ce: 0.0298, aux.acc_seg: 96.2850, loss: 0.0767 2022-05-06 08:17:41,395 - mmseg - INFO - Iter [48550/80000] lr: 5.645e-07, eta: 5:13:39, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.6075, aux.loss_ce: 0.0298, aux.acc_seg: 96.4149, loss: 0.0756 2022-05-06 08:18:08,050 - mmseg - INFO - Iter [48600/80000] lr: 5.636e-07, eta: 5:13:07, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.7497, aux.loss_ce: 0.0272, aux.acc_seg: 96.6138, loss: 0.0690 2022-05-06 08:18:35,057 - mmseg - INFO - Iter [48650/80000] lr: 5.627e-07, eta: 5:12:35, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0434, decode.acc_seg: 97.7055, aux.loss_ce: 0.0281, aux.acc_seg: 96.5871, loss: 0.0715 2022-05-06 08:19:04,659 - mmseg - INFO - Iter [48700/80000] lr: 5.618e-07, eta: 5:12:05, time: 0.591, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0425, decode.acc_seg: 97.6359, aux.loss_ce: 0.0274, aux.acc_seg: 96.4532, loss: 0.0699 2022-05-06 08:19:31,325 - mmseg - INFO - Iter [48750/80000] lr: 5.609e-07, eta: 5:11:33, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0431, decode.acc_seg: 97.6969, aux.loss_ce: 0.0281, aux.acc_seg: 96.5307, loss: 0.0712 2022-05-06 08:19:58,269 - mmseg - INFO - Iter [48800/80000] lr: 5.600e-07, eta: 5:11:01, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.6903, aux.loss_ce: 0.0285, aux.acc_seg: 96.5563, loss: 0.0727 2022-05-06 08:20:24,793 - mmseg - INFO - Iter [48850/80000] lr: 5.591e-07, eta: 5:10:29, time: 0.532, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0476, decode.acc_seg: 97.4588, aux.loss_ce: 0.0298, aux.acc_seg: 96.3423, loss: 0.0775 2022-05-06 08:20:51,906 - mmseg - INFO - Iter [48900/80000] lr: 5.582e-07, eta: 5:09:57, time: 0.541, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0467, decode.acc_seg: 97.5585, aux.loss_ce: 0.0299, aux.acc_seg: 96.3748, loss: 0.0766 2022-05-06 08:21:18,561 - mmseg - INFO - Iter [48950/80000] lr: 5.573e-07, eta: 5:09:25, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0450, decode.acc_seg: 97.5922, aux.loss_ce: 0.0290, aux.acc_seg: 96.4237, loss: 0.0740 2022-05-06 08:21:47,669 - mmseg - INFO - Saving checkpoint at 49000 iterations 2022-05-06 08:22:08,677 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:22:08,686 - mmseg - INFO - Iter [49000/80000] lr: 5.564e-07, eta: 5:09:08, time: 0.999, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0467, decode.acc_seg: 97.4349, aux.loss_ce: 0.0303, aux.acc_seg: 96.1421, loss: 0.0771 2022-05-06 08:22:35,603 - mmseg - INFO - Iter [49050/80000] lr: 5.555e-07, eta: 5:08:36, time: 0.542, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0433, decode.acc_seg: 97.6616, aux.loss_ce: 0.0283, aux.acc_seg: 96.4565, loss: 0.0715 2022-05-06 08:23:02,193 - mmseg - INFO - Iter [49100/80000] lr: 5.546e-07, eta: 5:08:04, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0462, decode.acc_seg: 97.5007, aux.loss_ce: 0.0297, aux.acc_seg: 96.2740, loss: 0.0760 2022-05-06 08:23:28,649 - mmseg - INFO - Iter [49150/80000] lr: 5.537e-07, eta: 5:07:32, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0461, decode.acc_seg: 97.5101, aux.loss_ce: 0.0296, aux.acc_seg: 96.3218, loss: 0.0757 2022-05-06 08:23:55,269 - mmseg - INFO - Iter [49200/80000] lr: 5.528e-07, eta: 5:07:00, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0439, decode.acc_seg: 97.6508, aux.loss_ce: 0.0282, aux.acc_seg: 96.5011, loss: 0.0722 2022-05-06 08:24:21,820 - mmseg - INFO - Iter [49250/80000] lr: 5.519e-07, eta: 5:06:28, time: 0.531, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0460, decode.acc_seg: 97.5577, aux.loss_ce: 0.0298, aux.acc_seg: 96.3445, loss: 0.0758 2022-05-06 08:24:50,955 - mmseg - INFO - Iter [49300/80000] lr: 5.510e-07, eta: 5:05:58, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0438, decode.acc_seg: 97.6330, aux.loss_ce: 0.0282, aux.acc_seg: 96.5409, loss: 0.0720 2022-05-06 08:25:17,707 - mmseg - INFO - Iter [49350/80000] lr: 5.501e-07, eta: 5:05:26, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.5720, aux.loss_ce: 0.0287, aux.acc_seg: 96.4131, loss: 0.0739 2022-05-06 08:25:44,432 - mmseg - INFO - Iter [49400/80000] lr: 5.492e-07, eta: 5:04:54, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0471, decode.acc_seg: 97.4003, aux.loss_ce: 0.0296, aux.acc_seg: 96.2201, loss: 0.0767 2022-05-06 08:26:10,945 - mmseg - INFO - Iter [49450/80000] lr: 5.483e-07, eta: 5:04:22, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0420, decode.acc_seg: 97.7237, aux.loss_ce: 0.0271, aux.acc_seg: 96.6028, loss: 0.0690 2022-05-06 08:26:37,386 - mmseg - INFO - Iter [49500/80000] lr: 5.474e-07, eta: 5:03:50, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0480, decode.acc_seg: 97.4902, aux.loss_ce: 0.0305, aux.acc_seg: 96.2989, loss: 0.0785 2022-05-06 08:27:04,007 - mmseg - INFO - Iter [49550/80000] lr: 5.465e-07, eta: 5:03:18, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0459, decode.acc_seg: 97.4695, aux.loss_ce: 0.0292, aux.acc_seg: 96.3152, loss: 0.0751 2022-05-06 08:27:30,612 - mmseg - INFO - Iter [49600/80000] lr: 5.456e-07, eta: 5:02:47, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0457, decode.acc_seg: 97.5826, aux.loss_ce: 0.0291, aux.acc_seg: 96.3801, loss: 0.0748 2022-05-06 08:27:59,823 - mmseg - INFO - Iter [49650/80000] lr: 5.447e-07, eta: 5:02:16, time: 0.584, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0462, decode.acc_seg: 97.5186, aux.loss_ce: 0.0292, aux.acc_seg: 96.3377, loss: 0.0754 2022-05-06 08:28:26,579 - mmseg - INFO - Iter [49700/80000] lr: 5.438e-07, eta: 5:01:44, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.6401, aux.loss_ce: 0.0275, aux.acc_seg: 96.5100, loss: 0.0703 2022-05-06 08:28:53,068 - mmseg - INFO - Iter [49750/80000] lr: 5.429e-07, eta: 5:01:13, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0450, decode.acc_seg: 97.5388, aux.loss_ce: 0.0294, aux.acc_seg: 96.3512, loss: 0.0743 2022-05-06 08:29:19,965 - mmseg - INFO - Iter [49800/80000] lr: 5.420e-07, eta: 5:00:41, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0443, decode.acc_seg: 97.5215, aux.loss_ce: 0.0281, aux.acc_seg: 96.3557, loss: 0.0724 2022-05-06 08:29:46,899 - mmseg - INFO - Iter [49850/80000] lr: 5.411e-07, eta: 5:00:09, time: 0.539, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0448, decode.acc_seg: 97.6016, aux.loss_ce: 0.0289, aux.acc_seg: 96.4005, loss: 0.0736 2022-05-06 08:30:13,531 - mmseg - INFO - Iter [49900/80000] lr: 5.402e-07, eta: 4:59:37, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0439, decode.acc_seg: 97.7329, aux.loss_ce: 0.0280, aux.acc_seg: 96.6277, loss: 0.0719 2022-05-06 08:30:42,435 - mmseg - INFO - Iter [49950/80000] lr: 5.393e-07, eta: 4:59:07, time: 0.578, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0476, decode.acc_seg: 97.4775, aux.loss_ce: 0.0302, aux.acc_seg: 96.2949, loss: 0.0779 2022-05-06 08:31:09,143 - mmseg - INFO - Saving checkpoint at 50000 iterations 2022-05-06 08:31:30,353 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:31:30,361 - mmseg - INFO - Iter [50000/80000] lr: 5.384e-07, eta: 4:58:48, time: 0.956, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0436, decode.acc_seg: 97.5617, aux.loss_ce: 0.0282, aux.acc_seg: 96.4090, loss: 0.0718 2022-05-06 08:31:57,305 - mmseg - INFO - Iter [50050/80000] lr: 5.375e-07, eta: 4:58:16, time: 0.542, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0455, decode.acc_seg: 97.5901, aux.loss_ce: 0.0293, aux.acc_seg: 96.3940, loss: 0.0748 2022-05-06 08:32:23,736 - mmseg - INFO - Iter [50100/80000] lr: 5.366e-07, eta: 4:57:44, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0433, decode.acc_seg: 97.6519, aux.loss_ce: 0.0280, aux.acc_seg: 96.5053, loss: 0.0713 2022-05-06 08:32:50,274 - mmseg - INFO - Iter [50150/80000] lr: 5.357e-07, eta: 4:57:12, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0435, decode.acc_seg: 97.5737, aux.loss_ce: 0.0284, aux.acc_seg: 96.3780, loss: 0.0718 2022-05-06 08:33:16,886 - mmseg - INFO - Iter [50200/80000] lr: 5.349e-07, eta: 4:56:41, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0461, decode.acc_seg: 97.5533, aux.loss_ce: 0.0293, aux.acc_seg: 96.4630, loss: 0.0753 2022-05-06 08:33:46,567 - mmseg - INFO - Iter [50250/80000] lr: 5.340e-07, eta: 4:56:11, time: 0.592, data_time: 0.058, memory: 58091, decode.loss_ce: 0.0493, decode.acc_seg: 97.3444, aux.loss_ce: 0.0306, aux.acc_seg: 96.1293, loss: 0.0799 2022-05-06 08:34:13,351 - mmseg - INFO - Iter [50300/80000] lr: 5.331e-07, eta: 4:55:39, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0470, decode.acc_seg: 97.5526, aux.loss_ce: 0.0302, aux.acc_seg: 96.3466, loss: 0.0772 2022-05-06 08:34:40,581 - mmseg - INFO - Iter [50350/80000] lr: 5.322e-07, eta: 4:55:08, time: 0.545, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0470, decode.acc_seg: 97.4433, aux.loss_ce: 0.0300, aux.acc_seg: 96.2323, loss: 0.0770 2022-05-06 08:35:07,273 - mmseg - INFO - Iter [50400/80000] lr: 5.313e-07, eta: 4:54:36, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.7754, aux.loss_ce: 0.0262, aux.acc_seg: 96.6132, loss: 0.0658 2022-05-06 08:35:33,980 - mmseg - INFO - Iter [50450/80000] lr: 5.304e-07, eta: 4:54:04, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.5895, aux.loss_ce: 0.0290, aux.acc_seg: 96.4042, loss: 0.0737 2022-05-06 08:36:00,947 - mmseg - INFO - Iter [50500/80000] lr: 5.295e-07, eta: 4:53:33, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0454, decode.acc_seg: 97.4988, aux.loss_ce: 0.0289, aux.acc_seg: 96.3588, loss: 0.0743 2022-05-06 08:36:30,104 - mmseg - INFO - Iter [50550/80000] lr: 5.286e-07, eta: 4:53:02, time: 0.583, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0444, decode.acc_seg: 97.6207, aux.loss_ce: 0.0285, aux.acc_seg: 96.4372, loss: 0.0729 2022-05-06 08:36:56,824 - mmseg - INFO - Iter [50600/80000] lr: 5.277e-07, eta: 4:52:31, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0463, decode.acc_seg: 97.5450, aux.loss_ce: 0.0299, aux.acc_seg: 96.3053, loss: 0.0762 2022-05-06 08:37:23,566 - mmseg - INFO - Iter [50650/80000] lr: 5.268e-07, eta: 4:51:59, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.5639, aux.loss_ce: 0.0292, aux.acc_seg: 96.3413, loss: 0.0738 2022-05-06 08:37:50,073 - mmseg - INFO - Iter [50700/80000] lr: 5.259e-07, eta: 4:51:27, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0455, decode.acc_seg: 97.5313, aux.loss_ce: 0.0296, aux.acc_seg: 96.3202, loss: 0.0752 2022-05-06 08:38:16,900 - mmseg - INFO - Iter [50750/80000] lr: 5.250e-07, eta: 4:50:56, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0429, decode.acc_seg: 97.6651, aux.loss_ce: 0.0277, aux.acc_seg: 96.5195, loss: 0.0706 2022-05-06 08:38:43,868 - mmseg - INFO - Iter [50800/80000] lr: 5.241e-07, eta: 4:50:24, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0433, decode.acc_seg: 97.6764, aux.loss_ce: 0.0284, aux.acc_seg: 96.5141, loss: 0.0717 2022-05-06 08:39:11,034 - mmseg - INFO - Iter [50850/80000] lr: 5.232e-07, eta: 4:49:53, time: 0.543, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0429, decode.acc_seg: 97.7727, aux.loss_ce: 0.0280, aux.acc_seg: 96.6113, loss: 0.0709 2022-05-06 08:39:40,296 - mmseg - INFO - Iter [50900/80000] lr: 5.223e-07, eta: 4:49:23, time: 0.585, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0412, decode.acc_seg: 97.7641, aux.loss_ce: 0.0269, aux.acc_seg: 96.6314, loss: 0.0682 2022-05-06 08:40:07,075 - mmseg - INFO - Iter [50950/80000] lr: 5.214e-07, eta: 4:48:51, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5160, aux.loss_ce: 0.0293, aux.acc_seg: 96.3435, loss: 0.0751 2022-05-06 08:40:33,730 - mmseg - INFO - Saving checkpoint at 51000 iterations 2022-05-06 08:40:54,866 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:40:54,874 - mmseg - INFO - Iter [51000/80000] lr: 5.205e-07, eta: 4:48:31, time: 0.954, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0436, decode.acc_seg: 97.6365, aux.loss_ce: 0.0285, aux.acc_seg: 96.4390, loss: 0.0721 2022-05-06 08:41:22,182 - mmseg - INFO - Iter [51050/80000] lr: 5.196e-07, eta: 4:48:00, time: 0.548, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.5757, aux.loss_ce: 0.0281, aux.acc_seg: 96.3953, loss: 0.0722 2022-05-06 08:41:49,509 - mmseg - INFO - Iter [51100/80000] lr: 5.187e-07, eta: 4:47:29, time: 0.547, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.7799, aux.loss_ce: 0.0264, aux.acc_seg: 96.6733, loss: 0.0669 2022-05-06 08:42:16,348 - mmseg - INFO - Iter [51150/80000] lr: 5.178e-07, eta: 4:46:57, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0446, decode.acc_seg: 97.5493, aux.loss_ce: 0.0289, aux.acc_seg: 96.3457, loss: 0.0735 2022-05-06 08:42:45,559 - mmseg - INFO - Iter [51200/80000] lr: 5.169e-07, eta: 4:46:27, time: 0.584, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0455, decode.acc_seg: 97.6626, aux.loss_ce: 0.0292, aux.acc_seg: 96.5502, loss: 0.0747 2022-05-06 08:43:12,107 - mmseg - INFO - Iter [51250/80000] lr: 5.160e-07, eta: 4:45:56, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.7277, aux.loss_ce: 0.0282, aux.acc_seg: 96.5493, loss: 0.0708 2022-05-06 08:43:38,773 - mmseg - INFO - Iter [51300/80000] lr: 5.151e-07, eta: 4:45:24, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0436, decode.acc_seg: 97.6618, aux.loss_ce: 0.0277, aux.acc_seg: 96.5583, loss: 0.0713 2022-05-06 08:44:05,252 - mmseg - INFO - Iter [51350/80000] lr: 5.142e-07, eta: 4:44:52, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0429, decode.acc_seg: 97.6973, aux.loss_ce: 0.0282, aux.acc_seg: 96.5205, loss: 0.0712 2022-05-06 08:44:31,848 - mmseg - INFO - Iter [51400/80000] lr: 5.133e-07, eta: 4:44:21, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.6306, aux.loss_ce: 0.0286, aux.acc_seg: 96.4657, loss: 0.0729 2022-05-06 08:44:58,197 - mmseg - INFO - Iter [51450/80000] lr: 5.124e-07, eta: 4:43:49, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.6422, aux.loss_ce: 0.0282, aux.acc_seg: 96.4229, loss: 0.0709 2022-05-06 08:45:27,250 - mmseg - INFO - Iter [51500/80000] lr: 5.115e-07, eta: 4:43:19, time: 0.581, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0473, decode.acc_seg: 97.5524, aux.loss_ce: 0.0290, aux.acc_seg: 96.5164, loss: 0.0763 2022-05-06 08:45:53,838 - mmseg - INFO - Iter [51550/80000] lr: 5.106e-07, eta: 4:42:47, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.5778, aux.loss_ce: 0.0287, aux.acc_seg: 96.4524, loss: 0.0740 2022-05-06 08:46:20,438 - mmseg - INFO - Iter [51600/80000] lr: 5.097e-07, eta: 4:42:15, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0465, decode.acc_seg: 97.5348, aux.loss_ce: 0.0305, aux.acc_seg: 96.1988, loss: 0.0770 2022-05-06 08:46:47,287 - mmseg - INFO - Iter [51650/80000] lr: 5.088e-07, eta: 4:41:44, time: 0.537, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0427, decode.acc_seg: 97.7180, aux.loss_ce: 0.0276, aux.acc_seg: 96.5447, loss: 0.0704 2022-05-06 08:47:13,859 - mmseg - INFO - Iter [51700/80000] lr: 5.079e-07, eta: 4:41:12, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7835, aux.loss_ce: 0.0270, aux.acc_seg: 96.6449, loss: 0.0677 2022-05-06 08:47:40,425 - mmseg - INFO - Iter [51750/80000] lr: 5.070e-07, eta: 4:40:41, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.6101, aux.loss_ce: 0.0292, aux.acc_seg: 96.3911, loss: 0.0740 2022-05-06 08:48:09,496 - mmseg - INFO - Iter [51800/80000] lr: 5.061e-07, eta: 4:40:11, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0445, decode.acc_seg: 97.5096, aux.loss_ce: 0.0287, aux.acc_seg: 96.2385, loss: 0.0732 2022-05-06 08:48:35,826 - mmseg - INFO - Iter [51850/80000] lr: 5.052e-07, eta: 4:39:39, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0466, decode.acc_seg: 97.4685, aux.loss_ce: 0.0296, aux.acc_seg: 96.2627, loss: 0.0762 2022-05-06 08:49:02,240 - mmseg - INFO - Iter [51900/80000] lr: 5.043e-07, eta: 4:39:07, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0430, decode.acc_seg: 97.6951, aux.loss_ce: 0.0281, aux.acc_seg: 96.5267, loss: 0.0711 2022-05-06 08:49:29,453 - mmseg - INFO - Iter [51950/80000] lr: 5.034e-07, eta: 4:38:36, time: 0.544, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0424, decode.acc_seg: 97.7107, aux.loss_ce: 0.0270, aux.acc_seg: 96.6072, loss: 0.0694 2022-05-06 08:49:56,007 - mmseg - INFO - Saving checkpoint at 52000 iterations 2022-05-06 08:50:16,991 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:50:17,000 - mmseg - INFO - Iter [52000/80000] lr: 5.025e-07, eta: 4:38:16, time: 0.948, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0460, decode.acc_seg: 97.5326, aux.loss_ce: 0.0286, aux.acc_seg: 96.4137, loss: 0.0747 2022-05-06 08:50:44,101 - mmseg - INFO - Iter [52050/80000] lr: 5.016e-07, eta: 4:37:44, time: 0.545, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0449, decode.acc_seg: 97.5440, aux.loss_ce: 0.0290, aux.acc_seg: 96.3750, loss: 0.0739 2022-05-06 08:51:11,168 - mmseg - INFO - Iter [52100/80000] lr: 5.008e-07, eta: 4:37:13, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0444, decode.acc_seg: 97.6277, aux.loss_ce: 0.0288, aux.acc_seg: 96.4702, loss: 0.0733 2022-05-06 08:51:40,406 - mmseg - INFO - Iter [52150/80000] lr: 4.999e-07, eta: 4:36:43, time: 0.585, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0454, decode.acc_seg: 97.6427, aux.loss_ce: 0.0298, aux.acc_seg: 96.4423, loss: 0.0752 2022-05-06 08:52:07,099 - mmseg - INFO - Iter [52200/80000] lr: 4.990e-07, eta: 4:36:12, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0456, decode.acc_seg: 97.6093, aux.loss_ce: 0.0293, aux.acc_seg: 96.4362, loss: 0.0749 2022-05-06 08:52:33,916 - mmseg - INFO - Iter [52250/80000] lr: 4.981e-07, eta: 4:35:40, time: 0.536, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0455, decode.acc_seg: 97.6428, aux.loss_ce: 0.0286, aux.acc_seg: 96.5524, loss: 0.0741 2022-05-06 08:53:00,746 - mmseg - INFO - Iter [52300/80000] lr: 4.972e-07, eta: 4:35:09, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0436, decode.acc_seg: 97.6260, aux.loss_ce: 0.0286, aux.acc_seg: 96.3880, loss: 0.0722 2022-05-06 08:53:28,198 - mmseg - INFO - Iter [52350/80000] lr: 4.963e-07, eta: 4:34:38, time: 0.549, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.5051, aux.loss_ce: 0.0294, aux.acc_seg: 96.2368, loss: 0.0741 2022-05-06 08:53:54,956 - mmseg - INFO - Iter [52400/80000] lr: 4.954e-07, eta: 4:34:06, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.6775, aux.loss_ce: 0.0273, aux.acc_seg: 96.5872, loss: 0.0701 2022-05-06 08:54:24,292 - mmseg - INFO - Iter [52450/80000] lr: 4.945e-07, eta: 4:33:36, time: 0.587, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0438, decode.acc_seg: 97.6906, aux.loss_ce: 0.0282, aux.acc_seg: 96.5427, loss: 0.0720 2022-05-06 08:54:50,750 - mmseg - INFO - Iter [52500/80000] lr: 4.936e-07, eta: 4:33:05, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0410, decode.acc_seg: 97.7902, aux.loss_ce: 0.0267, aux.acc_seg: 96.6677, loss: 0.0676 2022-05-06 08:55:17,440 - mmseg - INFO - Iter [52550/80000] lr: 4.927e-07, eta: 4:32:33, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0450, decode.acc_seg: 97.5354, aux.loss_ce: 0.0289, aux.acc_seg: 96.3355, loss: 0.0739 2022-05-06 08:55:43,932 - mmseg - INFO - Iter [52600/80000] lr: 4.918e-07, eta: 4:32:02, time: 0.530, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0431, decode.acc_seg: 97.7170, aux.loss_ce: 0.0273, aux.acc_seg: 96.6009, loss: 0.0704 2022-05-06 08:56:10,381 - mmseg - INFO - Iter [52650/80000] lr: 4.909e-07, eta: 4:31:30, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0450, decode.acc_seg: 97.5627, aux.loss_ce: 0.0281, aux.acc_seg: 96.5300, loss: 0.0731 2022-05-06 08:56:36,884 - mmseg - INFO - Iter [52700/80000] lr: 4.900e-07, eta: 4:30:59, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0434, decode.acc_seg: 97.6071, aux.loss_ce: 0.0279, aux.acc_seg: 96.4673, loss: 0.0713 2022-05-06 08:57:06,532 - mmseg - INFO - Iter [52750/80000] lr: 4.891e-07, eta: 4:30:29, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6808, aux.loss_ce: 0.0283, aux.acc_seg: 96.4988, loss: 0.0715 2022-05-06 08:57:33,428 - mmseg - INFO - Iter [52800/80000] lr: 4.882e-07, eta: 4:29:58, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.8603, aux.loss_ce: 0.0249, aux.acc_seg: 96.7568, loss: 0.0629 2022-05-06 08:57:59,963 - mmseg - INFO - Iter [52850/80000] lr: 4.873e-07, eta: 4:29:26, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0444, decode.acc_seg: 97.5542, aux.loss_ce: 0.0286, aux.acc_seg: 96.3338, loss: 0.0731 2022-05-06 08:58:26,796 - mmseg - INFO - Iter [52900/80000] lr: 4.864e-07, eta: 4:28:55, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0456, decode.acc_seg: 97.5001, aux.loss_ce: 0.0296, aux.acc_seg: 96.2752, loss: 0.0752 2022-05-06 08:58:53,414 - mmseg - INFO - Iter [52950/80000] lr: 4.855e-07, eta: 4:28:24, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.7102, aux.loss_ce: 0.0278, aux.acc_seg: 96.5662, loss: 0.0706 2022-05-06 08:59:20,543 - mmseg - INFO - Saving checkpoint at 53000 iterations 2022-05-06 08:59:43,172 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 08:59:43,180 - mmseg - INFO - Iter [53000/80000] lr: 4.846e-07, eta: 4:28:04, time: 0.993, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0414, decode.acc_seg: 97.7052, aux.loss_ce: 0.0270, aux.acc_seg: 96.5825, loss: 0.0683 2022-05-06 09:00:12,905 - mmseg - INFO - Iter [53050/80000] lr: 4.837e-07, eta: 4:27:34, time: 0.597, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.6306, aux.loss_ce: 0.0294, aux.acc_seg: 96.4393, loss: 0.0745 2022-05-06 09:00:39,916 - mmseg - INFO - Iter [53100/80000] lr: 4.828e-07, eta: 4:27:03, time: 0.541, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0436, decode.acc_seg: 97.6601, aux.loss_ce: 0.0286, aux.acc_seg: 96.4333, loss: 0.0722 2022-05-06 09:01:06,767 - mmseg - INFO - Iter [53150/80000] lr: 4.819e-07, eta: 4:26:32, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.7634, aux.loss_ce: 0.0283, aux.acc_seg: 96.5141, loss: 0.0703 2022-05-06 09:01:33,434 - mmseg - INFO - Iter [53200/80000] lr: 4.810e-07, eta: 4:26:00, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0414, decode.acc_seg: 97.7033, aux.loss_ce: 0.0265, aux.acc_seg: 96.6280, loss: 0.0679 2022-05-06 09:02:00,158 - mmseg - INFO - Iter [53250/80000] lr: 4.801e-07, eta: 4:25:29, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5713, aux.loss_ce: 0.0293, aux.acc_seg: 96.4053, loss: 0.0751 2022-05-06 09:02:26,875 - mmseg - INFO - Iter [53300/80000] lr: 4.792e-07, eta: 4:24:58, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6533, aux.loss_ce: 0.0279, aux.acc_seg: 96.4729, loss: 0.0710 2022-05-06 09:02:53,574 - mmseg - INFO - Iter [53350/80000] lr: 4.783e-07, eta: 4:24:27, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6595, aux.loss_ce: 0.0280, aux.acc_seg: 96.4827, loss: 0.0712 2022-05-06 09:03:22,769 - mmseg - INFO - Iter [53400/80000] lr: 4.774e-07, eta: 4:23:57, time: 0.584, data_time: 0.048, memory: 58091, decode.loss_ce: 0.0453, decode.acc_seg: 97.5776, aux.loss_ce: 0.0297, aux.acc_seg: 96.3072, loss: 0.0750 2022-05-06 09:03:49,949 - mmseg - INFO - Iter [53450/80000] lr: 4.765e-07, eta: 4:23:25, time: 0.544, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0454, decode.acc_seg: 97.5740, aux.loss_ce: 0.0287, aux.acc_seg: 96.4430, loss: 0.0742 2022-05-06 09:04:16,736 - mmseg - INFO - Iter [53500/80000] lr: 4.756e-07, eta: 4:22:54, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.6805, aux.loss_ce: 0.0284, aux.acc_seg: 96.5683, loss: 0.0726 2022-05-06 09:04:44,074 - mmseg - INFO - Iter [53550/80000] lr: 4.747e-07, eta: 4:22:23, time: 0.547, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.5411, aux.loss_ce: 0.0281, aux.acc_seg: 96.4111, loss: 0.0732 2022-05-06 09:05:10,578 - mmseg - INFO - Iter [53600/80000] lr: 4.738e-07, eta: 4:21:52, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0407, decode.acc_seg: 97.7804, aux.loss_ce: 0.0262, aux.acc_seg: 96.7032, loss: 0.0669 2022-05-06 09:05:37,077 - mmseg - INFO - Iter [53650/80000] lr: 4.729e-07, eta: 4:21:21, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.5428, aux.loss_ce: 0.0294, aux.acc_seg: 96.2871, loss: 0.0745 2022-05-06 09:06:06,273 - mmseg - INFO - Iter [53700/80000] lr: 4.720e-07, eta: 4:20:50, time: 0.584, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.8481, aux.loss_ce: 0.0263, aux.acc_seg: 96.7830, loss: 0.0669 2022-05-06 09:06:32,947 - mmseg - INFO - Iter [53750/80000] lr: 4.711e-07, eta: 4:20:19, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.6024, aux.loss_ce: 0.0286, aux.acc_seg: 96.4295, loss: 0.0728 2022-05-06 09:06:59,717 - mmseg - INFO - Iter [53800/80000] lr: 4.702e-07, eta: 4:19:48, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.6738, aux.loss_ce: 0.0270, aux.acc_seg: 96.4921, loss: 0.0681 2022-05-06 09:07:26,149 - mmseg - INFO - Iter [53850/80000] lr: 4.693e-07, eta: 4:19:17, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0484, decode.acc_seg: 97.4654, aux.loss_ce: 0.0307, aux.acc_seg: 96.2600, loss: 0.0791 2022-05-06 09:07:52,897 - mmseg - INFO - Iter [53900/80000] lr: 4.684e-07, eta: 4:18:45, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0477, decode.acc_seg: 97.4802, aux.loss_ce: 0.0307, aux.acc_seg: 96.2647, loss: 0.0784 2022-05-06 09:08:19,529 - mmseg - INFO - Iter [53950/80000] lr: 4.675e-07, eta: 4:18:14, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0431, decode.acc_seg: 97.5139, aux.loss_ce: 0.0267, aux.acc_seg: 96.4258, loss: 0.0698 2022-05-06 09:08:48,700 - mmseg - INFO - Saving checkpoint at 54000 iterations 2022-05-06 09:09:10,011 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 09:09:10,024 - mmseg - INFO - Iter [54000/80000] lr: 4.667e-07, eta: 4:17:54, time: 1.006, data_time: 0.051, memory: 58091, decode.loss_ce: 0.0431, decode.acc_seg: 97.6867, aux.loss_ce: 0.0281, aux.acc_seg: 96.5028, loss: 0.0712 2022-05-06 09:09:37,167 - mmseg - INFO - Iter [54050/80000] lr: 4.658e-07, eta: 4:17:23, time: 0.547, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0422, decode.acc_seg: 97.7261, aux.loss_ce: 0.0271, aux.acc_seg: 96.6059, loss: 0.0693 2022-05-06 09:10:04,150 - mmseg - INFO - Iter [54100/80000] lr: 4.649e-07, eta: 4:16:52, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0420, decode.acc_seg: 97.7333, aux.loss_ce: 0.0269, aux.acc_seg: 96.6246, loss: 0.0689 2022-05-06 09:10:30,778 - mmseg - INFO - Iter [54150/80000] lr: 4.640e-07, eta: 4:16:21, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.7985, aux.loss_ce: 0.0267, aux.acc_seg: 96.6422, loss: 0.0673 2022-05-06 09:10:57,587 - mmseg - INFO - Iter [54200/80000] lr: 4.631e-07, eta: 4:15:50, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0430, decode.acc_seg: 97.6893, aux.loss_ce: 0.0279, aux.acc_seg: 96.5158, loss: 0.0709 2022-05-06 09:11:24,497 - mmseg - INFO - Iter [54250/80000] lr: 4.622e-07, eta: 4:15:19, time: 0.538, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6546, aux.loss_ce: 0.0280, aux.acc_seg: 96.4533, loss: 0.0711 2022-05-06 09:11:53,475 - mmseg - INFO - Iter [54300/80000] lr: 4.613e-07, eta: 4:14:49, time: 0.579, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0457, decode.acc_seg: 97.5029, aux.loss_ce: 0.0294, aux.acc_seg: 96.2569, loss: 0.0751 2022-05-06 09:12:20,188 - mmseg - INFO - Iter [54350/80000] lr: 4.604e-07, eta: 4:14:18, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0410, decode.acc_seg: 97.7784, aux.loss_ce: 0.0269, aux.acc_seg: 96.6454, loss: 0.0679 2022-05-06 09:12:46,641 - mmseg - INFO - Iter [54400/80000] lr: 4.595e-07, eta: 4:13:46, time: 0.531, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.8216, aux.loss_ce: 0.0271, aux.acc_seg: 96.6473, loss: 0.0681 2022-05-06 09:13:13,494 - mmseg - INFO - Iter [54450/80000] lr: 4.586e-07, eta: 4:13:15, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.5564, aux.loss_ce: 0.0295, aux.acc_seg: 96.3269, loss: 0.0753 2022-05-06 09:13:40,228 - mmseg - INFO - Iter [54500/80000] lr: 4.577e-07, eta: 4:12:44, time: 0.535, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0437, decode.acc_seg: 97.6621, aux.loss_ce: 0.0279, aux.acc_seg: 96.4785, loss: 0.0716 2022-05-06 09:14:06,807 - mmseg - INFO - Iter [54550/80000] lr: 4.568e-07, eta: 4:12:13, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0433, decode.acc_seg: 97.6114, aux.loss_ce: 0.0289, aux.acc_seg: 96.3440, loss: 0.0722 2022-05-06 09:14:33,385 - mmseg - INFO - Iter [54600/80000] lr: 4.559e-07, eta: 4:11:42, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0437, decode.acc_seg: 97.6842, aux.loss_ce: 0.0283, aux.acc_seg: 96.5290, loss: 0.0720 2022-05-06 09:15:02,861 - mmseg - INFO - Iter [54650/80000] lr: 4.550e-07, eta: 4:11:12, time: 0.590, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8215, aux.loss_ce: 0.0260, aux.acc_seg: 96.7228, loss: 0.0658 2022-05-06 09:15:29,512 - mmseg - INFO - Iter [54700/80000] lr: 4.541e-07, eta: 4:10:41, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.5366, aux.loss_ce: 0.0287, aux.acc_seg: 96.3110, loss: 0.0728 2022-05-06 09:15:55,860 - mmseg - INFO - Iter [54750/80000] lr: 4.532e-07, eta: 4:10:09, time: 0.527, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0462, decode.acc_seg: 97.5830, aux.loss_ce: 0.0301, aux.acc_seg: 96.3334, loss: 0.0763 2022-05-06 09:16:23,206 - mmseg - INFO - Iter [54800/80000] lr: 4.523e-07, eta: 4:09:39, time: 0.547, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0420, decode.acc_seg: 97.7547, aux.loss_ce: 0.0270, aux.acc_seg: 96.6569, loss: 0.0690 2022-05-06 09:16:50,265 - mmseg - INFO - Iter [54850/80000] lr: 4.514e-07, eta: 4:09:08, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0497, decode.acc_seg: 97.3588, aux.loss_ce: 0.0321, aux.acc_seg: 96.0880, loss: 0.0818 2022-05-06 09:17:16,717 - mmseg - INFO - Iter [54900/80000] lr: 4.505e-07, eta: 4:08:36, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0415, decode.acc_seg: 97.7233, aux.loss_ce: 0.0270, aux.acc_seg: 96.5893, loss: 0.0685 2022-05-06 09:17:45,898 - mmseg - INFO - Iter [54950/80000] lr: 4.496e-07, eta: 4:08:06, time: 0.582, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0424, decode.acc_seg: 97.6557, aux.loss_ce: 0.0273, aux.acc_seg: 96.4488, loss: 0.0697 2022-05-06 09:18:12,400 - mmseg - INFO - Saving checkpoint at 55000 iterations 2022-05-06 09:18:34,222 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 09:18:34,227 - mmseg - INFO - Iter [55000/80000] lr: 4.487e-07, eta: 4:07:45, time: 0.966, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0423, decode.acc_seg: 97.6951, aux.loss_ce: 0.0275, aux.acc_seg: 96.5444, loss: 0.0699 2022-05-06 09:19:01,388 - mmseg - INFO - Iter [55050/80000] lr: 4.478e-07, eta: 4:07:14, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0434, decode.acc_seg: 97.6328, aux.loss_ce: 0.0283, aux.acc_seg: 96.4595, loss: 0.0717 2022-05-06 09:19:27,861 - mmseg - INFO - Iter [55100/80000] lr: 4.469e-07, eta: 4:06:43, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8332, aux.loss_ce: 0.0264, aux.acc_seg: 96.7203, loss: 0.0671 2022-05-06 09:19:54,897 - mmseg - INFO - Iter [55150/80000] lr: 4.460e-07, eta: 4:06:12, time: 0.541, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0447, decode.acc_seg: 97.6700, aux.loss_ce: 0.0291, aux.acc_seg: 96.4632, loss: 0.0739 2022-05-06 09:20:21,912 - mmseg - INFO - Iter [55200/80000] lr: 4.451e-07, eta: 4:05:41, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0423, decode.acc_seg: 97.7644, aux.loss_ce: 0.0271, aux.acc_seg: 96.6661, loss: 0.0694 2022-05-06 09:20:51,246 - mmseg - INFO - Iter [55250/80000] lr: 4.442e-07, eta: 4:05:11, time: 0.587, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0467, decode.acc_seg: 97.5545, aux.loss_ce: 0.0304, aux.acc_seg: 96.3169, loss: 0.0771 2022-05-06 09:21:17,801 - mmseg - INFO - Iter [55300/80000] lr: 4.433e-07, eta: 4:04:40, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0449, decode.acc_seg: 97.5882, aux.loss_ce: 0.0286, aux.acc_seg: 96.4471, loss: 0.0736 2022-05-06 09:21:44,613 - mmseg - INFO - Iter [55350/80000] lr: 4.424e-07, eta: 4:04:09, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0422, decode.acc_seg: 97.7421, aux.loss_ce: 0.0277, aux.acc_seg: 96.5673, loss: 0.0699 2022-05-06 09:22:11,735 - mmseg - INFO - Iter [55400/80000] lr: 4.415e-07, eta: 4:03:38, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0414, decode.acc_seg: 97.8182, aux.loss_ce: 0.0271, aux.acc_seg: 96.6769, loss: 0.0685 2022-05-06 09:22:38,239 - mmseg - INFO - Iter [55450/80000] lr: 4.406e-07, eta: 4:03:07, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.7581, aux.loss_ce: 0.0276, aux.acc_seg: 96.5740, loss: 0.0694 2022-05-06 09:23:04,958 - mmseg - INFO - Iter [55500/80000] lr: 4.397e-07, eta: 4:02:36, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0446, decode.acc_seg: 97.5292, aux.loss_ce: 0.0290, aux.acc_seg: 96.2961, loss: 0.0735 2022-05-06 09:23:34,016 - mmseg - INFO - Iter [55550/80000] lr: 4.388e-07, eta: 4:02:06, time: 0.581, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8069, aux.loss_ce: 0.0264, aux.acc_seg: 96.6828, loss: 0.0670 2022-05-06 09:24:00,904 - mmseg - INFO - Iter [55600/80000] lr: 4.379e-07, eta: 4:01:35, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.8147, aux.loss_ce: 0.0258, aux.acc_seg: 96.7392, loss: 0.0658 2022-05-06 09:24:27,716 - mmseg - INFO - Iter [55650/80000] lr: 4.370e-07, eta: 4:01:04, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8087, aux.loss_ce: 0.0263, aux.acc_seg: 96.7258, loss: 0.0669 2022-05-06 09:24:54,523 - mmseg - INFO - Iter [55700/80000] lr: 4.361e-07, eta: 4:00:33, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0439, decode.acc_seg: 97.6337, aux.loss_ce: 0.0286, aux.acc_seg: 96.4188, loss: 0.0725 2022-05-06 09:25:21,166 - mmseg - INFO - Iter [55750/80000] lr: 4.352e-07, eta: 4:00:02, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.7106, aux.loss_ce: 0.0271, aux.acc_seg: 96.5593, loss: 0.0689 2022-05-06 09:25:47,814 - mmseg - INFO - Iter [55800/80000] lr: 4.343e-07, eta: 3:59:31, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0438, decode.acc_seg: 97.5576, aux.loss_ce: 0.0285, aux.acc_seg: 96.3042, loss: 0.0723 2022-05-06 09:26:16,999 - mmseg - INFO - Iter [55850/80000] lr: 4.334e-07, eta: 3:59:01, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.6318, aux.loss_ce: 0.0275, aux.acc_seg: 96.3988, loss: 0.0693 2022-05-06 09:26:43,567 - mmseg - INFO - Iter [55900/80000] lr: 4.326e-07, eta: 3:58:30, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0413, decode.acc_seg: 97.6937, aux.loss_ce: 0.0264, aux.acc_seg: 96.5576, loss: 0.0678 2022-05-06 09:27:10,002 - mmseg - INFO - Iter [55950/80000] lr: 4.317e-07, eta: 3:57:59, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0474, decode.acc_seg: 97.4298, aux.loss_ce: 0.0304, aux.acc_seg: 96.1813, loss: 0.0778 2022-05-06 09:27:36,820 - mmseg - INFO - Saving checkpoint at 56000 iterations 2022-05-06 09:27:58,815 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 09:27:58,817 - mmseg - INFO - Iter [56000/80000] lr: 4.308e-07, eta: 3:57:38, time: 0.974, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.7121, aux.loss_ce: 0.0272, aux.acc_seg: 96.5604, loss: 0.0691 2022-05-06 09:32:09,229 - mmseg - INFO - per class results: 2022-05-06 09:32:09,236 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 92.88 | 97.47 | | bag | 45.59 | 60.52 | | bed | 34.55 | 45.04 | | bedclothes | 44.7 | 64.91 | | bench | 32.69 | 40.22 | | bicycle | 83.91 | 93.97 | | bird | 94.51 | 98.1 | | boat | 85.57 | 91.96 | | book | 60.9 | 74.1 | | bottle | 88.62 | 97.09 | | building | 68.55 | 80.83 | | bus | 94.47 | 97.59 | | cabinet | 51.18 | 65.04 | | car | 93.78 | 97.0 | | cat | 93.75 | 98.46 | | ceiling | 60.52 | 74.68 | | chair | 65.67 | 78.78 | | cloth | 27.3 | 36.04 | | computer | 61.81 | 71.82 | | cow | 95.79 | 98.3 | | cup | 47.55 | 66.64 | | curtain | 59.8 | 73.48 | | dog | 92.04 | 97.54 | | door | 34.97 | 49.91 | | fence | 46.61 | 61.4 | | floor | 76.73 | 89.25 | | flower | 35.87 | 46.65 | | food | 41.78 | 50.45 | | grass | 82.97 | 92.53 | | ground | 57.92 | 72.79 | | horse | 94.72 | 97.81 | | keyboard | 91.4 | 94.53 | | light | 59.08 | 73.13 | | motorbike | 90.6 | 97.06 | | mountain | 58.62 | 73.96 | | mouse | 79.07 | 93.86 | | person | 90.45 | 97.05 | | plate | 30.46 | 40.75 | | platform | 58.95 | 73.69 | | pottedplant | 82.0 | 89.83 | | road | 52.4 | 67.65 | | rock | 56.86 | 64.63 | | sheep | 95.1 | 98.32 | | shelves | 35.51 | 46.96 | | sidewalk | 33.63 | 48.48 | | sign | 51.82 | 58.69 | | sky | 94.76 | 97.56 | | snow | 76.03 | 90.71 | | sofa | 61.76 | 70.95 | | table | 73.28 | 85.49 | | track | 73.14 | 84.85 | | train | 93.28 | 97.22 | | tree | 81.61 | 90.22 | | truck | 52.1 | 59.92 | | tvmonitor | 90.61 | 94.01 | | wall | 74.27 | 86.41 | | water | 92.17 | 96.29 | | window | 47.59 | 61.9 | | wood | 24.7 | 31.47 | +-------------+-------+-------+ 2022-05-06 09:32:09,236 - mmseg - INFO - Summary: 2022-05-06 09:32:09,236 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.67 | 66.93 | 76.71 | +-------+-------+-------+ 2022-05-06 09:32:09,239 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_48000.pth was removed 2022-05-06 09:32:29,977 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_56000.pth. 2022-05-06 09:32:29,989 - mmseg - INFO - Best mIoU is 0.6693 at 56000 iter. 2022-05-06 09:32:30,014 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 09:32:30,015 - mmseg - INFO - Iter(val) [638] aAcc: 0.8667, mIoU: 0.6693, mAcc: 0.7671, IoU.aeroplane: 0.9288, IoU.bag: 0.4559, IoU.bed: 0.3455, IoU.bedclothes: 0.4470, IoU.bench: 0.3269, IoU.bicycle: 0.8391, IoU.bird: 0.9451, IoU.boat: 0.8557, IoU.book: 0.6090, IoU.bottle: 0.8862, IoU.building: 0.6855, IoU.bus: 0.9447, IoU.cabinet: 0.5118, IoU.car: 0.9378, IoU.cat: 0.9375, IoU.ceiling: 0.6052, IoU.chair: 0.6567, IoU.cloth: 0.2730, IoU.computer: 0.6181, IoU.cow: 0.9579, IoU.cup: 0.4755, IoU.curtain: 0.5980, IoU.dog: 0.9204, IoU.door: 0.3497, IoU.fence: 0.4661, IoU.floor: 0.7673, IoU.flower: 0.3587, IoU.food: 0.4178, IoU.grass: 0.8297, IoU.ground: 0.5792, IoU.horse: 0.9472, IoU.keyboard: 0.9140, IoU.light: 0.5908, IoU.motorbike: 0.9060, IoU.mountain: 0.5862, IoU.mouse: 0.7907, IoU.person: 0.9045, IoU.plate: 0.3046, IoU.platform: 0.5895, IoU.pottedplant: 0.8200, IoU.road: 0.5240, IoU.rock: 0.5686, IoU.sheep: 0.9510, IoU.shelves: 0.3551, IoU.sidewalk: 0.3363, IoU.sign: 0.5182, IoU.sky: 0.9476, IoU.snow: 0.7603, IoU.sofa: 0.6176, IoU.table: 0.7328, IoU.track: 0.7314, IoU.train: 0.9328, IoU.tree: 0.8161, IoU.truck: 0.5210, IoU.tvmonitor: 0.9061, IoU.wall: 0.7427, IoU.water: 0.9217, IoU.window: 0.4759, IoU.wood: 0.2470, Acc.aeroplane: 0.9747, Acc.bag: 0.6052, Acc.bed: 0.4504, Acc.bedclothes: 0.6491, Acc.bench: 0.4022, Acc.bicycle: 0.9397, Acc.bird: 0.9810, Acc.boat: 0.9196, Acc.book: 0.7410, Acc.bottle: 0.9709, Acc.building: 0.8083, Acc.bus: 0.9759, Acc.cabinet: 0.6504, Acc.car: 0.9700, Acc.cat: 0.9846, Acc.ceiling: 0.7468, Acc.chair: 0.7878, Acc.cloth: 0.3604, Acc.computer: 0.7182, Acc.cow: 0.9830, Acc.cup: 0.6664, Acc.curtain: 0.7348, Acc.dog: 0.9754, Acc.door: 0.4991, Acc.fence: 0.6140, Acc.floor: 0.8925, Acc.flower: 0.4665, Acc.food: 0.5045, Acc.grass: 0.9253, Acc.ground: 0.7279, Acc.horse: 0.9781, Acc.keyboard: 0.9453, Acc.light: 0.7313, Acc.motorbike: 0.9706, Acc.mountain: 0.7396, Acc.mouse: 0.9386, Acc.person: 0.9705, Acc.plate: 0.4075, Acc.platform: 0.7369, Acc.pottedplant: 0.8983, Acc.road: 0.6765, Acc.rock: 0.6463, Acc.sheep: 0.9832, Acc.shelves: 0.4696, Acc.sidewalk: 0.4848, Acc.sign: 0.5869, Acc.sky: 0.9756, Acc.snow: 0.9071, Acc.sofa: 0.7095, Acc.table: 0.8549, Acc.track: 0.8485, Acc.train: 0.9722, Acc.tree: 0.9022, Acc.truck: 0.5992, Acc.tvmonitor: 0.9401, Acc.wall: 0.8641, Acc.water: 0.9629, Acc.window: 0.6190, Acc.wood: 0.3147 2022-05-06 09:32:57,468 - mmseg - INFO - Iter [56050/80000] lr: 4.299e-07, eta: 3:59:03, time: 5.976, data_time: 5.432, memory: 58091, decode.loss_ce: 0.0452, decode.acc_seg: 97.5795, aux.loss_ce: 0.0289, aux.acc_seg: 96.4207, loss: 0.0741 2022-05-06 09:33:24,049 - mmseg - INFO - Iter [56100/80000] lr: 4.290e-07, eta: 3:58:31, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.8754, aux.loss_ce: 0.0259, aux.acc_seg: 96.7558, loss: 0.0655 2022-05-06 09:33:51,272 - mmseg - INFO - Iter [56150/80000] lr: 4.281e-07, eta: 3:58:00, time: 0.546, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0424, decode.acc_seg: 97.7178, aux.loss_ce: 0.0275, aux.acc_seg: 96.5758, loss: 0.0699 2022-05-06 09:34:20,722 - mmseg - INFO - Iter [56200/80000] lr: 4.272e-07, eta: 3:57:30, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0434, decode.acc_seg: 97.6438, aux.loss_ce: 0.0282, aux.acc_seg: 96.4453, loss: 0.0716 2022-05-06 09:34:47,337 - mmseg - INFO - Iter [56250/80000] lr: 4.263e-07, eta: 3:56:59, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0429, decode.acc_seg: 97.6584, aux.loss_ce: 0.0278, aux.acc_seg: 96.5191, loss: 0.0706 2022-05-06 09:35:14,130 - mmseg - INFO - Iter [56300/80000] lr: 4.254e-07, eta: 3:56:28, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.7726, aux.loss_ce: 0.0269, aux.acc_seg: 96.6371, loss: 0.0681 2022-05-06 09:35:40,546 - mmseg - INFO - Iter [56350/80000] lr: 4.245e-07, eta: 3:55:56, time: 0.530, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.8406, aux.loss_ce: 0.0259, aux.acc_seg: 96.7958, loss: 0.0660 2022-05-06 09:36:07,283 - mmseg - INFO - Iter [56400/80000] lr: 4.236e-07, eta: 3:55:25, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0427, decode.acc_seg: 97.7246, aux.loss_ce: 0.0281, aux.acc_seg: 96.5051, loss: 0.0708 2022-05-06 09:36:34,320 - mmseg - INFO - Iter [56450/80000] lr: 4.227e-07, eta: 3:54:54, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0483, decode.acc_seg: 97.4287, aux.loss_ce: 0.0302, aux.acc_seg: 96.2452, loss: 0.0784 2022-05-06 09:37:03,670 - mmseg - INFO - Iter [56500/80000] lr: 4.218e-07, eta: 3:54:24, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.7173, aux.loss_ce: 0.0259, aux.acc_seg: 96.5930, loss: 0.0663 2022-05-06 09:37:30,270 - mmseg - INFO - Iter [56550/80000] lr: 4.209e-07, eta: 3:53:52, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0438, decode.acc_seg: 97.6777, aux.loss_ce: 0.0281, aux.acc_seg: 96.5285, loss: 0.0719 2022-05-06 09:37:57,259 - mmseg - INFO - Iter [56600/80000] lr: 4.200e-07, eta: 3:53:21, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0444, decode.acc_seg: 97.6155, aux.loss_ce: 0.0288, aux.acc_seg: 96.4697, loss: 0.0731 2022-05-06 09:38:23,977 - mmseg - INFO - Iter [56650/80000] lr: 4.191e-07, eta: 3:52:50, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.7670, aux.loss_ce: 0.0272, aux.acc_seg: 96.6972, loss: 0.0697 2022-05-06 09:38:50,576 - mmseg - INFO - Iter [56700/80000] lr: 4.182e-07, eta: 3:52:19, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0459, decode.acc_seg: 97.5415, aux.loss_ce: 0.0296, aux.acc_seg: 96.3699, loss: 0.0755 2022-05-06 09:39:17,229 - mmseg - INFO - Iter [56750/80000] lr: 4.173e-07, eta: 3:51:48, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0425, decode.acc_seg: 97.7940, aux.loss_ce: 0.0280, aux.acc_seg: 96.6223, loss: 0.0706 2022-05-06 09:39:46,488 - mmseg - INFO - Iter [56800/80000] lr: 4.164e-07, eta: 3:51:17, time: 0.585, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0423, decode.acc_seg: 97.7299, aux.loss_ce: 0.0278, aux.acc_seg: 96.5525, loss: 0.0701 2022-05-06 09:40:13,427 - mmseg - INFO - Iter [56850/80000] lr: 4.155e-07, eta: 3:50:46, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0421, decode.acc_seg: 97.7668, aux.loss_ce: 0.0277, aux.acc_seg: 96.5880, loss: 0.0698 2022-05-06 09:40:39,786 - mmseg - INFO - Iter [56900/80000] lr: 4.146e-07, eta: 3:50:15, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0409, decode.acc_seg: 97.8093, aux.loss_ce: 0.0269, aux.acc_seg: 96.6842, loss: 0.0678 2022-05-06 09:41:06,196 - mmseg - INFO - Iter [56950/80000] lr: 4.137e-07, eta: 3:49:44, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0417, decode.acc_seg: 97.8215, aux.loss_ce: 0.0269, aux.acc_seg: 96.7227, loss: 0.0685 2022-05-06 09:41:33,118 - mmseg - INFO - Saving checkpoint at 57000 iterations 2022-05-06 09:41:54,149 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 09:41:54,156 - mmseg - INFO - Iter [57000/80000] lr: 4.128e-07, eta: 3:49:21, time: 0.957, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0430, decode.acc_seg: 97.7090, aux.loss_ce: 0.0282, aux.acc_seg: 96.5241, loss: 0.0711 2022-05-06 09:42:21,291 - mmseg - INFO - Iter [57050/80000] lr: 4.119e-07, eta: 3:48:50, time: 0.545, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.7049, aux.loss_ce: 0.0276, aux.acc_seg: 96.5796, loss: 0.0702 2022-05-06 09:42:50,611 - mmseg - INFO - Iter [57100/80000] lr: 4.110e-07, eta: 3:48:20, time: 0.586, data_time: 0.060, memory: 58091, decode.loss_ce: 0.0434, decode.acc_seg: 97.6036, aux.loss_ce: 0.0279, aux.acc_seg: 96.4651, loss: 0.0713 2022-05-06 09:43:17,197 - mmseg - INFO - Iter [57150/80000] lr: 4.101e-07, eta: 3:47:49, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0417, decode.acc_seg: 97.7486, aux.loss_ce: 0.0272, aux.acc_seg: 96.5945, loss: 0.0689 2022-05-06 09:43:44,039 - mmseg - INFO - Iter [57200/80000] lr: 4.092e-07, eta: 3:47:17, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0416, decode.acc_seg: 97.7198, aux.loss_ce: 0.0273, aux.acc_seg: 96.5387, loss: 0.0689 2022-05-06 09:44:11,121 - mmseg - INFO - Iter [57250/80000] lr: 4.083e-07, eta: 3:46:46, time: 0.542, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0421, decode.acc_seg: 97.7235, aux.loss_ce: 0.0275, aux.acc_seg: 96.5694, loss: 0.0696 2022-05-06 09:44:37,610 - mmseg - INFO - Iter [57300/80000] lr: 4.074e-07, eta: 3:46:15, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0434, decode.acc_seg: 97.6632, aux.loss_ce: 0.0283, aux.acc_seg: 96.4788, loss: 0.0717 2022-05-06 09:45:04,030 - mmseg - INFO - Iter [57350/80000] lr: 4.065e-07, eta: 3:45:44, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0409, decode.acc_seg: 97.7550, aux.loss_ce: 0.0264, aux.acc_seg: 96.6199, loss: 0.0673 2022-05-06 09:45:30,881 - mmseg - INFO - Iter [57400/80000] lr: 4.056e-07, eta: 3:45:13, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6727, aux.loss_ce: 0.0283, aux.acc_seg: 96.4780, loss: 0.0715 2022-05-06 09:46:00,542 - mmseg - INFO - Iter [57450/80000] lr: 4.047e-07, eta: 3:44:43, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0429, decode.acc_seg: 97.6903, aux.loss_ce: 0.0283, aux.acc_seg: 96.4907, loss: 0.0713 2022-05-06 09:46:27,162 - mmseg - INFO - Iter [57500/80000] lr: 4.038e-07, eta: 3:44:12, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6915, aux.loss_ce: 0.0281, aux.acc_seg: 96.5344, loss: 0.0713 2022-05-06 09:46:53,673 - mmseg - INFO - Iter [57550/80000] lr: 4.029e-07, eta: 3:43:40, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.7284, aux.loss_ce: 0.0276, aux.acc_seg: 96.5808, loss: 0.0704 2022-05-06 09:47:20,432 - mmseg - INFO - Iter [57600/80000] lr: 4.020e-07, eta: 3:43:09, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0385, decode.acc_seg: 97.8513, aux.loss_ce: 0.0253, aux.acc_seg: 96.7563, loss: 0.0638 2022-05-06 09:47:47,001 - mmseg - INFO - Iter [57650/80000] lr: 4.011e-07, eta: 3:42:38, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8858, aux.loss_ce: 0.0258, aux.acc_seg: 96.6810, loss: 0.0643 2022-05-06 09:48:13,943 - mmseg - INFO - Iter [57700/80000] lr: 4.002e-07, eta: 3:42:07, time: 0.539, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0412, decode.acc_seg: 97.7745, aux.loss_ce: 0.0271, aux.acc_seg: 96.6089, loss: 0.0683 2022-05-06 09:48:43,086 - mmseg - INFO - Iter [57750/80000] lr: 3.993e-07, eta: 3:41:37, time: 0.583, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.7961, aux.loss_ce: 0.0265, aux.acc_seg: 96.6322, loss: 0.0664 2022-05-06 09:49:09,721 - mmseg - INFO - Iter [57800/80000] lr: 3.985e-07, eta: 3:41:06, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0442, decode.acc_seg: 97.5252, aux.loss_ce: 0.0286, aux.acc_seg: 96.2728, loss: 0.0728 2022-05-06 09:49:36,420 - mmseg - INFO - Iter [57850/80000] lr: 3.976e-07, eta: 3:40:35, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0425, decode.acc_seg: 97.6317, aux.loss_ce: 0.0272, aux.acc_seg: 96.4750, loss: 0.0697 2022-05-06 09:50:02,947 - mmseg - INFO - Iter [57900/80000] lr: 3.967e-07, eta: 3:40:03, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.6675, aux.loss_ce: 0.0279, aux.acc_seg: 96.4438, loss: 0.0706 2022-05-06 09:50:29,318 - mmseg - INFO - Iter [57950/80000] lr: 3.958e-07, eta: 3:39:32, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8316, aux.loss_ce: 0.0270, aux.acc_seg: 96.6725, loss: 0.0676 2022-05-06 09:50:56,017 - mmseg - INFO - Saving checkpoint at 58000 iterations 2022-05-06 09:51:16,646 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 09:51:16,649 - mmseg - INFO - Iter [58000/80000] lr: 3.949e-07, eta: 3:39:09, time: 0.944, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0435, decode.acc_seg: 97.7015, aux.loss_ce: 0.0283, aux.acc_seg: 96.5592, loss: 0.0718 2022-05-06 09:51:46,165 - mmseg - INFO - Iter [58050/80000] lr: 3.940e-07, eta: 3:38:39, time: 0.591, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7987, aux.loss_ce: 0.0267, aux.acc_seg: 96.6766, loss: 0.0675 2022-05-06 09:52:13,013 - mmseg - INFO - Iter [58100/80000] lr: 3.931e-07, eta: 3:38:08, time: 0.539, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7760, aux.loss_ce: 0.0266, aux.acc_seg: 96.6663, loss: 0.0675 2022-05-06 09:52:39,793 - mmseg - INFO - Iter [58150/80000] lr: 3.922e-07, eta: 3:37:37, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0421, decode.acc_seg: 97.7555, aux.loss_ce: 0.0276, aux.acc_seg: 96.5203, loss: 0.0697 2022-05-06 09:53:06,251 - mmseg - INFO - Iter [58200/80000] lr: 3.913e-07, eta: 3:37:06, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.7688, aux.loss_ce: 0.0260, aux.acc_seg: 96.6533, loss: 0.0663 2022-05-06 09:53:32,964 - mmseg - INFO - Iter [58250/80000] lr: 3.904e-07, eta: 3:36:35, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0417, decode.acc_seg: 97.7429, aux.loss_ce: 0.0270, aux.acc_seg: 96.6230, loss: 0.0686 2022-05-06 09:53:59,413 - mmseg - INFO - Iter [58300/80000] lr: 3.895e-07, eta: 3:36:04, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.7824, aux.loss_ce: 0.0267, aux.acc_seg: 96.6092, loss: 0.0671 2022-05-06 09:54:28,424 - mmseg - INFO - Iter [58350/80000] lr: 3.886e-07, eta: 3:35:33, time: 0.580, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7716, aux.loss_ce: 0.0271, aux.acc_seg: 96.5484, loss: 0.0679 2022-05-06 09:54:55,281 - mmseg - INFO - Iter [58400/80000] lr: 3.877e-07, eta: 3:35:02, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0423, decode.acc_seg: 97.6628, aux.loss_ce: 0.0280, aux.acc_seg: 96.3993, loss: 0.0703 2022-05-06 09:55:21,673 - mmseg - INFO - Iter [58450/80000] lr: 3.868e-07, eta: 3:34:31, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0416, decode.acc_seg: 97.7521, aux.loss_ce: 0.0274, aux.acc_seg: 96.6033, loss: 0.0690 2022-05-06 09:55:48,175 - mmseg - INFO - Iter [58500/80000] lr: 3.859e-07, eta: 3:34:00, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0421, decode.acc_seg: 97.6897, aux.loss_ce: 0.0274, aux.acc_seg: 96.5272, loss: 0.0695 2022-05-06 09:56:15,098 - mmseg - INFO - Iter [58550/80000] lr: 3.850e-07, eta: 3:33:29, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8676, aux.loss_ce: 0.0259, aux.acc_seg: 96.7781, loss: 0.0657 2022-05-06 09:56:41,990 - mmseg - INFO - Iter [58600/80000] lr: 3.841e-07, eta: 3:32:58, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0415, decode.acc_seg: 97.6894, aux.loss_ce: 0.0268, aux.acc_seg: 96.5738, loss: 0.0683 2022-05-06 09:57:09,059 - mmseg - INFO - Iter [58650/80000] lr: 3.832e-07, eta: 3:32:27, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0435, decode.acc_seg: 97.6657, aux.loss_ce: 0.0281, aux.acc_seg: 96.4654, loss: 0.0715 2022-05-06 09:57:38,316 - mmseg - INFO - Iter [58700/80000] lr: 3.823e-07, eta: 3:31:57, time: 0.585, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0402, decode.acc_seg: 97.7662, aux.loss_ce: 0.0257, aux.acc_seg: 96.6445, loss: 0.0659 2022-05-06 09:58:05,056 - mmseg - INFO - Iter [58750/80000] lr: 3.814e-07, eta: 3:31:26, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.7943, aux.loss_ce: 0.0275, aux.acc_seg: 96.6268, loss: 0.0693 2022-05-06 09:58:31,422 - mmseg - INFO - Iter [58800/80000] lr: 3.805e-07, eta: 3:30:55, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0422, decode.acc_seg: 97.7134, aux.loss_ce: 0.0274, aux.acc_seg: 96.5795, loss: 0.0696 2022-05-06 09:58:57,980 - mmseg - INFO - Iter [58850/80000] lr: 3.796e-07, eta: 3:30:24, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.7370, aux.loss_ce: 0.0282, aux.acc_seg: 96.5555, loss: 0.0707 2022-05-06 09:59:24,604 - mmseg - INFO - Iter [58900/80000] lr: 3.787e-07, eta: 3:29:53, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.7088, aux.loss_ce: 0.0277, aux.acc_seg: 96.6242, loss: 0.0708 2022-05-06 09:59:51,210 - mmseg - INFO - Iter [58950/80000] lr: 3.778e-07, eta: 3:29:22, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0433, decode.acc_seg: 97.6944, aux.loss_ce: 0.0281, aux.acc_seg: 96.5808, loss: 0.0714 2022-05-06 10:00:20,730 - mmseg - INFO - Saving checkpoint at 59000 iterations 2022-05-06 10:00:41,893 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:00:41,895 - mmseg - INFO - Iter [59000/80000] lr: 3.769e-07, eta: 3:29:00, time: 1.012, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9246, aux.loss_ce: 0.0251, aux.acc_seg: 96.8519, loss: 0.0633 2022-05-06 10:01:09,114 - mmseg - INFO - Iter [59050/80000] lr: 3.760e-07, eta: 3:28:29, time: 0.546, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.6890, aux.loss_ce: 0.0275, aux.acc_seg: 96.5423, loss: 0.0702 2022-05-06 10:01:35,572 - mmseg - INFO - Iter [59100/80000] lr: 3.751e-07, eta: 3:27:58, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0436, decode.acc_seg: 97.6365, aux.loss_ce: 0.0282, aux.acc_seg: 96.4182, loss: 0.0718 2022-05-06 10:02:02,015 - mmseg - INFO - Iter [59150/80000] lr: 3.742e-07, eta: 3:27:27, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.7994, aux.loss_ce: 0.0259, aux.acc_seg: 96.6604, loss: 0.0659 2022-05-06 10:02:28,786 - mmseg - INFO - Iter [59200/80000] lr: 3.733e-07, eta: 3:26:56, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0440, decode.acc_seg: 97.6280, aux.loss_ce: 0.0277, aux.acc_seg: 96.5202, loss: 0.0717 2022-05-06 10:02:55,250 - mmseg - INFO - Iter [59250/80000] lr: 3.724e-07, eta: 3:26:25, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0417, decode.acc_seg: 97.7159, aux.loss_ce: 0.0269, aux.acc_seg: 96.6066, loss: 0.0686 2022-05-06 10:03:24,420 - mmseg - INFO - Iter [59300/80000] lr: 3.715e-07, eta: 3:25:55, time: 0.583, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.8434, aux.loss_ce: 0.0262, aux.acc_seg: 96.7403, loss: 0.0662 2022-05-06 10:03:50,998 - mmseg - INFO - Iter [59350/80000] lr: 3.706e-07, eta: 3:25:24, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9008, aux.loss_ce: 0.0256, aux.acc_seg: 96.7799, loss: 0.0643 2022-05-06 10:04:17,640 - mmseg - INFO - Iter [59400/80000] lr: 3.697e-07, eta: 3:24:53, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0415, decode.acc_seg: 97.7259, aux.loss_ce: 0.0275, aux.acc_seg: 96.5309, loss: 0.0690 2022-05-06 10:04:44,901 - mmseg - INFO - Iter [59450/80000] lr: 3.688e-07, eta: 3:24:22, time: 0.545, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0430, decode.acc_seg: 97.6569, aux.loss_ce: 0.0280, aux.acc_seg: 96.5066, loss: 0.0710 2022-05-06 10:05:11,863 - mmseg - INFO - Iter [59500/80000] lr: 3.679e-07, eta: 3:23:51, time: 0.539, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0391, decode.acc_seg: 97.8187, aux.loss_ce: 0.0257, aux.acc_seg: 96.6619, loss: 0.0648 2022-05-06 10:05:38,602 - mmseg - INFO - Iter [59550/80000] lr: 3.670e-07, eta: 3:23:20, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.8265, aux.loss_ce: 0.0270, aux.acc_seg: 96.6875, loss: 0.0680 2022-05-06 10:06:08,105 - mmseg - INFO - Iter [59600/80000] lr: 3.661e-07, eta: 3:22:50, time: 0.590, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.8289, aux.loss_ce: 0.0264, aux.acc_seg: 96.7041, loss: 0.0668 2022-05-06 10:06:34,847 - mmseg - INFO - Iter [59650/80000] lr: 3.652e-07, eta: 3:22:20, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0413, decode.acc_seg: 97.7672, aux.loss_ce: 0.0263, aux.acc_seg: 96.6962, loss: 0.0676 2022-05-06 10:07:01,369 - mmseg - INFO - Iter [59700/80000] lr: 3.644e-07, eta: 3:21:49, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0416, decode.acc_seg: 97.7209, aux.loss_ce: 0.0280, aux.acc_seg: 96.4669, loss: 0.0696 2022-05-06 10:07:28,074 - mmseg - INFO - Iter [59750/80000] lr: 3.635e-07, eta: 3:21:18, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0422, decode.acc_seg: 97.7726, aux.loss_ce: 0.0271, aux.acc_seg: 96.6590, loss: 0.0692 2022-05-06 10:07:55,144 - mmseg - INFO - Iter [59800/80000] lr: 3.626e-07, eta: 3:20:47, time: 0.544, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0410, decode.acc_seg: 97.8364, aux.loss_ce: 0.0269, aux.acc_seg: 96.6916, loss: 0.0679 2022-05-06 10:08:21,893 - mmseg - INFO - Iter [59850/80000] lr: 3.617e-07, eta: 3:20:16, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0413, decode.acc_seg: 97.7657, aux.loss_ce: 0.0263, aux.acc_seg: 96.6714, loss: 0.0676 2022-05-06 10:08:48,488 - mmseg - INFO - Iter [59900/80000] lr: 3.608e-07, eta: 3:19:45, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.7012, aux.loss_ce: 0.0262, aux.acc_seg: 96.5800, loss: 0.0673 2022-05-06 10:09:18,004 - mmseg - INFO - Iter [59950/80000] lr: 3.599e-07, eta: 3:19:15, time: 0.590, data_time: 0.051, memory: 58091, decode.loss_ce: 0.0416, decode.acc_seg: 97.7209, aux.loss_ce: 0.0271, aux.acc_seg: 96.5240, loss: 0.0687 2022-05-06 10:09:44,557 - mmseg - INFO - Saving checkpoint at 60000 iterations 2022-05-06 10:10:07,242 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:10:07,247 - mmseg - INFO - Iter [60000/80000] lr: 3.590e-07, eta: 3:18:52, time: 0.982, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0402, decode.acc_seg: 97.8096, aux.loss_ce: 0.0263, aux.acc_seg: 96.6815, loss: 0.0665 2022-05-06 10:10:34,408 - mmseg - INFO - Iter [60050/80000] lr: 3.581e-07, eta: 3:18:21, time: 0.546, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8024, aux.loss_ce: 0.0265, aux.acc_seg: 96.6959, loss: 0.0671 2022-05-06 10:11:01,180 - mmseg - INFO - Iter [60100/80000] lr: 3.572e-07, eta: 3:17:50, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.7359, aux.loss_ce: 0.0275, aux.acc_seg: 96.5519, loss: 0.0694 2022-05-06 10:11:27,697 - mmseg - INFO - Iter [60150/80000] lr: 3.563e-07, eta: 3:17:20, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0420, decode.acc_seg: 97.7261, aux.loss_ce: 0.0281, aux.acc_seg: 96.4729, loss: 0.0700 2022-05-06 10:11:54,379 - mmseg - INFO - Iter [60200/80000] lr: 3.554e-07, eta: 3:16:49, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.6955, aux.loss_ce: 0.0287, aux.acc_seg: 96.4825, loss: 0.0715 2022-05-06 10:12:23,584 - mmseg - INFO - Iter [60250/80000] lr: 3.545e-07, eta: 3:16:19, time: 0.584, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.8424, aux.loss_ce: 0.0271, aux.acc_seg: 96.6825, loss: 0.0674 2022-05-06 10:12:50,611 - mmseg - INFO - Iter [60300/80000] lr: 3.536e-07, eta: 3:15:48, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.9472, aux.loss_ce: 0.0253, aux.acc_seg: 96.8839, loss: 0.0637 2022-05-06 10:13:17,355 - mmseg - INFO - Iter [60350/80000] lr: 3.527e-07, eta: 3:15:17, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.9104, aux.loss_ce: 0.0260, aux.acc_seg: 96.8149, loss: 0.0655 2022-05-06 10:13:44,775 - mmseg - INFO - Iter [60400/80000] lr: 3.518e-07, eta: 3:14:46, time: 0.548, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.7360, aux.loss_ce: 0.0265, aux.acc_seg: 96.5460, loss: 0.0665 2022-05-06 10:14:11,279 - mmseg - INFO - Iter [60450/80000] lr: 3.509e-07, eta: 3:14:16, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.8610, aux.loss_ce: 0.0264, aux.acc_seg: 96.6899, loss: 0.0660 2022-05-06 10:14:37,809 - mmseg - INFO - Iter [60500/80000] lr: 3.500e-07, eta: 3:13:45, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0454, decode.acc_seg: 97.5590, aux.loss_ce: 0.0296, aux.acc_seg: 96.3525, loss: 0.0750 2022-05-06 10:15:07,332 - mmseg - INFO - Iter [60550/80000] lr: 3.491e-07, eta: 3:13:15, time: 0.589, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0424, decode.acc_seg: 97.6511, aux.loss_ce: 0.0274, aux.acc_seg: 96.5627, loss: 0.0698 2022-05-06 10:15:33,883 - mmseg - INFO - Iter [60600/80000] lr: 3.482e-07, eta: 3:12:44, time: 0.533, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.7606, aux.loss_ce: 0.0277, aux.acc_seg: 96.5711, loss: 0.0696 2022-05-06 10:16:00,522 - mmseg - INFO - Iter [60650/80000] lr: 3.473e-07, eta: 3:12:13, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.8320, aux.loss_ce: 0.0269, aux.acc_seg: 96.6882, loss: 0.0677 2022-05-06 10:16:27,053 - mmseg - INFO - Iter [60700/80000] lr: 3.464e-07, eta: 3:11:42, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.8005, aux.loss_ce: 0.0268, aux.acc_seg: 96.6792, loss: 0.0676 2022-05-06 10:16:53,768 - mmseg - INFO - Iter [60750/80000] lr: 3.455e-07, eta: 3:11:12, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.8295, aux.loss_ce: 0.0267, aux.acc_seg: 96.6511, loss: 0.0667 2022-05-06 10:17:20,406 - mmseg - INFO - Iter [60800/80000] lr: 3.446e-07, eta: 3:10:41, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0425, decode.acc_seg: 97.7001, aux.loss_ce: 0.0276, aux.acc_seg: 96.5673, loss: 0.0702 2022-05-06 10:17:49,926 - mmseg - INFO - Iter [60850/80000] lr: 3.437e-07, eta: 3:10:11, time: 0.590, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.7532, aux.loss_ce: 0.0276, aux.acc_seg: 96.5926, loss: 0.0696 2022-05-06 10:18:16,675 - mmseg - INFO - Iter [60900/80000] lr: 3.428e-07, eta: 3:09:40, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.8143, aux.loss_ce: 0.0267, aux.acc_seg: 96.6657, loss: 0.0670 2022-05-06 10:18:43,748 - mmseg - INFO - Iter [60950/80000] lr: 3.419e-07, eta: 3:09:09, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.7901, aux.loss_ce: 0.0266, aux.acc_seg: 96.6690, loss: 0.0677 2022-05-06 10:19:10,295 - mmseg - INFO - Saving checkpoint at 61000 iterations 2022-05-06 10:19:30,062 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:19:30,076 - mmseg - INFO - Iter [61000/80000] lr: 3.410e-07, eta: 3:08:45, time: 0.924, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0407, decode.acc_seg: 97.7591, aux.loss_ce: 0.0273, aux.acc_seg: 96.5152, loss: 0.0680 2022-05-06 10:19:57,595 - mmseg - INFO - Iter [61050/80000] lr: 3.401e-07, eta: 3:08:14, time: 0.551, data_time: 0.009, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.6851, aux.loss_ce: 0.0284, aux.acc_seg: 96.4855, loss: 0.0717 2022-05-06 10:20:24,313 - mmseg - INFO - Iter [61100/80000] lr: 3.392e-07, eta: 3:07:44, time: 0.536, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.7756, aux.loss_ce: 0.0263, aux.acc_seg: 96.6031, loss: 0.0658 2022-05-06 10:20:51,446 - mmseg - INFO - Iter [61150/80000] lr: 3.383e-07, eta: 3:07:13, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0383, decode.acc_seg: 97.8787, aux.loss_ce: 0.0252, aux.acc_seg: 96.7894, loss: 0.0635 2022-05-06 10:21:20,811 - mmseg - INFO - Iter [61200/80000] lr: 3.374e-07, eta: 3:06:43, time: 0.587, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.7058, aux.loss_ce: 0.0285, aux.acc_seg: 96.4560, loss: 0.0711 2022-05-06 10:21:47,867 - mmseg - INFO - Iter [61250/80000] lr: 3.365e-07, eta: 3:06:12, time: 0.541, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.8687, aux.loss_ce: 0.0251, aux.acc_seg: 96.7647, loss: 0.0630 2022-05-06 10:22:14,623 - mmseg - INFO - Iter [61300/80000] lr: 3.356e-07, eta: 3:05:42, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8244, aux.loss_ce: 0.0264, aux.acc_seg: 96.6740, loss: 0.0670 2022-05-06 10:22:41,213 - mmseg - INFO - Iter [61350/80000] lr: 3.347e-07, eta: 3:05:11, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.8075, aux.loss_ce: 0.0275, aux.acc_seg: 96.6385, loss: 0.0694 2022-05-06 10:23:08,023 - mmseg - INFO - Iter [61400/80000] lr: 3.338e-07, eta: 3:04:40, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.8084, aux.loss_ce: 0.0260, aux.acc_seg: 96.7159, loss: 0.0663 2022-05-06 10:23:34,950 - mmseg - INFO - Iter [61450/80000] lr: 3.329e-07, eta: 3:04:10, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.8338, aux.loss_ce: 0.0270, aux.acc_seg: 96.6767, loss: 0.0675 2022-05-06 10:24:04,126 - mmseg - INFO - Iter [61500/80000] lr: 3.320e-07, eta: 3:03:40, time: 0.583, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7356, aux.loss_ce: 0.0269, aux.acc_seg: 96.5542, loss: 0.0677 2022-05-06 10:24:30,965 - mmseg - INFO - Iter [61550/80000] lr: 3.311e-07, eta: 3:03:09, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0420, decode.acc_seg: 97.7826, aux.loss_ce: 0.0284, aux.acc_seg: 96.5553, loss: 0.0705 2022-05-06 10:24:57,641 - mmseg - INFO - Iter [61600/80000] lr: 3.303e-07, eta: 3:02:38, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0407, decode.acc_seg: 97.7824, aux.loss_ce: 0.0265, aux.acc_seg: 96.6728, loss: 0.0671 2022-05-06 10:25:24,083 - mmseg - INFO - Iter [61650/80000] lr: 3.294e-07, eta: 3:02:07, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.8244, aux.loss_ce: 0.0257, aux.acc_seg: 96.7701, loss: 0.0660 2022-05-06 10:25:50,628 - mmseg - INFO - Iter [61700/80000] lr: 3.285e-07, eta: 3:01:37, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8640, aux.loss_ce: 0.0260, aux.acc_seg: 96.7070, loss: 0.0652 2022-05-06 10:26:17,319 - mmseg - INFO - Iter [61750/80000] lr: 3.276e-07, eta: 3:01:06, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.6385, aux.loss_ce: 0.0279, aux.acc_seg: 96.5450, loss: 0.0720 2022-05-06 10:26:46,395 - mmseg - INFO - Iter [61800/80000] lr: 3.267e-07, eta: 3:00:36, time: 0.581, data_time: 0.051, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7464, aux.loss_ce: 0.0268, aux.acc_seg: 96.6054, loss: 0.0675 2022-05-06 10:27:13,006 - mmseg - INFO - Iter [61850/80000] lr: 3.258e-07, eta: 3:00:05, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.8255, aux.loss_ce: 0.0260, aux.acc_seg: 96.7131, loss: 0.0656 2022-05-06 10:27:39,683 - mmseg - INFO - Iter [61900/80000] lr: 3.249e-07, eta: 2:59:35, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0412, decode.acc_seg: 97.7531, aux.loss_ce: 0.0273, aux.acc_seg: 96.5674, loss: 0.0684 2022-05-06 10:28:06,026 - mmseg - INFO - Iter [61950/80000] lr: 3.240e-07, eta: 2:59:04, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0428, decode.acc_seg: 97.7727, aux.loss_ce: 0.0283, aux.acc_seg: 96.5485, loss: 0.0710 2022-05-06 10:28:32,745 - mmseg - INFO - Saving checkpoint at 62000 iterations 2022-05-06 10:28:54,603 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:28:54,605 - mmseg - INFO - Iter [62000/80000] lr: 3.231e-07, eta: 2:58:40, time: 0.970, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0388, decode.acc_seg: 97.9000, aux.loss_ce: 0.0255, aux.acc_seg: 96.8177, loss: 0.0643 2022-05-06 10:29:21,632 - mmseg - INFO - Iter [62050/80000] lr: 3.222e-07, eta: 2:58:09, time: 0.542, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0407, decode.acc_seg: 97.7498, aux.loss_ce: 0.0267, aux.acc_seg: 96.5676, loss: 0.0674 2022-05-06 10:29:50,848 - mmseg - INFO - Iter [62100/80000] lr: 3.213e-07, eta: 2:57:39, time: 0.584, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.7961, aux.loss_ce: 0.0253, aux.acc_seg: 96.6502, loss: 0.0639 2022-05-06 10:30:17,748 - mmseg - INFO - Iter [62150/80000] lr: 3.204e-07, eta: 2:57:09, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0407, decode.acc_seg: 97.8094, aux.loss_ce: 0.0272, aux.acc_seg: 96.6240, loss: 0.0679 2022-05-06 10:30:44,160 - mmseg - INFO - Iter [62200/80000] lr: 3.195e-07, eta: 2:56:38, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9594, aux.loss_ce: 0.0254, aux.acc_seg: 96.8385, loss: 0.0634 2022-05-06 10:31:10,843 - mmseg - INFO - Iter [62250/80000] lr: 3.186e-07, eta: 2:56:07, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.7577, aux.loss_ce: 0.0267, aux.acc_seg: 96.5008, loss: 0.0665 2022-05-06 10:31:37,281 - mmseg - INFO - Iter [62300/80000] lr: 3.177e-07, eta: 2:55:36, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0422, decode.acc_seg: 97.7403, aux.loss_ce: 0.0274, aux.acc_seg: 96.5898, loss: 0.0695 2022-05-06 10:32:03,806 - mmseg - INFO - Iter [62350/80000] lr: 3.168e-07, eta: 2:55:06, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7907, aux.loss_ce: 0.0272, aux.acc_seg: 96.6307, loss: 0.0680 2022-05-06 10:32:30,262 - mmseg - INFO - Iter [62400/80000] lr: 3.159e-07, eta: 2:54:35, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9195, aux.loss_ce: 0.0244, aux.acc_seg: 96.8130, loss: 0.0613 2022-05-06 10:32:59,793 - mmseg - INFO - Iter [62450/80000] lr: 3.150e-07, eta: 2:54:05, time: 0.591, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.8910, aux.loss_ce: 0.0264, aux.acc_seg: 96.7971, loss: 0.0668 2022-05-06 10:33:26,555 - mmseg - INFO - Iter [62500/80000] lr: 3.141e-07, eta: 2:53:35, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0433, decode.acc_seg: 97.6334, aux.loss_ce: 0.0283, aux.acc_seg: 96.4366, loss: 0.0717 2022-05-06 10:33:53,043 - mmseg - INFO - Iter [62550/80000] lr: 3.132e-07, eta: 2:53:04, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.8549, aux.loss_ce: 0.0265, aux.acc_seg: 96.7119, loss: 0.0666 2022-05-06 10:34:19,788 - mmseg - INFO - Iter [62600/80000] lr: 3.123e-07, eta: 2:52:33, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0397, decode.acc_seg: 97.8668, aux.loss_ce: 0.0261, aux.acc_seg: 96.7657, loss: 0.0658 2022-05-06 10:34:46,305 - mmseg - INFO - Iter [62650/80000] lr: 3.114e-07, eta: 2:52:03, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.8282, aux.loss_ce: 0.0257, aux.acc_seg: 96.7484, loss: 0.0653 2022-05-06 10:35:12,828 - mmseg - INFO - Iter [62700/80000] lr: 3.105e-07, eta: 2:51:32, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8502, aux.loss_ce: 0.0269, aux.acc_seg: 96.6620, loss: 0.0674 2022-05-06 10:35:41,836 - mmseg - INFO - Iter [62750/80000] lr: 3.096e-07, eta: 2:51:02, time: 0.580, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.7994, aux.loss_ce: 0.0270, aux.acc_seg: 96.5956, loss: 0.0674 2022-05-06 10:36:08,294 - mmseg - INFO - Iter [62800/80000] lr: 3.087e-07, eta: 2:50:31, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0458, decode.acc_seg: 97.6717, aux.loss_ce: 0.0291, aux.acc_seg: 96.4898, loss: 0.0748 2022-05-06 10:36:34,753 - mmseg - INFO - Iter [62850/80000] lr: 3.078e-07, eta: 2:50:01, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0391, decode.acc_seg: 97.8590, aux.loss_ce: 0.0260, aux.acc_seg: 96.6901, loss: 0.0651 2022-05-06 10:37:01,358 - mmseg - INFO - Iter [62900/80000] lr: 3.069e-07, eta: 2:49:30, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0419, decode.acc_seg: 97.7175, aux.loss_ce: 0.0274, aux.acc_seg: 96.5723, loss: 0.0693 2022-05-06 10:37:27,875 - mmseg - INFO - Iter [62950/80000] lr: 3.060e-07, eta: 2:49:00, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0409, decode.acc_seg: 97.7722, aux.loss_ce: 0.0267, aux.acc_seg: 96.6024, loss: 0.0676 2022-05-06 10:37:54,640 - mmseg - INFO - Saving checkpoint at 63000 iterations 2022-05-06 10:38:14,482 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:38:14,491 - mmseg - INFO - Iter [63000/80000] lr: 3.051e-07, eta: 2:48:34, time: 0.931, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0409, decode.acc_seg: 97.7645, aux.loss_ce: 0.0273, aux.acc_seg: 96.5675, loss: 0.0682 2022-05-06 10:38:44,913 - mmseg - INFO - Iter [63050/80000] lr: 3.042e-07, eta: 2:48:05, time: 0.608, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0414, decode.acc_seg: 97.7095, aux.loss_ce: 0.0273, aux.acc_seg: 96.5131, loss: 0.0687 2022-05-06 10:39:11,752 - mmseg - INFO - Iter [63100/80000] lr: 3.033e-07, eta: 2:47:34, time: 0.539, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.7755, aux.loss_ce: 0.0264, aux.acc_seg: 96.5995, loss: 0.0668 2022-05-06 10:39:38,260 - mmseg - INFO - Iter [63150/80000] lr: 3.024e-07, eta: 2:47:04, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8117, aux.loss_ce: 0.0262, aux.acc_seg: 96.7139, loss: 0.0668 2022-05-06 10:40:05,527 - mmseg - INFO - Iter [63200/80000] lr: 3.015e-07, eta: 2:46:33, time: 0.546, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7676, aux.loss_ce: 0.0267, aux.acc_seg: 96.5720, loss: 0.0674 2022-05-06 10:40:32,355 - mmseg - INFO - Iter [63250/80000] lr: 3.006e-07, eta: 2:46:03, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0415, decode.acc_seg: 97.7305, aux.loss_ce: 0.0278, aux.acc_seg: 96.5113, loss: 0.0693 2022-05-06 10:40:59,060 - mmseg - INFO - Iter [63300/80000] lr: 2.997e-07, eta: 2:45:32, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.9522, aux.loss_ce: 0.0247, aux.acc_seg: 96.8195, loss: 0.0618 2022-05-06 10:41:28,167 - mmseg - INFO - Iter [63350/80000] lr: 2.988e-07, eta: 2:45:02, time: 0.582, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7999, aux.loss_ce: 0.0268, aux.acc_seg: 96.6625, loss: 0.0676 2022-05-06 10:41:54,650 - mmseg - INFO - Iter [63400/80000] lr: 2.979e-07, eta: 2:44:32, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.8271, aux.loss_ce: 0.0269, aux.acc_seg: 96.7246, loss: 0.0677 2022-05-06 10:42:21,195 - mmseg - INFO - Iter [63450/80000] lr: 2.970e-07, eta: 2:44:01, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8372, aux.loss_ce: 0.0265, aux.acc_seg: 96.6604, loss: 0.0663 2022-05-06 10:42:47,875 - mmseg - INFO - Iter [63500/80000] lr: 2.962e-07, eta: 2:43:31, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0435, decode.acc_seg: 97.6991, aux.loss_ce: 0.0283, aux.acc_seg: 96.5431, loss: 0.0717 2022-05-06 10:43:14,496 - mmseg - INFO - Iter [63550/80000] lr: 2.953e-07, eta: 2:43:00, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 98.0164, aux.loss_ce: 0.0249, aux.acc_seg: 96.8782, loss: 0.0619 2022-05-06 10:43:40,941 - mmseg - INFO - Iter [63600/80000] lr: 2.944e-07, eta: 2:42:30, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.8228, aux.loss_ce: 0.0261, aux.acc_seg: 96.7142, loss: 0.0660 2022-05-06 10:44:10,287 - mmseg - INFO - Iter [63650/80000] lr: 2.935e-07, eta: 2:42:00, time: 0.587, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0397, decode.acc_seg: 97.8851, aux.loss_ce: 0.0264, aux.acc_seg: 96.7639, loss: 0.0661 2022-05-06 10:44:36,798 - mmseg - INFO - Iter [63700/80000] lr: 2.926e-07, eta: 2:41:29, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.8348, aux.loss_ce: 0.0256, aux.acc_seg: 96.7461, loss: 0.0649 2022-05-06 10:45:03,305 - mmseg - INFO - Iter [63750/80000] lr: 2.917e-07, eta: 2:40:59, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.9199, aux.loss_ce: 0.0258, aux.acc_seg: 96.7563, loss: 0.0642 2022-05-06 10:45:29,786 - mmseg - INFO - Iter [63800/80000] lr: 2.908e-07, eta: 2:40:28, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8980, aux.loss_ce: 0.0261, aux.acc_seg: 96.7751, loss: 0.0653 2022-05-06 10:45:56,146 - mmseg - INFO - Iter [63850/80000] lr: 2.899e-07, eta: 2:39:58, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0413, decode.acc_seg: 97.7494, aux.loss_ce: 0.0273, aux.acc_seg: 96.5774, loss: 0.0686 2022-05-06 10:46:23,064 - mmseg - INFO - Iter [63900/80000] lr: 2.890e-07, eta: 2:39:27, time: 0.538, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0410, decode.acc_seg: 97.7993, aux.loss_ce: 0.0270, aux.acc_seg: 96.6304, loss: 0.0680 2022-05-06 10:46:50,005 - mmseg - INFO - Iter [63950/80000] lr: 2.881e-07, eta: 2:38:57, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.7713, aux.loss_ce: 0.0263, aux.acc_seg: 96.6606, loss: 0.0667 2022-05-06 10:47:19,151 - mmseg - INFO - Saving checkpoint at 64000 iterations 2022-05-06 10:47:41,509 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:47:41,519 - mmseg - INFO - Iter [64000/80000] lr: 2.872e-07, eta: 2:38:32, time: 1.027, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.8614, aux.loss_ce: 0.0267, aux.acc_seg: 96.7136, loss: 0.0668 2022-05-06 10:51:53,139 - mmseg - INFO - per class results: 2022-05-06 10:51:53,146 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 93.07 | 96.93 | | bag | 43.47 | 52.92 | | bed | 35.25 | 45.02 | | bedclothes | 45.61 | 68.39 | | bench | 32.55 | 41.33 | | bicycle | 84.21 | 93.73 | | bird | 94.0 | 98.17 | | boat | 85.73 | 92.35 | | book | 61.16 | 74.57 | | bottle | 88.52 | 96.81 | | building | 68.53 | 82.52 | | bus | 94.53 | 97.5 | | cabinet | 51.37 | 65.77 | | car | 94.02 | 97.18 | | cat | 93.12 | 98.14 | | ceiling | 59.58 | 73.09 | | chair | 64.19 | 78.62 | | cloth | 25.86 | 33.05 | | computer | 60.92 | 71.76 | | cow | 95.36 | 98.49 | | cup | 47.66 | 66.0 | | curtain | 60.61 | 74.98 | | dog | 91.67 | 98.27 | | door | 35.88 | 51.26 | | fence | 45.93 | 59.02 | | floor | 76.74 | 88.46 | | flower | 37.09 | 48.5 | | food | 42.17 | 51.53 | | grass | 83.24 | 92.62 | | ground | 57.37 | 71.0 | | horse | 94.54 | 97.46 | | keyboard | 91.11 | 94.88 | | light | 59.74 | 73.28 | | motorbike | 90.83 | 96.84 | | mountain | 58.69 | 73.87 | | mouse | 80.47 | 93.34 | | person | 90.54 | 96.85 | | plate | 30.18 | 40.91 | | platform | 58.84 | 74.11 | | pottedplant | 81.76 | 90.4 | | road | 53.72 | 71.24 | | rock | 56.72 | 64.76 | | sheep | 94.86 | 98.23 | | shelves | 36.74 | 47.27 | | sidewalk | 33.53 | 50.52 | | sign | 53.57 | 60.54 | | sky | 94.99 | 97.47 | | snow | 76.61 | 90.68 | | sofa | 60.18 | 69.19 | | table | 73.74 | 86.05 | | track | 73.33 | 86.45 | | train | 93.16 | 97.5 | | tree | 81.67 | 90.29 | | truck | 51.55 | 58.27 | | tvmonitor | 90.78 | 94.46 | | wall | 74.25 | 85.74 | | water | 91.85 | 96.54 | | window | 47.1 | 59.89 | | wood | 25.76 | 33.03 | +-------------+-------+-------+ 2022-05-06 10:51:53,146 - mmseg - INFO - Summary: 2022-05-06 10:51:53,146 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.65 | 66.95 | 76.75 | +-------+-------+-------+ 2022-05-06 10:51:53,148 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_56000.pth was removed 2022-05-06 10:52:14,001 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_64000.pth. 2022-05-06 10:52:14,009 - mmseg - INFO - Best mIoU is 0.6695 at 64000 iter. 2022-05-06 10:52:14,041 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 10:52:14,043 - mmseg - INFO - Iter(val) [638] aAcc: 0.8665, mIoU: 0.6695, mAcc: 0.7675, IoU.aeroplane: 0.9307, IoU.bag: 0.4347, IoU.bed: 0.3525, IoU.bedclothes: 0.4561, IoU.bench: 0.3255, IoU.bicycle: 0.8421, IoU.bird: 0.9400, IoU.boat: 0.8573, IoU.book: 0.6116, IoU.bottle: 0.8852, IoU.building: 0.6853, IoU.bus: 0.9453, IoU.cabinet: 0.5137, IoU.car: 0.9402, IoU.cat: 0.9312, IoU.ceiling: 0.5958, IoU.chair: 0.6419, IoU.cloth: 0.2586, IoU.computer: 0.6092, IoU.cow: 0.9536, IoU.cup: 0.4766, IoU.curtain: 0.6061, IoU.dog: 0.9167, IoU.door: 0.3588, IoU.fence: 0.4593, IoU.floor: 0.7674, IoU.flower: 0.3709, IoU.food: 0.4217, IoU.grass: 0.8324, IoU.ground: 0.5737, IoU.horse: 0.9454, IoU.keyboard: 0.9111, IoU.light: 0.5974, IoU.motorbike: 0.9083, IoU.mountain: 0.5869, IoU.mouse: 0.8047, IoU.person: 0.9054, IoU.plate: 0.3018, IoU.platform: 0.5884, IoU.pottedplant: 0.8176, IoU.road: 0.5372, IoU.rock: 0.5672, IoU.sheep: 0.9486, IoU.shelves: 0.3674, IoU.sidewalk: 0.3353, IoU.sign: 0.5357, IoU.sky: 0.9499, IoU.snow: 0.7661, IoU.sofa: 0.6018, IoU.table: 0.7374, IoU.track: 0.7333, IoU.train: 0.9316, IoU.tree: 0.8167, IoU.truck: 0.5155, IoU.tvmonitor: 0.9078, IoU.wall: 0.7425, IoU.water: 0.9185, IoU.window: 0.4710, IoU.wood: 0.2576, Acc.aeroplane: 0.9693, Acc.bag: 0.5292, Acc.bed: 0.4502, Acc.bedclothes: 0.6839, Acc.bench: 0.4133, Acc.bicycle: 0.9373, Acc.bird: 0.9817, Acc.boat: 0.9235, Acc.book: 0.7457, Acc.bottle: 0.9681, Acc.building: 0.8252, Acc.bus: 0.9750, Acc.cabinet: 0.6577, Acc.car: 0.9718, Acc.cat: 0.9814, Acc.ceiling: 0.7309, Acc.chair: 0.7862, Acc.cloth: 0.3305, Acc.computer: 0.7176, Acc.cow: 0.9849, Acc.cup: 0.6600, Acc.curtain: 0.7498, Acc.dog: 0.9827, Acc.door: 0.5126, Acc.fence: 0.5902, Acc.floor: 0.8846, Acc.flower: 0.4850, Acc.food: 0.5153, Acc.grass: 0.9262, Acc.ground: 0.7100, Acc.horse: 0.9746, Acc.keyboard: 0.9488, Acc.light: 0.7328, Acc.motorbike: 0.9684, Acc.mountain: 0.7387, Acc.mouse: 0.9334, Acc.person: 0.9685, Acc.plate: 0.4091, Acc.platform: 0.7411, Acc.pottedplant: 0.9040, Acc.road: 0.7124, Acc.rock: 0.6476, Acc.sheep: 0.9823, Acc.shelves: 0.4727, Acc.sidewalk: 0.5052, Acc.sign: 0.6054, Acc.sky: 0.9747, Acc.snow: 0.9068, Acc.sofa: 0.6919, Acc.table: 0.8605, Acc.track: 0.8645, Acc.train: 0.9750, Acc.tree: 0.9029, Acc.truck: 0.5827, Acc.tvmonitor: 0.9446, Acc.wall: 0.8574, Acc.water: 0.9654, Acc.window: 0.5989, Acc.wood: 0.3303 2022-05-06 10:52:41,556 - mmseg - INFO - Iter [64050/80000] lr: 2.863e-07, eta: 2:39:10, time: 6.004, data_time: 5.459, memory: 58091, decode.loss_ce: 0.0415, decode.acc_seg: 97.6990, aux.loss_ce: 0.0270, aux.acc_seg: 96.5380, loss: 0.0685 2022-05-06 10:53:07,984 - mmseg - INFO - Iter [64100/80000] lr: 2.854e-07, eta: 2:38:39, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.7453, aux.loss_ce: 0.0268, aux.acc_seg: 96.5331, loss: 0.0673 2022-05-06 10:53:34,908 - mmseg - INFO - Iter [64150/80000] lr: 2.845e-07, eta: 2:38:09, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0391, decode.acc_seg: 97.8772, aux.loss_ce: 0.0259, aux.acc_seg: 96.7309, loss: 0.0650 2022-05-06 10:54:01,397 - mmseg - INFO - Iter [64200/80000] lr: 2.836e-07, eta: 2:37:38, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8521, aux.loss_ce: 0.0263, aux.acc_seg: 96.7496, loss: 0.0661 2022-05-06 10:54:27,862 - mmseg - INFO - Iter [64250/80000] lr: 2.827e-07, eta: 2:37:07, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.7630, aux.loss_ce: 0.0268, aux.acc_seg: 96.6369, loss: 0.0679 2022-05-06 10:54:57,314 - mmseg - INFO - Iter [64300/80000] lr: 2.818e-07, eta: 2:36:37, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.7944, aux.loss_ce: 0.0256, aux.acc_seg: 96.6693, loss: 0.0654 2022-05-06 10:55:23,864 - mmseg - INFO - Iter [64350/80000] lr: 2.809e-07, eta: 2:36:06, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8003, aux.loss_ce: 0.0268, aux.acc_seg: 96.5841, loss: 0.0667 2022-05-06 10:55:50,510 - mmseg - INFO - Iter [64400/80000] lr: 2.800e-07, eta: 2:35:35, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.7866, aux.loss_ce: 0.0261, aux.acc_seg: 96.6302, loss: 0.0667 2022-05-06 10:56:17,037 - mmseg - INFO - Iter [64450/80000] lr: 2.791e-07, eta: 2:35:05, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.8988, aux.loss_ce: 0.0259, aux.acc_seg: 96.8070, loss: 0.0654 2022-05-06 10:56:43,542 - mmseg - INFO - Iter [64500/80000] lr: 2.782e-07, eta: 2:34:34, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0373, decode.acc_seg: 97.9765, aux.loss_ce: 0.0247, aux.acc_seg: 96.8887, loss: 0.0620 2022-05-06 10:57:10,501 - mmseg - INFO - Iter [64550/80000] lr: 2.773e-07, eta: 2:34:03, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.8857, aux.loss_ce: 0.0267, aux.acc_seg: 96.7369, loss: 0.0661 2022-05-06 10:57:39,863 - mmseg - INFO - Iter [64600/80000] lr: 2.764e-07, eta: 2:33:33, time: 0.587, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.7552, aux.loss_ce: 0.0262, aux.acc_seg: 96.5833, loss: 0.0662 2022-05-06 10:58:06,327 - mmseg - INFO - Iter [64650/80000] lr: 2.755e-07, eta: 2:33:03, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.8260, aux.loss_ce: 0.0270, aux.acc_seg: 96.6581, loss: 0.0688 2022-05-06 10:58:33,442 - mmseg - INFO - Iter [64700/80000] lr: 2.746e-07, eta: 2:32:32, time: 0.542, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.7570, aux.loss_ce: 0.0268, aux.acc_seg: 96.4506, loss: 0.0663 2022-05-06 10:59:00,211 - mmseg - INFO - Iter [64750/80000] lr: 2.737e-07, eta: 2:32:01, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8928, aux.loss_ce: 0.0254, aux.acc_seg: 96.7810, loss: 0.0640 2022-05-06 10:59:26,767 - mmseg - INFO - Iter [64800/80000] lr: 2.728e-07, eta: 2:31:31, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.8375, aux.loss_ce: 0.0263, aux.acc_seg: 96.6437, loss: 0.0656 2022-05-06 10:59:53,322 - mmseg - INFO - Iter [64850/80000] lr: 2.719e-07, eta: 2:31:00, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.8381, aux.loss_ce: 0.0259, aux.acc_seg: 96.6818, loss: 0.0653 2022-05-06 11:00:22,583 - mmseg - INFO - Iter [64900/80000] lr: 2.710e-07, eta: 2:30:30, time: 0.585, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.8741, aux.loss_ce: 0.0253, aux.acc_seg: 96.7646, loss: 0.0643 2022-05-06 11:00:49,582 - mmseg - INFO - Iter [64950/80000] lr: 2.701e-07, eta: 2:29:59, time: 0.540, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.7811, aux.loss_ce: 0.0265, aux.acc_seg: 96.6163, loss: 0.0664 2022-05-06 11:01:16,323 - mmseg - INFO - Saving checkpoint at 65000 iterations 2022-05-06 11:01:37,579 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:01:37,588 - mmseg - INFO - Iter [65000/80000] lr: 2.692e-07, eta: 2:29:34, time: 0.956, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.7797, aux.loss_ce: 0.0264, aux.acc_seg: 96.6105, loss: 0.0663 2022-05-06 11:02:04,753 - mmseg - INFO - Iter [65050/80000] lr: 2.683e-07, eta: 2:29:03, time: 0.547, data_time: 0.009, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.8419, aux.loss_ce: 0.0268, aux.acc_seg: 96.6213, loss: 0.0668 2022-05-06 11:02:31,353 - mmseg - INFO - Iter [65100/80000] lr: 2.674e-07, eta: 2:28:32, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.8404, aux.loss_ce: 0.0263, aux.acc_seg: 96.6258, loss: 0.0656 2022-05-06 11:02:58,237 - mmseg - INFO - Iter [65150/80000] lr: 2.665e-07, eta: 2:28:02, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.9084, aux.loss_ce: 0.0262, aux.acc_seg: 96.7141, loss: 0.0652 2022-05-06 11:03:24,964 - mmseg - INFO - Iter [65200/80000] lr: 2.656e-07, eta: 2:27:31, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.8728, aux.loss_ce: 0.0271, aux.acc_seg: 96.7042, loss: 0.0677 2022-05-06 11:03:54,003 - mmseg - INFO - Iter [65250/80000] lr: 2.647e-07, eta: 2:27:01, time: 0.581, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.9168, aux.loss_ce: 0.0255, aux.acc_seg: 96.7618, loss: 0.0635 2022-05-06 11:04:20,808 - mmseg - INFO - Iter [65300/80000] lr: 2.638e-07, eta: 2:26:30, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.8697, aux.loss_ce: 0.0259, aux.acc_seg: 96.6994, loss: 0.0649 2022-05-06 11:04:47,365 - mmseg - INFO - Iter [65350/80000] lr: 2.629e-07, eta: 2:26:00, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0381, decode.acc_seg: 97.9380, aux.loss_ce: 0.0249, aux.acc_seg: 96.8643, loss: 0.0630 2022-05-06 11:05:13,913 - mmseg - INFO - Iter [65400/80000] lr: 2.621e-07, eta: 2:25:29, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0376, decode.acc_seg: 97.9271, aux.loss_ce: 0.0249, aux.acc_seg: 96.8312, loss: 0.0625 2022-05-06 11:05:40,446 - mmseg - INFO - Iter [65450/80000] lr: 2.612e-07, eta: 2:24:59, time: 0.531, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.7452, aux.loss_ce: 0.0266, aux.acc_seg: 96.5320, loss: 0.0670 2022-05-06 11:06:06,926 - mmseg - INFO - Iter [65500/80000] lr: 2.603e-07, eta: 2:24:28, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0409, decode.acc_seg: 97.8204, aux.loss_ce: 0.0273, aux.acc_seg: 96.6390, loss: 0.0683 2022-05-06 11:06:36,304 - mmseg - INFO - Iter [65550/80000] lr: 2.594e-07, eta: 2:23:58, time: 0.586, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9194, aux.loss_ce: 0.0253, aux.acc_seg: 96.7836, loss: 0.0630 2022-05-06 11:07:03,066 - mmseg - INFO - Iter [65600/80000] lr: 2.585e-07, eta: 2:23:27, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.8762, aux.loss_ce: 0.0259, aux.acc_seg: 96.7685, loss: 0.0655 2022-05-06 11:07:29,534 - mmseg - INFO - Iter [65650/80000] lr: 2.576e-07, eta: 2:22:57, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.7768, aux.loss_ce: 0.0264, aux.acc_seg: 96.6036, loss: 0.0661 2022-05-06 11:07:56,355 - mmseg - INFO - Iter [65700/80000] lr: 2.567e-07, eta: 2:22:26, time: 0.536, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9471, aux.loss_ce: 0.0253, aux.acc_seg: 96.8107, loss: 0.0632 2022-05-06 11:08:23,171 - mmseg - INFO - Iter [65750/80000] lr: 2.558e-07, eta: 2:21:56, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.8337, aux.loss_ce: 0.0260, aux.acc_seg: 96.6779, loss: 0.0653 2022-05-06 11:08:49,765 - mmseg - INFO - Iter [65800/80000] lr: 2.549e-07, eta: 2:21:25, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.7536, aux.loss_ce: 0.0273, aux.acc_seg: 96.5254, loss: 0.0681 2022-05-06 11:09:18,972 - mmseg - INFO - Iter [65850/80000] lr: 2.540e-07, eta: 2:20:55, time: 0.584, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.8769, aux.loss_ce: 0.0265, aux.acc_seg: 96.7429, loss: 0.0664 2022-05-06 11:09:45,686 - mmseg - INFO - Iter [65900/80000] lr: 2.531e-07, eta: 2:20:24, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.7683, aux.loss_ce: 0.0277, aux.acc_seg: 96.4916, loss: 0.0678 2022-05-06 11:10:12,432 - mmseg - INFO - Iter [65950/80000] lr: 2.522e-07, eta: 2:19:54, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.8859, aux.loss_ce: 0.0252, aux.acc_seg: 96.7971, loss: 0.0645 2022-05-06 11:10:39,348 - mmseg - INFO - Saving checkpoint at 66000 iterations 2022-05-06 11:11:00,348 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:11:00,357 - mmseg - INFO - Iter [66000/80000] lr: 2.513e-07, eta: 2:19:28, time: 0.956, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0406, decode.acc_seg: 97.7703, aux.loss_ce: 0.0271, aux.acc_seg: 96.5781, loss: 0.0676 2022-05-06 11:11:27,356 - mmseg - INFO - Iter [66050/80000] lr: 2.504e-07, eta: 2:18:57, time: 0.543, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.8302, aux.loss_ce: 0.0262, aux.acc_seg: 96.6643, loss: 0.0658 2022-05-06 11:11:54,059 - mmseg - INFO - Iter [66100/80000] lr: 2.495e-07, eta: 2:18:27, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.8319, aux.loss_ce: 0.0265, aux.acc_seg: 96.6653, loss: 0.0665 2022-05-06 11:12:23,524 - mmseg - INFO - Iter [66150/80000] lr: 2.486e-07, eta: 2:17:57, time: 0.589, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.8501, aux.loss_ce: 0.0265, aux.acc_seg: 96.6790, loss: 0.0664 2022-05-06 11:12:50,169 - mmseg - INFO - Iter [66200/80000] lr: 2.477e-07, eta: 2:17:26, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8365, aux.loss_ce: 0.0261, aux.acc_seg: 96.6150, loss: 0.0647 2022-05-06 11:13:16,537 - mmseg - INFO - Iter [66250/80000] lr: 2.468e-07, eta: 2:16:56, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9122, aux.loss_ce: 0.0259, aux.acc_seg: 96.7350, loss: 0.0645 2022-05-06 11:13:43,114 - mmseg - INFO - Iter [66300/80000] lr: 2.459e-07, eta: 2:16:25, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0416, decode.acc_seg: 97.8247, aux.loss_ce: 0.0271, aux.acc_seg: 96.6377, loss: 0.0687 2022-05-06 11:14:09,608 - mmseg - INFO - Iter [66350/80000] lr: 2.450e-07, eta: 2:15:54, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8677, aux.loss_ce: 0.0257, aux.acc_seg: 96.7279, loss: 0.0644 2022-05-06 11:14:36,240 - mmseg - INFO - Iter [66400/80000] lr: 2.441e-07, eta: 2:15:24, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.8185, aux.loss_ce: 0.0268, aux.acc_seg: 96.6102, loss: 0.0670 2022-05-06 11:15:02,777 - mmseg - INFO - Iter [66450/80000] lr: 2.432e-07, eta: 2:14:53, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.8634, aux.loss_ce: 0.0259, aux.acc_seg: 96.7889, loss: 0.0652 2022-05-06 11:15:32,419 - mmseg - INFO - Iter [66500/80000] lr: 2.423e-07, eta: 2:14:23, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8308, aux.loss_ce: 0.0259, aux.acc_seg: 96.6309, loss: 0.0646 2022-05-06 11:15:59,415 - mmseg - INFO - Iter [66550/80000] lr: 2.414e-07, eta: 2:13:53, time: 0.540, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0441, decode.acc_seg: 97.7485, aux.loss_ce: 0.0273, aux.acc_seg: 96.5586, loss: 0.0713 2022-05-06 11:16:26,007 - mmseg - INFO - Iter [66600/80000] lr: 2.405e-07, eta: 2:13:23, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0408, decode.acc_seg: 97.8527, aux.loss_ce: 0.0268, aux.acc_seg: 96.7131, loss: 0.0676 2022-05-06 11:16:52,936 - mmseg - INFO - Iter [66650/80000] lr: 2.396e-07, eta: 2:12:52, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8387, aux.loss_ce: 0.0262, aux.acc_seg: 96.6588, loss: 0.0654 2022-05-06 11:17:19,471 - mmseg - INFO - Iter [66700/80000] lr: 2.387e-07, eta: 2:12:22, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8726, aux.loss_ce: 0.0257, aux.acc_seg: 96.6708, loss: 0.0643 2022-05-06 11:17:46,104 - mmseg - INFO - Iter [66750/80000] lr: 2.378e-07, eta: 2:11:51, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0403, decode.acc_seg: 97.8393, aux.loss_ce: 0.0268, aux.acc_seg: 96.6667, loss: 0.0671 2022-05-06 11:18:15,081 - mmseg - INFO - Iter [66800/80000] lr: 2.369e-07, eta: 2:11:21, time: 0.579, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.8779, aux.loss_ce: 0.0261, aux.acc_seg: 96.7590, loss: 0.0655 2022-05-06 11:18:41,675 - mmseg - INFO - Iter [66850/80000] lr: 2.360e-07, eta: 2:10:51, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0437, decode.acc_seg: 97.6526, aux.loss_ce: 0.0288, aux.acc_seg: 96.3629, loss: 0.0726 2022-05-06 11:19:08,324 - mmseg - INFO - Iter [66900/80000] lr: 2.351e-07, eta: 2:10:20, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.9056, aux.loss_ce: 0.0269, aux.acc_seg: 96.7396, loss: 0.0667 2022-05-06 11:19:34,990 - mmseg - INFO - Iter [66950/80000] lr: 2.342e-07, eta: 2:09:50, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9094, aux.loss_ce: 0.0248, aux.acc_seg: 96.7396, loss: 0.0618 2022-05-06 11:20:01,433 - mmseg - INFO - Saving checkpoint at 67000 iterations 2022-05-06 11:20:22,552 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:20:22,560 - mmseg - INFO - Iter [67000/80000] lr: 2.333e-07, eta: 2:09:23, time: 0.949, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9361, aux.loss_ce: 0.0251, aux.acc_seg: 96.7621, loss: 0.0622 2022-05-06 11:20:49,351 - mmseg - INFO - Iter [67050/80000] lr: 2.324e-07, eta: 2:08:53, time: 0.538, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.8860, aux.loss_ce: 0.0263, aux.acc_seg: 96.7774, loss: 0.0664 2022-05-06 11:21:18,688 - mmseg - INFO - Iter [67100/80000] lr: 2.315e-07, eta: 2:08:23, time: 0.585, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8620, aux.loss_ce: 0.0261, aux.acc_seg: 96.7106, loss: 0.0653 2022-05-06 11:21:45,421 - mmseg - INFO - Iter [67150/80000] lr: 2.306e-07, eta: 2:07:52, time: 0.536, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0388, decode.acc_seg: 97.8632, aux.loss_ce: 0.0256, aux.acc_seg: 96.7019, loss: 0.0644 2022-05-06 11:22:11,980 - mmseg - INFO - Iter [67200/80000] lr: 2.297e-07, eta: 2:07:22, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8643, aux.loss_ce: 0.0262, aux.acc_seg: 96.6634, loss: 0.0650 2022-05-06 11:22:38,545 - mmseg - INFO - Iter [67250/80000] lr: 2.288e-07, eta: 2:06:51, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8371, aux.loss_ce: 0.0252, aux.acc_seg: 96.7387, loss: 0.0637 2022-05-06 11:23:05,387 - mmseg - INFO - Iter [67300/80000] lr: 2.280e-07, eta: 2:06:21, time: 0.537, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0401, decode.acc_seg: 97.8029, aux.loss_ce: 0.0268, aux.acc_seg: 96.5904, loss: 0.0669 2022-05-06 11:23:31,884 - mmseg - INFO - Iter [67350/80000] lr: 2.271e-07, eta: 2:05:50, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.9254, aux.loss_ce: 0.0254, aux.acc_seg: 96.8637, loss: 0.0641 2022-05-06 11:24:00,924 - mmseg - INFO - Iter [67400/80000] lr: 2.262e-07, eta: 2:05:20, time: 0.581, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9280, aux.loss_ce: 0.0253, aux.acc_seg: 96.7673, loss: 0.0631 2022-05-06 11:24:27,398 - mmseg - INFO - Iter [67450/80000] lr: 2.253e-07, eta: 2:04:50, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9778, aux.loss_ce: 0.0248, aux.acc_seg: 96.8892, loss: 0.0627 2022-05-06 11:24:53,969 - mmseg - INFO - Iter [67500/80000] lr: 2.244e-07, eta: 2:04:20, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.6982, aux.loss_ce: 0.0278, aux.acc_seg: 96.4128, loss: 0.0696 2022-05-06 11:25:20,419 - mmseg - INFO - Iter [67550/80000] lr: 2.235e-07, eta: 2:03:49, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0389, decode.acc_seg: 97.9085, aux.loss_ce: 0.0256, aux.acc_seg: 96.8434, loss: 0.0645 2022-05-06 11:25:47,176 - mmseg - INFO - Iter [67600/80000] lr: 2.226e-07, eta: 2:03:19, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8220, aux.loss_ce: 0.0268, aux.acc_seg: 96.6001, loss: 0.0666 2022-05-06 11:26:13,792 - mmseg - INFO - Iter [67650/80000] lr: 2.217e-07, eta: 2:02:48, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0388, decode.acc_seg: 97.8862, aux.loss_ce: 0.0255, aux.acc_seg: 96.8016, loss: 0.0643 2022-05-06 11:26:40,630 - mmseg - INFO - Iter [67700/80000] lr: 2.208e-07, eta: 2:02:18, time: 0.537, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0410, decode.acc_seg: 97.7872, aux.loss_ce: 0.0271, aux.acc_seg: 96.6258, loss: 0.0681 2022-05-06 11:27:10,146 - mmseg - INFO - Iter [67750/80000] lr: 2.199e-07, eta: 2:01:48, time: 0.590, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0415, decode.acc_seg: 97.7010, aux.loss_ce: 0.0274, aux.acc_seg: 96.4803, loss: 0.0689 2022-05-06 11:27:36,626 - mmseg - INFO - Iter [67800/80000] lr: 2.190e-07, eta: 2:01:18, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9633, aux.loss_ce: 0.0251, aux.acc_seg: 96.8388, loss: 0.0628 2022-05-06 11:28:03,513 - mmseg - INFO - Iter [67850/80000] lr: 2.181e-07, eta: 2:00:47, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0371, decode.acc_seg: 97.9953, aux.loss_ce: 0.0248, aux.acc_seg: 96.8778, loss: 0.0619 2022-05-06 11:28:30,119 - mmseg - INFO - Iter [67900/80000] lr: 2.172e-07, eta: 2:00:17, time: 0.534, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.7676, aux.loss_ce: 0.0266, aux.acc_seg: 96.5566, loss: 0.0663 2022-05-06 11:28:56,670 - mmseg - INFO - Iter [67950/80000] lr: 2.163e-07, eta: 1:59:46, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0364, decode.acc_seg: 98.0557, aux.loss_ce: 0.0248, aux.acc_seg: 96.8739, loss: 0.0612 2022-05-06 11:29:23,369 - mmseg - INFO - Saving checkpoint at 68000 iterations 2022-05-06 11:29:44,412 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:29:44,420 - mmseg - INFO - Iter [68000/80000] lr: 2.154e-07, eta: 1:59:20, time: 0.953, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9415, aux.loss_ce: 0.0258, aux.acc_seg: 96.7458, loss: 0.0640 2022-05-06 11:30:14,342 - mmseg - INFO - Iter [68050/80000] lr: 2.145e-07, eta: 1:58:50, time: 0.601, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8616, aux.loss_ce: 0.0261, aux.acc_seg: 96.6708, loss: 0.0647 2022-05-06 11:30:40,842 - mmseg - INFO - Iter [68100/80000] lr: 2.136e-07, eta: 1:58:19, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9489, aux.loss_ce: 0.0254, aux.acc_seg: 96.7817, loss: 0.0631 2022-05-06 11:31:07,405 - mmseg - INFO - Iter [68150/80000] lr: 2.127e-07, eta: 1:57:49, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0349, decode.acc_seg: 98.0525, aux.loss_ce: 0.0234, aux.acc_seg: 96.9641, loss: 0.0583 2022-05-06 11:31:34,020 - mmseg - INFO - Iter [68200/80000] lr: 2.118e-07, eta: 1:57:19, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.8180, aux.loss_ce: 0.0270, aux.acc_seg: 96.6430, loss: 0.0674 2022-05-06 11:32:00,586 - mmseg - INFO - Iter [68250/80000] lr: 2.109e-07, eta: 1:56:48, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8394, aux.loss_ce: 0.0261, aux.acc_seg: 96.6622, loss: 0.0654 2022-05-06 11:32:27,072 - mmseg - INFO - Iter [68300/80000] lr: 2.100e-07, eta: 1:56:18, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.9328, aux.loss_ce: 0.0255, aux.acc_seg: 96.8150, loss: 0.0639 2022-05-06 11:32:56,547 - mmseg - INFO - Iter [68350/80000] lr: 2.091e-07, eta: 1:55:48, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.8886, aux.loss_ce: 0.0268, aux.acc_seg: 96.6766, loss: 0.0663 2022-05-06 11:33:23,051 - mmseg - INFO - Iter [68400/80000] lr: 2.082e-07, eta: 1:55:18, time: 0.532, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.9416, aux.loss_ce: 0.0257, aux.acc_seg: 96.7765, loss: 0.0637 2022-05-06 11:33:49,624 - mmseg - INFO - Iter [68450/80000] lr: 2.073e-07, eta: 1:54:47, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0369, decode.acc_seg: 97.9707, aux.loss_ce: 0.0245, aux.acc_seg: 96.8503, loss: 0.0614 2022-05-06 11:34:16,048 - mmseg - INFO - Iter [68500/80000] lr: 2.064e-07, eta: 1:54:17, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.8617, aux.loss_ce: 0.0264, aux.acc_seg: 96.6854, loss: 0.0654 2022-05-06 11:34:42,774 - mmseg - INFO - Iter [68550/80000] lr: 2.055e-07, eta: 1:53:47, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.8033, aux.loss_ce: 0.0267, aux.acc_seg: 96.5753, loss: 0.0670 2022-05-06 11:35:09,333 - mmseg - INFO - Iter [68600/80000] lr: 2.046e-07, eta: 1:53:16, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8321, aux.loss_ce: 0.0265, aux.acc_seg: 96.6621, loss: 0.0663 2022-05-06 11:35:38,469 - mmseg - INFO - Iter [68650/80000] lr: 2.037e-07, eta: 1:52:46, time: 0.583, data_time: 0.058, memory: 58091, decode.loss_ce: 0.0383, decode.acc_seg: 97.9226, aux.loss_ce: 0.0253, aux.acc_seg: 96.8277, loss: 0.0636 2022-05-06 11:36:04,972 - mmseg - INFO - Iter [68700/80000] lr: 2.028e-07, eta: 1:52:16, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0375, decode.acc_seg: 97.9004, aux.loss_ce: 0.0247, aux.acc_seg: 96.7457, loss: 0.0622 2022-05-06 11:36:31,423 - mmseg - INFO - Iter [68750/80000] lr: 2.019e-07, eta: 1:51:46, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0432, decode.acc_seg: 97.7446, aux.loss_ce: 0.0280, aux.acc_seg: 96.5668, loss: 0.0712 2022-05-06 11:36:58,578 - mmseg - INFO - Iter [68800/80000] lr: 2.010e-07, eta: 1:51:15, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8503, aux.loss_ce: 0.0257, aux.acc_seg: 96.6471, loss: 0.0644 2022-05-06 11:37:25,110 - mmseg - INFO - Iter [68850/80000] lr: 2.001e-07, eta: 1:50:45, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0395, decode.acc_seg: 97.8642, aux.loss_ce: 0.0267, aux.acc_seg: 96.6465, loss: 0.0662 2022-05-06 11:37:51,849 - mmseg - INFO - Iter [68900/80000] lr: 1.992e-07, eta: 1:50:15, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.9117, aux.loss_ce: 0.0254, aux.acc_seg: 96.7316, loss: 0.0634 2022-05-06 11:38:18,594 - mmseg - INFO - Iter [68950/80000] lr: 1.983e-07, eta: 1:49:44, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0354, decode.acc_seg: 97.9968, aux.loss_ce: 0.0237, aux.acc_seg: 96.8768, loss: 0.0591 2022-05-06 11:38:47,844 - mmseg - INFO - Saving checkpoint at 69000 iterations 2022-05-06 11:39:08,149 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:39:08,161 - mmseg - INFO - Iter [69000/80000] lr: 1.974e-07, eta: 1:49:18, time: 0.989, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0451, decode.acc_seg: 97.6813, aux.loss_ce: 0.0284, aux.acc_seg: 96.5235, loss: 0.0734 2022-05-06 11:39:35,355 - mmseg - INFO - Iter [69050/80000] lr: 1.965e-07, eta: 1:48:48, time: 0.545, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0407, decode.acc_seg: 97.7552, aux.loss_ce: 0.0270, aux.acc_seg: 96.5349, loss: 0.0677 2022-05-06 11:40:01,846 - mmseg - INFO - Iter [69100/80000] lr: 1.956e-07, eta: 1:48:17, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0353, decode.acc_seg: 98.0213, aux.loss_ce: 0.0239, aux.acc_seg: 96.8737, loss: 0.0592 2022-05-06 11:40:28,543 - mmseg - INFO - Iter [69150/80000] lr: 1.947e-07, eta: 1:47:47, time: 0.534, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.8765, aux.loss_ce: 0.0268, aux.acc_seg: 96.7135, loss: 0.0667 2022-05-06 11:40:55,019 - mmseg - INFO - Iter [69200/80000] lr: 1.939e-07, eta: 1:47:17, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8915, aux.loss_ce: 0.0261, aux.acc_seg: 96.7762, loss: 0.0658 2022-05-06 11:41:21,559 - mmseg - INFO - Iter [69250/80000] lr: 1.930e-07, eta: 1:46:46, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0362, decode.acc_seg: 98.0114, aux.loss_ce: 0.0242, aux.acc_seg: 96.9105, loss: 0.0604 2022-05-06 11:41:50,731 - mmseg - INFO - Iter [69300/80000] lr: 1.921e-07, eta: 1:46:16, time: 0.583, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8789, aux.loss_ce: 0.0255, aux.acc_seg: 96.7468, loss: 0.0638 2022-05-06 11:42:17,290 - mmseg - INFO - Iter [69350/80000] lr: 1.912e-07, eta: 1:45:46, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.8539, aux.loss_ce: 0.0253, aux.acc_seg: 96.6663, loss: 0.0631 2022-05-06 11:42:43,993 - mmseg - INFO - Iter [69400/80000] lr: 1.903e-07, eta: 1:45:16, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9318, aux.loss_ce: 0.0260, aux.acc_seg: 96.8070, loss: 0.0647 2022-05-06 11:43:10,458 - mmseg - INFO - Iter [69450/80000] lr: 1.894e-07, eta: 1:44:46, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.8428, aux.loss_ce: 0.0265, aux.acc_seg: 96.6310, loss: 0.0658 2022-05-06 11:43:37,090 - mmseg - INFO - Iter [69500/80000] lr: 1.885e-07, eta: 1:44:15, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9085, aux.loss_ce: 0.0256, aux.acc_seg: 96.6950, loss: 0.0634 2022-05-06 11:44:03,629 - mmseg - INFO - Iter [69550/80000] lr: 1.876e-07, eta: 1:43:45, time: 0.533, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9284, aux.loss_ce: 0.0262, aux.acc_seg: 96.7070, loss: 0.0644 2022-05-06 11:44:33,205 - mmseg - INFO - Iter [69600/80000] lr: 1.867e-07, eta: 1:43:15, time: 0.591, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0391, decode.acc_seg: 97.8069, aux.loss_ce: 0.0263, aux.acc_seg: 96.5222, loss: 0.0654 2022-05-06 11:44:59,930 - mmseg - INFO - Iter [69650/80000] lr: 1.858e-07, eta: 1:42:45, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.8831, aux.loss_ce: 0.0251, aux.acc_seg: 96.7372, loss: 0.0627 2022-05-06 11:45:26,430 - mmseg - INFO - Iter [69700/80000] lr: 1.849e-07, eta: 1:42:15, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.8822, aux.loss_ce: 0.0254, aux.acc_seg: 96.7228, loss: 0.0636 2022-05-06 11:45:53,281 - mmseg - INFO - Iter [69750/80000] lr: 1.840e-07, eta: 1:41:44, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0357, decode.acc_seg: 98.0018, aux.loss_ce: 0.0240, aux.acc_seg: 96.9256, loss: 0.0598 2022-05-06 11:46:19,683 - mmseg - INFO - Iter [69800/80000] lr: 1.831e-07, eta: 1:41:14, time: 0.528, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0381, decode.acc_seg: 97.9187, aux.loss_ce: 0.0256, aux.acc_seg: 96.7953, loss: 0.0637 2022-05-06 11:46:46,266 - mmseg - INFO - Iter [69850/80000] lr: 1.822e-07, eta: 1:40:44, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9518, aux.loss_ce: 0.0257, aux.acc_seg: 96.8163, loss: 0.0639 2022-05-06 11:47:15,252 - mmseg - INFO - Iter [69900/80000] lr: 1.813e-07, eta: 1:40:14, time: 0.578, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0373, decode.acc_seg: 97.9514, aux.loss_ce: 0.0247, aux.acc_seg: 96.8550, loss: 0.0620 2022-05-06 11:47:41,771 - mmseg - INFO - Iter [69950/80000] lr: 1.804e-07, eta: 1:39:44, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0404, decode.acc_seg: 97.7555, aux.loss_ce: 0.0268, aux.acc_seg: 96.6180, loss: 0.0673 2022-05-06 11:48:08,271 - mmseg - INFO - Saving checkpoint at 70000 iterations 2022-05-06 11:48:28,162 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:48:28,166 - mmseg - INFO - Iter [70000/80000] lr: 1.795e-07, eta: 1:39:16, time: 0.926, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.8337, aux.loss_ce: 0.0264, aux.acc_seg: 96.6721, loss: 0.0661 2022-05-06 11:48:54,865 - mmseg - INFO - Iter [70050/80000] lr: 1.786e-07, eta: 1:38:46, time: 0.536, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.8492, aux.loss_ce: 0.0259, aux.acc_seg: 96.6076, loss: 0.0639 2022-05-06 11:49:21,313 - mmseg - INFO - Iter [70100/80000] lr: 1.777e-07, eta: 1:38:16, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9396, aux.loss_ce: 0.0251, aux.acc_seg: 96.8524, loss: 0.0625 2022-05-06 11:49:47,916 - mmseg - INFO - Iter [70150/80000] lr: 1.768e-07, eta: 1:37:46, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9939, aux.loss_ce: 0.0247, aux.acc_seg: 96.8411, loss: 0.0613 2022-05-06 11:50:14,299 - mmseg - INFO - Iter [70200/80000] lr: 1.759e-07, eta: 1:37:15, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.9390, aux.loss_ce: 0.0253, aux.acc_seg: 96.7427, loss: 0.0626 2022-05-06 11:50:43,268 - mmseg - INFO - Iter [70250/80000] lr: 1.750e-07, eta: 1:36:46, time: 0.580, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8469, aux.loss_ce: 0.0264, aux.acc_seg: 96.7076, loss: 0.0661 2022-05-06 11:51:09,702 - mmseg - INFO - Iter [70300/80000] lr: 1.741e-07, eta: 1:36:15, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0381, decode.acc_seg: 97.8615, aux.loss_ce: 0.0255, aux.acc_seg: 96.7230, loss: 0.0635 2022-05-06 11:51:36,453 - mmseg - INFO - Iter [70350/80000] lr: 1.732e-07, eta: 1:35:45, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.7616, aux.loss_ce: 0.0271, aux.acc_seg: 96.5177, loss: 0.0675 2022-05-06 11:52:02,934 - mmseg - INFO - Iter [70400/80000] lr: 1.723e-07, eta: 1:35:15, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0365, decode.acc_seg: 98.0364, aux.loss_ce: 0.0240, aux.acc_seg: 97.0175, loss: 0.0605 2022-05-06 11:52:29,282 - mmseg - INFO - Iter [70450/80000] lr: 1.714e-07, eta: 1:34:45, time: 0.527, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.8686, aux.loss_ce: 0.0262, aux.acc_seg: 96.6607, loss: 0.0652 2022-05-06 11:52:55,926 - mmseg - INFO - Iter [70500/80000] lr: 1.705e-07, eta: 1:34:15, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0388, decode.acc_seg: 97.9141, aux.loss_ce: 0.0259, aux.acc_seg: 96.7768, loss: 0.0647 2022-05-06 11:53:25,581 - mmseg - INFO - Iter [70550/80000] lr: 1.696e-07, eta: 1:33:45, time: 0.593, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.7344, aux.loss_ce: 0.0266, aux.acc_seg: 96.5160, loss: 0.0672 2022-05-06 11:53:52,578 - mmseg - INFO - Iter [70600/80000] lr: 1.687e-07, eta: 1:33:15, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.8979, aux.loss_ce: 0.0252, aux.acc_seg: 96.6889, loss: 0.0624 2022-05-06 11:54:19,420 - mmseg - INFO - Iter [70650/80000] lr: 1.678e-07, eta: 1:32:44, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.8342, aux.loss_ce: 0.0254, aux.acc_seg: 96.6347, loss: 0.0634 2022-05-06 11:54:45,875 - mmseg - INFO - Iter [70700/80000] lr: 1.669e-07, eta: 1:32:14, time: 0.531, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0363, decode.acc_seg: 97.9816, aux.loss_ce: 0.0243, aux.acc_seg: 96.8375, loss: 0.0606 2022-05-06 11:55:12,284 - mmseg - INFO - Iter [70750/80000] lr: 1.660e-07, eta: 1:31:44, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0411, decode.acc_seg: 97.8198, aux.loss_ce: 0.0273, aux.acc_seg: 96.6597, loss: 0.0684 2022-05-06 11:55:38,862 - mmseg - INFO - Iter [70800/80000] lr: 1.651e-07, eta: 1:31:14, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 98.0042, aux.loss_ce: 0.0249, aux.acc_seg: 96.9076, loss: 0.0619 2022-05-06 11:56:08,164 - mmseg - INFO - Iter [70850/80000] lr: 1.642e-07, eta: 1:30:44, time: 0.586, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0388, decode.acc_seg: 97.9077, aux.loss_ce: 0.0261, aux.acc_seg: 96.7293, loss: 0.0649 2022-05-06 11:56:34,615 - mmseg - INFO - Iter [70900/80000] lr: 1.633e-07, eta: 1:30:14, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.9366, aux.loss_ce: 0.0260, aux.acc_seg: 96.7739, loss: 0.0645 2022-05-06 11:57:01,094 - mmseg - INFO - Iter [70950/80000] lr: 1.624e-07, eta: 1:29:44, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8909, aux.loss_ce: 0.0259, aux.acc_seg: 96.6943, loss: 0.0643 2022-05-06 11:57:27,730 - mmseg - INFO - Saving checkpoint at 71000 iterations 2022-05-06 11:57:47,914 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 11:57:47,922 - mmseg - INFO - Iter [71000/80000] lr: 1.615e-07, eta: 1:29:16, time: 0.934, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0385, decode.acc_seg: 97.9571, aux.loss_ce: 0.0255, aux.acc_seg: 96.8555, loss: 0.0640 2022-05-06 11:58:14,669 - mmseg - INFO - Iter [71050/80000] lr: 1.606e-07, eta: 1:28:46, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0389, decode.acc_seg: 97.9070, aux.loss_ce: 0.0261, aux.acc_seg: 96.7432, loss: 0.0650 2022-05-06 11:58:41,469 - mmseg - INFO - Iter [71100/80000] lr: 1.598e-07, eta: 1:28:16, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0368, decode.acc_seg: 98.0098, aux.loss_ce: 0.0250, aux.acc_seg: 96.8935, loss: 0.0618 2022-05-06 11:59:10,869 - mmseg - INFO - Iter [71150/80000] lr: 1.589e-07, eta: 1:27:46, time: 0.588, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8894, aux.loss_ce: 0.0259, aux.acc_seg: 96.6819, loss: 0.0644 2022-05-06 11:59:37,375 - mmseg - INFO - Iter [71200/80000] lr: 1.580e-07, eta: 1:27:16, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0381, decode.acc_seg: 97.9274, aux.loss_ce: 0.0252, aux.acc_seg: 96.8345, loss: 0.0634 2022-05-06 12:00:06,099 - mmseg - INFO - Iter [71250/80000] lr: 1.571e-07, eta: 1:26:46, time: 0.574, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0371, decode.acc_seg: 97.9925, aux.loss_ce: 0.0250, aux.acc_seg: 96.8772, loss: 0.0621 2022-05-06 12:00:32,792 - mmseg - INFO - Iter [71300/80000] lr: 1.562e-07, eta: 1:26:16, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.9191, aux.loss_ce: 0.0268, aux.acc_seg: 96.7293, loss: 0.0662 2022-05-06 12:00:59,745 - mmseg - INFO - Iter [71350/80000] lr: 1.553e-07, eta: 1:25:46, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0368, decode.acc_seg: 97.9317, aux.loss_ce: 0.0250, aux.acc_seg: 96.7544, loss: 0.0617 2022-05-06 12:01:26,429 - mmseg - INFO - Iter [71400/80000] lr: 1.544e-07, eta: 1:25:16, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0402, decode.acc_seg: 97.8011, aux.loss_ce: 0.0265, aux.acc_seg: 96.6224, loss: 0.0667 2022-05-06 12:01:55,533 - mmseg - INFO - Iter [71450/80000] lr: 1.535e-07, eta: 1:24:46, time: 0.582, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8387, aux.loss_ce: 0.0267, aux.acc_seg: 96.6149, loss: 0.0665 2022-05-06 12:02:22,234 - mmseg - INFO - Iter [71500/80000] lr: 1.526e-07, eta: 1:24:16, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9768, aux.loss_ce: 0.0246, aux.acc_seg: 96.8521, loss: 0.0612 2022-05-06 12:02:48,679 - mmseg - INFO - Iter [71550/80000] lr: 1.517e-07, eta: 1:23:46, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0375, decode.acc_seg: 97.9098, aux.loss_ce: 0.0244, aux.acc_seg: 96.8557, loss: 0.0620 2022-05-06 12:03:15,213 - mmseg - INFO - Iter [71600/80000] lr: 1.508e-07, eta: 1:23:16, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0402, decode.acc_seg: 97.8690, aux.loss_ce: 0.0266, aux.acc_seg: 96.7091, loss: 0.0668 2022-05-06 12:03:41,804 - mmseg - INFO - Iter [71650/80000] lr: 1.499e-07, eta: 1:22:45, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9062, aux.loss_ce: 0.0256, aux.acc_seg: 96.7236, loss: 0.0636 2022-05-06 12:04:08,329 - mmseg - INFO - Iter [71700/80000] lr: 1.490e-07, eta: 1:22:15, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8634, aux.loss_ce: 0.0260, aux.acc_seg: 96.6881, loss: 0.0647 2022-05-06 12:04:35,098 - mmseg - INFO - Iter [71750/80000] lr: 1.481e-07, eta: 1:21:45, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8428, aux.loss_ce: 0.0258, aux.acc_seg: 96.6429, loss: 0.0642 2022-05-06 12:05:04,146 - mmseg - INFO - Iter [71800/80000] lr: 1.472e-07, eta: 1:21:15, time: 0.581, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0368, decode.acc_seg: 97.9274, aux.loss_ce: 0.0243, aux.acc_seg: 96.8171, loss: 0.0610 2022-05-06 12:05:30,601 - mmseg - INFO - Iter [71850/80000] lr: 1.463e-07, eta: 1:20:45, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9473, aux.loss_ce: 0.0250, aux.acc_seg: 96.7412, loss: 0.0616 2022-05-06 12:05:57,300 - mmseg - INFO - Iter [71900/80000] lr: 1.454e-07, eta: 1:20:15, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0371, decode.acc_seg: 97.9004, aux.loss_ce: 0.0246, aux.acc_seg: 96.7409, loss: 0.0618 2022-05-06 12:06:23,777 - mmseg - INFO - Iter [71950/80000] lr: 1.445e-07, eta: 1:19:45, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0369, decode.acc_seg: 97.9168, aux.loss_ce: 0.0245, aux.acc_seg: 96.7876, loss: 0.0614 2022-05-06 12:06:50,899 - mmseg - INFO - Saving checkpoint at 72000 iterations 2022-05-06 12:07:11,443 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:07:11,445 - mmseg - INFO - Iter [72000/80000] lr: 1.436e-07, eta: 1:19:17, time: 0.952, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.9091, aux.loss_ce: 0.0259, aux.acc_seg: 96.7820, loss: 0.0651 2022-05-06 12:11:21,290 - mmseg - INFO - per class results: 2022-05-06 12:11:21,304 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 93.18 | 96.99 | | bag | 45.41 | 55.84 | | bed | 34.85 | 43.05 | | bedclothes | 46.21 | 69.09 | | bench | 32.92 | 41.17 | | bicycle | 84.74 | 93.53 | | bird | 94.24 | 98.06 | | boat | 85.7 | 92.32 | | book | 61.06 | 74.5 | | bottle | 88.83 | 96.92 | | building | 68.25 | 80.15 | | bus | 94.59 | 97.46 | | cabinet | 50.74 | 65.18 | | car | 94.01 | 97.03 | | cat | 93.37 | 98.61 | | ceiling | 60.08 | 76.94 | | chair | 64.96 | 78.16 | | cloth | 26.28 | 33.61 | | computer | 62.92 | 70.63 | | cow | 95.82 | 98.38 | | cup | 47.56 | 65.59 | | curtain | 60.85 | 75.2 | | dog | 91.87 | 98.05 | | door | 35.43 | 48.14 | | fence | 46.02 | 59.7 | | floor | 76.5 | 90.39 | | flower | 35.52 | 45.53 | | food | 43.17 | 54.0 | | grass | 83.32 | 92.38 | | ground | 57.49 | 71.07 | | horse | 94.59 | 97.9 | | keyboard | 89.75 | 95.55 | | light | 59.67 | 73.51 | | motorbike | 90.83 | 97.09 | | mountain | 58.73 | 73.31 | | mouse | 79.3 | 93.68 | | person | 90.63 | 97.15 | | plate | 31.54 | 44.84 | | platform | 58.72 | 77.19 | | pottedplant | 81.78 | 90.39 | | road | 53.64 | 70.83 | | rock | 56.58 | 64.5 | | sheep | 94.97 | 98.45 | | shelves | 35.17 | 45.17 | | sidewalk | 33.04 | 47.41 | | sign | 53.18 | 60.05 | | sky | 95.11 | 97.65 | | snow | 76.57 | 90.45 | | sofa | 60.35 | 69.28 | | table | 73.55 | 84.65 | | track | 73.01 | 84.56 | | train | 93.18 | 97.27 | | tree | 81.98 | 90.89 | | truck | 51.84 | 58.74 | | tvmonitor | 90.96 | 94.51 | | wall | 74.44 | 87.35 | | water | 92.19 | 96.31 | | window | 47.48 | 61.67 | | wood | 25.66 | 31.98 | +-------------+-------+-------+ 2022-05-06 12:11:21,304 - mmseg - INFO - Summary: 2022-05-06 12:11:21,304 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 86.73 | 67.02 | 76.78 | +-------+-------+-------+ 2022-05-06 12:11:21,306 - mmseg - INFO - The previous best checkpoint /mnt/lustre/duanyuchen/projects/DenseAdaptor/segmentation/work_dirs/upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2/best_mIoU_iter_64000.pth was removed 2022-05-06 12:11:42,599 - mmseg - INFO - Now best checkpoint is saved as best_mIoU_iter_72000.pth. 2022-05-06 12:11:42,604 - mmseg - INFO - Best mIoU is 0.6702 at 72000 iter. 2022-05-06 12:11:42,626 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:11:42,627 - mmseg - INFO - Iter(val) [638] aAcc: 0.8673, mIoU: 0.6702, mAcc: 0.7678, IoU.aeroplane: 0.9318, IoU.bag: 0.4541, IoU.bed: 0.3485, IoU.bedclothes: 0.4621, IoU.bench: 0.3292, IoU.bicycle: 0.8474, IoU.bird: 0.9424, IoU.boat: 0.8570, IoU.book: 0.6106, IoU.bottle: 0.8883, IoU.building: 0.6825, IoU.bus: 0.9459, IoU.cabinet: 0.5074, IoU.car: 0.9401, IoU.cat: 0.9337, IoU.ceiling: 0.6008, IoU.chair: 0.6496, IoU.cloth: 0.2628, IoU.computer: 0.6292, IoU.cow: 0.9582, IoU.cup: 0.4756, IoU.curtain: 0.6085, IoU.dog: 0.9187, IoU.door: 0.3543, IoU.fence: 0.4602, IoU.floor: 0.7650, IoU.flower: 0.3552, IoU.food: 0.4317, IoU.grass: 0.8332, IoU.ground: 0.5749, IoU.horse: 0.9459, IoU.keyboard: 0.8975, IoU.light: 0.5967, IoU.motorbike: 0.9083, IoU.mountain: 0.5873, IoU.mouse: 0.7930, IoU.person: 0.9063, IoU.plate: 0.3154, IoU.platform: 0.5872, IoU.pottedplant: 0.8178, IoU.road: 0.5364, IoU.rock: 0.5658, IoU.sheep: 0.9497, IoU.shelves: 0.3517, IoU.sidewalk: 0.3304, IoU.sign: 0.5318, IoU.sky: 0.9511, IoU.snow: 0.7657, IoU.sofa: 0.6035, IoU.table: 0.7355, IoU.track: 0.7301, IoU.train: 0.9318, IoU.tree: 0.8198, IoU.truck: 0.5184, IoU.tvmonitor: 0.9096, IoU.wall: 0.7444, IoU.water: 0.9219, IoU.window: 0.4748, IoU.wood: 0.2566, Acc.aeroplane: 0.9699, Acc.bag: 0.5584, Acc.bed: 0.4305, Acc.bedclothes: 0.6909, Acc.bench: 0.4117, Acc.bicycle: 0.9353, Acc.bird: 0.9806, Acc.boat: 0.9232, Acc.book: 0.7450, Acc.bottle: 0.9692, Acc.building: 0.8015, Acc.bus: 0.9746, Acc.cabinet: 0.6518, Acc.car: 0.9703, Acc.cat: 0.9861, Acc.ceiling: 0.7694, Acc.chair: 0.7816, Acc.cloth: 0.3361, Acc.computer: 0.7063, Acc.cow: 0.9838, Acc.cup: 0.6559, Acc.curtain: 0.7520, Acc.dog: 0.9805, Acc.door: 0.4814, Acc.fence: 0.5970, Acc.floor: 0.9039, Acc.flower: 0.4553, Acc.food: 0.5400, Acc.grass: 0.9238, Acc.ground: 0.7107, Acc.horse: 0.9790, Acc.keyboard: 0.9555, Acc.light: 0.7351, Acc.motorbike: 0.9709, Acc.mountain: 0.7331, Acc.mouse: 0.9368, Acc.person: 0.9715, Acc.plate: 0.4484, Acc.platform: 0.7719, Acc.pottedplant: 0.9039, Acc.road: 0.7083, Acc.rock: 0.6450, Acc.sheep: 0.9845, Acc.shelves: 0.4517, Acc.sidewalk: 0.4741, Acc.sign: 0.6005, Acc.sky: 0.9765, Acc.snow: 0.9045, Acc.sofa: 0.6928, Acc.table: 0.8465, Acc.track: 0.8456, Acc.train: 0.9727, Acc.tree: 0.9089, Acc.truck: 0.5874, Acc.tvmonitor: 0.9451, Acc.wall: 0.8735, Acc.water: 0.9631, Acc.window: 0.6167, Acc.wood: 0.3198 2022-05-06 12:12:09,822 - mmseg - INFO - Iter [72050/80000] lr: 1.427e-07, eta: 1:19:17, time: 5.969, data_time: 5.432, memory: 58091, decode.loss_ce: 0.0365, decode.acc_seg: 97.9846, aux.loss_ce: 0.0246, aux.acc_seg: 96.8425, loss: 0.0610 2022-05-06 12:12:39,072 - mmseg - INFO - Iter [72100/80000] lr: 1.418e-07, eta: 1:18:47, time: 0.585, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0350, decode.acc_seg: 97.9895, aux.loss_ce: 0.0233, aux.acc_seg: 96.8863, loss: 0.0582 2022-05-06 12:13:05,465 - mmseg - INFO - Iter [72150/80000] lr: 1.409e-07, eta: 1:18:17, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0373, decode.acc_seg: 97.9996, aux.loss_ce: 0.0251, aux.acc_seg: 96.8637, loss: 0.0624 2022-05-06 12:13:31,875 - mmseg - INFO - Iter [72200/80000] lr: 1.400e-07, eta: 1:17:47, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9029, aux.loss_ce: 0.0254, aux.acc_seg: 96.7562, loss: 0.0634 2022-05-06 12:13:58,445 - mmseg - INFO - Iter [72250/80000] lr: 1.391e-07, eta: 1:17:16, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0388, decode.acc_seg: 97.8982, aux.loss_ce: 0.0263, aux.acc_seg: 96.6858, loss: 0.0651 2022-05-06 12:14:25,019 - mmseg - INFO - Iter [72300/80000] lr: 1.382e-07, eta: 1:16:46, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8867, aux.loss_ce: 0.0267, aux.acc_seg: 96.6644, loss: 0.0659 2022-05-06 12:14:51,690 - mmseg - INFO - Iter [72350/80000] lr: 1.373e-07, eta: 1:16:16, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9538, aux.loss_ce: 0.0251, aux.acc_seg: 96.7843, loss: 0.0625 2022-05-06 12:15:20,989 - mmseg - INFO - Iter [72400/80000] lr: 1.364e-07, eta: 1:15:46, time: 0.586, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0417, decode.acc_seg: 97.7316, aux.loss_ce: 0.0283, aux.acc_seg: 96.4363, loss: 0.0700 2022-05-06 12:15:47,840 - mmseg - INFO - Iter [72450/80000] lr: 1.355e-07, eta: 1:15:16, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9230, aux.loss_ce: 0.0262, aux.acc_seg: 96.6935, loss: 0.0648 2022-05-06 12:16:14,379 - mmseg - INFO - Iter [72500/80000] lr: 1.346e-07, eta: 1:14:45, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0357, decode.acc_seg: 97.9712, aux.loss_ce: 0.0245, aux.acc_seg: 96.7913, loss: 0.0602 2022-05-06 12:16:41,090 - mmseg - INFO - Iter [72550/80000] lr: 1.337e-07, eta: 1:14:15, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8776, aux.loss_ce: 0.0258, aux.acc_seg: 96.6986, loss: 0.0642 2022-05-06 12:17:07,969 - mmseg - INFO - Iter [72600/80000] lr: 1.328e-07, eta: 1:13:45, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0391, decode.acc_seg: 97.8628, aux.loss_ce: 0.0259, aux.acc_seg: 96.7056, loss: 0.0650 2022-05-06 12:17:34,405 - mmseg - INFO - Iter [72650/80000] lr: 1.319e-07, eta: 1:13:15, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 98.0024, aux.loss_ce: 0.0249, aux.acc_seg: 96.8906, loss: 0.0619 2022-05-06 12:18:03,730 - mmseg - INFO - Iter [72700/80000] lr: 1.310e-07, eta: 1:12:45, time: 0.587, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0405, decode.acc_seg: 97.7907, aux.loss_ce: 0.0260, aux.acc_seg: 96.6729, loss: 0.0665 2022-05-06 12:18:30,390 - mmseg - INFO - Iter [72750/80000] lr: 1.301e-07, eta: 1:12:15, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9065, aux.loss_ce: 0.0250, aux.acc_seg: 96.7435, loss: 0.0619 2022-05-06 12:18:57,271 - mmseg - INFO - Iter [72800/80000] lr: 1.292e-07, eta: 1:11:44, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0353, decode.acc_seg: 98.0516, aux.loss_ce: 0.0234, aux.acc_seg: 96.9754, loss: 0.0587 2022-05-06 12:19:23,772 - mmseg - INFO - Iter [72850/80000] lr: 1.283e-07, eta: 1:11:14, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0365, decode.acc_seg: 97.9999, aux.loss_ce: 0.0243, aux.acc_seg: 96.9437, loss: 0.0608 2022-05-06 12:19:50,208 - mmseg - INFO - Iter [72900/80000] lr: 1.274e-07, eta: 1:10:44, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0389, decode.acc_seg: 97.8511, aux.loss_ce: 0.0271, aux.acc_seg: 96.5364, loss: 0.0660 2022-05-06 12:20:16,764 - mmseg - INFO - Iter [72950/80000] lr: 1.265e-07, eta: 1:10:14, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0369, decode.acc_seg: 97.9979, aux.loss_ce: 0.0246, aux.acc_seg: 96.8825, loss: 0.0615 2022-05-06 12:20:43,402 - mmseg - INFO - Saving checkpoint at 73000 iterations 2022-05-06 12:21:04,426 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:21:04,434 - mmseg - INFO - Iter [73000/80000] lr: 1.257e-07, eta: 1:09:46, time: 0.952, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0402, decode.acc_seg: 97.8201, aux.loss_ce: 0.0275, aux.acc_seg: 96.5885, loss: 0.0677 2022-05-06 12:21:34,051 - mmseg - INFO - Iter [73050/80000] lr: 1.248e-07, eta: 1:09:16, time: 0.594, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0362, decode.acc_seg: 97.9854, aux.loss_ce: 0.0249, aux.acc_seg: 96.8025, loss: 0.0611 2022-05-06 12:22:00,704 - mmseg - INFO - Iter [73100/80000] lr: 1.239e-07, eta: 1:08:45, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0422, decode.acc_seg: 97.7915, aux.loss_ce: 0.0275, aux.acc_seg: 96.6493, loss: 0.0697 2022-05-06 12:22:27,310 - mmseg - INFO - Iter [73150/80000] lr: 1.230e-07, eta: 1:08:15, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0363, decode.acc_seg: 98.0104, aux.loss_ce: 0.0244, aux.acc_seg: 96.8849, loss: 0.0607 2022-05-06 12:22:53,683 - mmseg - INFO - Iter [73200/80000] lr: 1.221e-07, eta: 1:07:45, time: 0.527, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0397, decode.acc_seg: 97.7377, aux.loss_ce: 0.0270, aux.acc_seg: 96.4337, loss: 0.0667 2022-05-06 12:23:20,171 - mmseg - INFO - Iter [73250/80000] lr: 1.212e-07, eta: 1:07:15, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0371, decode.acc_seg: 97.9747, aux.loss_ce: 0.0249, aux.acc_seg: 96.8626, loss: 0.0620 2022-05-06 12:23:46,785 - mmseg - INFO - Iter [73300/80000] lr: 1.203e-07, eta: 1:06:45, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8229, aux.loss_ce: 0.0270, aux.acc_seg: 96.6081, loss: 0.0668 2022-05-06 12:24:16,181 - mmseg - INFO - Iter [73350/80000] lr: 1.194e-07, eta: 1:06:15, time: 0.588, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9612, aux.loss_ce: 0.0256, aux.acc_seg: 96.7863, loss: 0.0634 2022-05-06 12:24:42,754 - mmseg - INFO - Iter [73400/80000] lr: 1.185e-07, eta: 1:05:44, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9893, aux.loss_ce: 0.0249, aux.acc_seg: 96.8113, loss: 0.0615 2022-05-06 12:25:09,269 - mmseg - INFO - Iter [73450/80000] lr: 1.176e-07, eta: 1:05:14, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0368, decode.acc_seg: 97.9795, aux.loss_ce: 0.0249, aux.acc_seg: 96.8269, loss: 0.0618 2022-05-06 12:25:35,700 - mmseg - INFO - Iter [73500/80000] lr: 1.167e-07, eta: 1:04:44, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.8652, aux.loss_ce: 0.0249, aux.acc_seg: 96.7207, loss: 0.0623 2022-05-06 12:26:02,249 - mmseg - INFO - Iter [73550/80000] lr: 1.158e-07, eta: 1:04:14, time: 0.531, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9705, aux.loss_ce: 0.0250, aux.acc_seg: 96.8687, loss: 0.0627 2022-05-06 12:26:29,215 - mmseg - INFO - Iter [73600/80000] lr: 1.149e-07, eta: 1:03:44, time: 0.537, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0383, decode.acc_seg: 97.8554, aux.loss_ce: 0.0256, aux.acc_seg: 96.6749, loss: 0.0639 2022-05-06 12:26:58,672 - mmseg - INFO - Iter [73650/80000] lr: 1.140e-07, eta: 1:03:14, time: 0.591, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.9060, aux.loss_ce: 0.0262, aux.acc_seg: 96.6806, loss: 0.0649 2022-05-06 12:27:25,233 - mmseg - INFO - Iter [73700/80000] lr: 1.131e-07, eta: 1:02:44, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0359, decode.acc_seg: 98.0017, aux.loss_ce: 0.0239, aux.acc_seg: 96.8990, loss: 0.0598 2022-05-06 12:27:51,778 - mmseg - INFO - Iter [73750/80000] lr: 1.122e-07, eta: 1:02:14, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0418, decode.acc_seg: 97.7789, aux.loss_ce: 0.0278, aux.acc_seg: 96.5445, loss: 0.0696 2022-05-06 12:28:18,322 - mmseg - INFO - Iter [73800/80000] lr: 1.113e-07, eta: 1:01:43, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0373, decode.acc_seg: 97.9103, aux.loss_ce: 0.0249, aux.acc_seg: 96.7252, loss: 0.0622 2022-05-06 12:28:44,823 - mmseg - INFO - Iter [73850/80000] lr: 1.104e-07, eta: 1:01:13, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.8823, aux.loss_ce: 0.0264, aux.acc_seg: 96.7111, loss: 0.0658 2022-05-06 12:29:11,296 - mmseg - INFO - Iter [73900/80000] lr: 1.095e-07, eta: 1:00:43, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8785, aux.loss_ce: 0.0256, aux.acc_seg: 96.7365, loss: 0.0642 2022-05-06 12:29:40,195 - mmseg - INFO - Iter [73950/80000] lr: 1.086e-07, eta: 1:00:13, time: 0.578, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.9787, aux.loss_ce: 0.0249, aux.acc_seg: 96.8641, loss: 0.0621 2022-05-06 12:30:06,682 - mmseg - INFO - Saving checkpoint at 74000 iterations 2022-05-06 12:30:27,946 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:30:27,950 - mmseg - INFO - Iter [74000/80000] lr: 1.077e-07, eta: 0:59:45, time: 0.952, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 98.0012, aux.loss_ce: 0.0253, aux.acc_seg: 96.8745, loss: 0.0630 2022-05-06 12:30:54,931 - mmseg - INFO - Iter [74050/80000] lr: 1.068e-07, eta: 0:59:15, time: 0.543, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0362, decode.acc_seg: 97.9016, aux.loss_ce: 0.0241, aux.acc_seg: 96.7745, loss: 0.0603 2022-05-06 12:31:21,673 - mmseg - INFO - Iter [74100/80000] lr: 1.059e-07, eta: 0:58:45, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0426, decode.acc_seg: 97.7655, aux.loss_ce: 0.0283, aux.acc_seg: 96.4978, loss: 0.0709 2022-05-06 12:31:48,278 - mmseg - INFO - Iter [74150/80000] lr: 1.050e-07, eta: 0:58:14, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0349, decode.acc_seg: 98.0500, aux.loss_ce: 0.0235, aux.acc_seg: 96.9347, loss: 0.0585 2022-05-06 12:32:14,715 - mmseg - INFO - Iter [74200/80000] lr: 1.041e-07, eta: 0:57:44, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0385, decode.acc_seg: 97.8868, aux.loss_ce: 0.0260, aux.acc_seg: 96.6904, loss: 0.0645 2022-05-06 12:32:41,180 - mmseg - INFO - Iter [74250/80000] lr: 1.032e-07, eta: 0:57:14, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0381, decode.acc_seg: 97.9204, aux.loss_ce: 0.0257, aux.acc_seg: 96.7451, loss: 0.0639 2022-05-06 12:33:10,409 - mmseg - INFO - Iter [74300/80000] lr: 1.023e-07, eta: 0:56:44, time: 0.585, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.9389, aux.loss_ce: 0.0254, aux.acc_seg: 96.8005, loss: 0.0634 2022-05-06 12:33:36,969 - mmseg - INFO - Iter [74350/80000] lr: 1.014e-07, eta: 0:56:14, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 98.0078, aux.loss_ce: 0.0255, aux.acc_seg: 96.8855, loss: 0.0634 2022-05-06 12:34:03,726 - mmseg - INFO - Iter [74400/80000] lr: 1.005e-07, eta: 0:55:44, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0385, decode.acc_seg: 97.8489, aux.loss_ce: 0.0255, aux.acc_seg: 96.6781, loss: 0.0640 2022-05-06 12:34:30,412 - mmseg - INFO - Iter [74450/80000] lr: 9.963e-08, eta: 0:55:14, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.8844, aux.loss_ce: 0.0260, aux.acc_seg: 96.6550, loss: 0.0638 2022-05-06 12:34:57,101 - mmseg - INFO - Iter [74500/80000] lr: 9.873e-08, eta: 0:54:44, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0354, decode.acc_seg: 98.0459, aux.loss_ce: 0.0245, aux.acc_seg: 96.8353, loss: 0.0599 2022-05-06 12:35:23,659 - mmseg - INFO - Iter [74550/80000] lr: 9.783e-08, eta: 0:54:14, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9010, aux.loss_ce: 0.0259, aux.acc_seg: 96.7206, loss: 0.0645 2022-05-06 12:35:52,805 - mmseg - INFO - Iter [74600/80000] lr: 9.693e-08, eta: 0:53:44, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0360, decode.acc_seg: 97.9683, aux.loss_ce: 0.0242, aux.acc_seg: 96.8068, loss: 0.0602 2022-05-06 12:36:19,287 - mmseg - INFO - Iter [74650/80000] lr: 9.604e-08, eta: 0:53:14, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0364, decode.acc_seg: 98.0097, aux.loss_ce: 0.0248, aux.acc_seg: 96.8535, loss: 0.0612 2022-05-06 12:36:45,836 - mmseg - INFO - Iter [74700/80000] lr: 9.514e-08, eta: 0:52:44, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.7968, aux.loss_ce: 0.0269, aux.acc_seg: 96.5350, loss: 0.0666 2022-05-06 12:37:12,433 - mmseg - INFO - Iter [74750/80000] lr: 9.424e-08, eta: 0:52:14, time: 0.532, data_time: 0.006, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.9024, aux.loss_ce: 0.0260, aux.acc_seg: 96.7384, loss: 0.0644 2022-05-06 12:37:39,010 - mmseg - INFO - Iter [74800/80000] lr: 9.334e-08, eta: 0:51:43, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9016, aux.loss_ce: 0.0258, aux.acc_seg: 96.7265, loss: 0.0639 2022-05-06 12:38:05,529 - mmseg - INFO - Iter [74850/80000] lr: 9.245e-08, eta: 0:51:13, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0392, decode.acc_seg: 97.8999, aux.loss_ce: 0.0259, aux.acc_seg: 96.7904, loss: 0.0651 2022-05-06 12:38:34,910 - mmseg - INFO - Iter [74900/80000] lr: 9.155e-08, eta: 0:50:44, time: 0.588, data_time: 0.055, memory: 58091, decode.loss_ce: 0.0361, decode.acc_seg: 98.0218, aux.loss_ce: 0.0245, aux.acc_seg: 96.9100, loss: 0.0606 2022-05-06 12:39:01,578 - mmseg - INFO - Iter [74950/80000] lr: 9.065e-08, eta: 0:50:13, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9340, aux.loss_ce: 0.0257, aux.acc_seg: 96.7547, loss: 0.0638 2022-05-06 12:39:28,416 - mmseg - INFO - Saving checkpoint at 75000 iterations 2022-05-06 12:39:48,903 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:39:48,910 - mmseg - INFO - Iter [75000/80000] lr: 8.976e-08, eta: 0:49:45, time: 0.944, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0399, decode.acc_seg: 97.8366, aux.loss_ce: 0.0267, aux.acc_seg: 96.6458, loss: 0.0666 2022-05-06 12:40:15,913 - mmseg - INFO - Iter [75050/80000] lr: 8.886e-08, eta: 0:49:15, time: 0.543, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9904, aux.loss_ce: 0.0256, aux.acc_seg: 96.8435, loss: 0.0633 2022-05-06 12:40:42,339 - mmseg - INFO - Iter [75100/80000] lr: 8.796e-08, eta: 0:48:45, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0371, decode.acc_seg: 97.9092, aux.loss_ce: 0.0251, aux.acc_seg: 96.7562, loss: 0.0622 2022-05-06 12:41:09,012 - mmseg - INFO - Iter [75150/80000] lr: 8.706e-08, eta: 0:48:15, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.8888, aux.loss_ce: 0.0266, aux.acc_seg: 96.7235, loss: 0.0661 2022-05-06 12:41:38,147 - mmseg - INFO - Iter [75200/80000] lr: 8.617e-08, eta: 0:47:45, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.8813, aux.loss_ce: 0.0258, aux.acc_seg: 96.6797, loss: 0.0643 2022-05-06 12:42:04,873 - mmseg - INFO - Iter [75250/80000] lr: 8.527e-08, eta: 0:47:15, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0359, decode.acc_seg: 97.9789, aux.loss_ce: 0.0244, aux.acc_seg: 96.8249, loss: 0.0603 2022-05-06 12:42:31,379 - mmseg - INFO - Iter [75300/80000] lr: 8.437e-08, eta: 0:46:45, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0384, decode.acc_seg: 97.9114, aux.loss_ce: 0.0262, aux.acc_seg: 96.7048, loss: 0.0646 2022-05-06 12:42:57,763 - mmseg - INFO - Iter [75350/80000] lr: 8.347e-08, eta: 0:46:15, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8569, aux.loss_ce: 0.0261, aux.acc_seg: 96.6762, loss: 0.0648 2022-05-06 12:43:24,431 - mmseg - INFO - Iter [75400/80000] lr: 8.258e-08, eta: 0:45:45, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.8731, aux.loss_ce: 0.0261, aux.acc_seg: 96.7197, loss: 0.0650 2022-05-06 12:43:51,120 - mmseg - INFO - Iter [75450/80000] lr: 8.168e-08, eta: 0:45:15, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0390, decode.acc_seg: 97.8508, aux.loss_ce: 0.0261, aux.acc_seg: 96.6586, loss: 0.0651 2022-05-06 12:44:17,582 - mmseg - INFO - Iter [75500/80000] lr: 8.078e-08, eta: 0:44:44, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0375, decode.acc_seg: 98.0166, aux.loss_ce: 0.0253, aux.acc_seg: 96.8928, loss: 0.0628 2022-05-06 12:44:46,623 - mmseg - INFO - Iter [75550/80000] lr: 7.988e-08, eta: 0:44:15, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0398, decode.acc_seg: 97.8271, aux.loss_ce: 0.0271, aux.acc_seg: 96.5726, loss: 0.0670 2022-05-06 12:45:13,662 - mmseg - INFO - Iter [75600/80000] lr: 7.899e-08, eta: 0:43:45, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0380, decode.acc_seg: 97.9518, aux.loss_ce: 0.0254, aux.acc_seg: 96.7814, loss: 0.0634 2022-05-06 12:45:40,258 - mmseg - INFO - Iter [75650/80000] lr: 7.809e-08, eta: 0:43:15, time: 0.534, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0383, decode.acc_seg: 97.9257, aux.loss_ce: 0.0260, aux.acc_seg: 96.7598, loss: 0.0643 2022-05-06 12:46:06,839 - mmseg - INFO - Iter [75700/80000] lr: 7.719e-08, eta: 0:42:45, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.9442, aux.loss_ce: 0.0250, aux.acc_seg: 96.7928, loss: 0.0621 2022-05-06 12:46:33,474 - mmseg - INFO - Iter [75750/80000] lr: 7.629e-08, eta: 0:42:15, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0361, decode.acc_seg: 98.0535, aux.loss_ce: 0.0245, aux.acc_seg: 96.9435, loss: 0.0606 2022-05-06 12:47:00,430 - mmseg - INFO - Iter [75800/80000] lr: 7.540e-08, eta: 0:41:45, time: 0.539, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0359, decode.acc_seg: 98.0192, aux.loss_ce: 0.0245, aux.acc_seg: 96.8693, loss: 0.0604 2022-05-06 12:47:29,438 - mmseg - INFO - Iter [75850/80000] lr: 7.450e-08, eta: 0:41:15, time: 0.580, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9905, aux.loss_ce: 0.0250, aux.acc_seg: 96.8585, loss: 0.0619 2022-05-06 12:47:55,942 - mmseg - INFO - Iter [75900/80000] lr: 7.360e-08, eta: 0:40:45, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9696, aux.loss_ce: 0.0254, aux.acc_seg: 96.7680, loss: 0.0624 2022-05-06 12:48:22,518 - mmseg - INFO - Iter [75950/80000] lr: 7.271e-08, eta: 0:40:15, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0369, decode.acc_seg: 97.9426, aux.loss_ce: 0.0249, aux.acc_seg: 96.7882, loss: 0.0619 2022-05-06 12:48:48,967 - mmseg - INFO - Saving checkpoint at 76000 iterations 2022-05-06 12:49:09,003 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:49:09,005 - mmseg - INFO - Iter [76000/80000] lr: 7.181e-08, eta: 0:39:46, time: 0.929, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0368, decode.acc_seg: 97.9964, aux.loss_ce: 0.0248, aux.acc_seg: 96.8277, loss: 0.0616 2022-05-06 12:49:35,835 - mmseg - INFO - Iter [76050/80000] lr: 7.091e-08, eta: 0:39:16, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0385, decode.acc_seg: 97.8641, aux.loss_ce: 0.0264, aux.acc_seg: 96.6132, loss: 0.0648 2022-05-06 12:50:02,560 - mmseg - INFO - Iter [76100/80000] lr: 7.001e-08, eta: 0:38:46, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.9391, aux.loss_ce: 0.0269, aux.acc_seg: 96.8145, loss: 0.0669 2022-05-06 12:50:31,756 - mmseg - INFO - Iter [76150/80000] lr: 6.912e-08, eta: 0:38:16, time: 0.584, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.8982, aux.loss_ce: 0.0253, aux.acc_seg: 96.7420, loss: 0.0632 2022-05-06 12:50:58,322 - mmseg - INFO - Iter [76200/80000] lr: 6.822e-08, eta: 0:37:46, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9510, aux.loss_ce: 0.0253, aux.acc_seg: 96.8350, loss: 0.0635 2022-05-06 12:51:25,179 - mmseg - INFO - Iter [76250/80000] lr: 6.732e-08, eta: 0:37:16, time: 0.537, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0369, decode.acc_seg: 98.0191, aux.loss_ce: 0.0246, aux.acc_seg: 96.9432, loss: 0.0614 2022-05-06 12:51:51,951 - mmseg - INFO - Iter [76300/80000] lr: 6.642e-08, eta: 0:36:46, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9325, aux.loss_ce: 0.0257, aux.acc_seg: 96.7214, loss: 0.0633 2022-05-06 12:52:18,358 - mmseg - INFO - Iter [76350/80000] lr: 6.553e-08, eta: 0:36:16, time: 0.528, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0373, decode.acc_seg: 97.9434, aux.loss_ce: 0.0251, aux.acc_seg: 96.7785, loss: 0.0624 2022-05-06 12:52:44,858 - mmseg - INFO - Iter [76400/80000] lr: 6.463e-08, eta: 0:35:46, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8601, aux.loss_ce: 0.0264, aux.acc_seg: 96.6038, loss: 0.0651 2022-05-06 12:53:14,017 - mmseg - INFO - Iter [76450/80000] lr: 6.373e-08, eta: 0:35:16, time: 0.583, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.8948, aux.loss_ce: 0.0253, aux.acc_seg: 96.7029, loss: 0.0627 2022-05-06 12:53:40,921 - mmseg - INFO - Iter [76500/80000] lr: 6.283e-08, eta: 0:34:46, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0389, decode.acc_seg: 97.9169, aux.loss_ce: 0.0265, aux.acc_seg: 96.7151, loss: 0.0655 2022-05-06 12:54:07,578 - mmseg - INFO - Iter [76550/80000] lr: 6.194e-08, eta: 0:34:16, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0352, decode.acc_seg: 98.0485, aux.loss_ce: 0.0239, aux.acc_seg: 96.9182, loss: 0.0591 2022-05-06 12:54:34,184 - mmseg - INFO - Iter [76600/80000] lr: 6.104e-08, eta: 0:33:46, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.9364, aux.loss_ce: 0.0266, aux.acc_seg: 96.7645, loss: 0.0659 2022-05-06 12:55:00,869 - mmseg - INFO - Iter [76650/80000] lr: 6.014e-08, eta: 0:33:16, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0389, decode.acc_seg: 97.8557, aux.loss_ce: 0.0261, aux.acc_seg: 96.6825, loss: 0.0650 2022-05-06 12:55:27,506 - mmseg - INFO - Iter [76700/80000] lr: 5.924e-08, eta: 0:32:46, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9510, aux.loss_ce: 0.0252, aux.acc_seg: 96.8257, loss: 0.0626 2022-05-06 12:55:54,165 - mmseg - INFO - Iter [76750/80000] lr: 5.835e-08, eta: 0:32:17, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9704, aux.loss_ce: 0.0248, aux.acc_seg: 96.8010, loss: 0.0614 2022-05-06 12:56:23,173 - mmseg - INFO - Iter [76800/80000] lr: 5.745e-08, eta: 0:31:47, time: 0.580, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0365, decode.acc_seg: 98.0297, aux.loss_ce: 0.0241, aux.acc_seg: 96.9699, loss: 0.0606 2022-05-06 12:56:49,906 - mmseg - INFO - Iter [76850/80000] lr: 5.655e-08, eta: 0:31:17, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9806, aux.loss_ce: 0.0256, aux.acc_seg: 96.8120, loss: 0.0632 2022-05-06 12:57:16,709 - mmseg - INFO - Iter [76900/80000] lr: 5.566e-08, eta: 0:30:47, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9708, aux.loss_ce: 0.0248, aux.acc_seg: 96.8397, loss: 0.0618 2022-05-06 12:57:43,455 - mmseg - INFO - Iter [76950/80000] lr: 5.476e-08, eta: 0:30:17, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0357, decode.acc_seg: 97.9754, aux.loss_ce: 0.0246, aux.acc_seg: 96.7473, loss: 0.0604 2022-05-06 12:58:09,909 - mmseg - INFO - Saving checkpoint at 77000 iterations 2022-05-06 12:58:29,402 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 12:58:29,412 - mmseg - INFO - Iter [77000/80000] lr: 5.386e-08, eta: 0:29:48, time: 0.918, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.9528, aux.loss_ce: 0.0251, aux.acc_seg: 96.7884, loss: 0.0624 2022-05-06 12:58:56,282 - mmseg - INFO - Iter [77050/80000] lr: 5.296e-08, eta: 0:29:18, time: 0.538, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9221, aux.loss_ce: 0.0257, aux.acc_seg: 96.6965, loss: 0.0630 2022-05-06 12:59:25,308 - mmseg - INFO - Iter [77100/80000] lr: 5.207e-08, eta: 0:28:48, time: 0.580, data_time: 0.051, memory: 58091, decode.loss_ce: 0.0355, decode.acc_seg: 98.0325, aux.loss_ce: 0.0239, aux.acc_seg: 96.9608, loss: 0.0593 2022-05-06 12:59:51,878 - mmseg - INFO - Iter [77150/80000] lr: 5.117e-08, eta: 0:28:18, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.9317, aux.loss_ce: 0.0262, aux.acc_seg: 96.7606, loss: 0.0649 2022-05-06 13:00:18,369 - mmseg - INFO - Iter [77200/80000] lr: 5.027e-08, eta: 0:27:48, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.9088, aux.loss_ce: 0.0257, aux.acc_seg: 96.7495, loss: 0.0639 2022-05-06 13:00:44,905 - mmseg - INFO - Iter [77250/80000] lr: 4.937e-08, eta: 0:27:18, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9173, aux.loss_ce: 0.0250, aux.acc_seg: 96.7880, loss: 0.0624 2022-05-06 13:01:11,358 - mmseg - INFO - Iter [77300/80000] lr: 4.848e-08, eta: 0:26:48, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0355, decode.acc_seg: 98.0030, aux.loss_ce: 0.0243, aux.acc_seg: 96.8251, loss: 0.0598 2022-05-06 13:01:37,788 - mmseg - INFO - Iter [77350/80000] lr: 4.758e-08, eta: 0:26:18, time: 0.528, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9162, aux.loss_ce: 0.0256, aux.acc_seg: 96.7226, loss: 0.0633 2022-05-06 13:02:06,899 - mmseg - INFO - Iter [77400/80000] lr: 4.668e-08, eta: 0:25:49, time: 0.582, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0382, decode.acc_seg: 97.8814, aux.loss_ce: 0.0259, aux.acc_seg: 96.6708, loss: 0.0641 2022-05-06 13:02:33,403 - mmseg - INFO - Iter [77450/80000] lr: 4.578e-08, eta: 0:25:19, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0354, decode.acc_seg: 98.0542, aux.loss_ce: 0.0239, aux.acc_seg: 96.9479, loss: 0.0593 2022-05-06 13:02:59,895 - mmseg - INFO - Iter [77500/80000] lr: 4.489e-08, eta: 0:24:49, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0348, decode.acc_seg: 98.0194, aux.loss_ce: 0.0233, aux.acc_seg: 96.8929, loss: 0.0581 2022-05-06 13:03:26,626 - mmseg - INFO - Iter [77550/80000] lr: 4.399e-08, eta: 0:24:19, time: 0.535, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8587, aux.loss_ce: 0.0263, aux.acc_seg: 96.6433, loss: 0.0650 2022-05-06 13:03:53,116 - mmseg - INFO - Iter [77600/80000] lr: 4.309e-08, eta: 0:23:49, time: 0.530, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8623, aux.loss_ce: 0.0260, aux.acc_seg: 96.6232, loss: 0.0645 2022-05-06 13:04:19,658 - mmseg - INFO - Iter [77650/80000] lr: 4.219e-08, eta: 0:23:19, time: 0.531, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9400, aux.loss_ce: 0.0258, aux.acc_seg: 96.7312, loss: 0.0636 2022-05-06 13:04:48,775 - mmseg - INFO - Iter [77700/80000] lr: 4.130e-08, eta: 0:22:49, time: 0.582, data_time: 0.052, memory: 58091, decode.loss_ce: 0.0371, decode.acc_seg: 97.9761, aux.loss_ce: 0.0256, aux.acc_seg: 96.7601, loss: 0.0627 2022-05-06 13:05:15,461 - mmseg - INFO - Iter [77750/80000] lr: 4.040e-08, eta: 0:22:20, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0400, decode.acc_seg: 97.8590, aux.loss_ce: 0.0273, aux.acc_seg: 96.6380, loss: 0.0672 2022-05-06 13:05:42,608 - mmseg - INFO - Iter [77800/80000] lr: 3.950e-08, eta: 0:21:50, time: 0.543, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9820, aux.loss_ce: 0.0253, aux.acc_seg: 96.8700, loss: 0.0629 2022-05-06 13:06:09,186 - mmseg - INFO - Iter [77850/80000] lr: 3.860e-08, eta: 0:21:20, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0378, decode.acc_seg: 97.9336, aux.loss_ce: 0.0257, aux.acc_seg: 96.7560, loss: 0.0634 2022-05-06 13:06:35,768 - mmseg - INFO - Iter [77900/80000] lr: 3.771e-08, eta: 0:20:50, time: 0.532, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9961, aux.loss_ce: 0.0250, aux.acc_seg: 96.8706, loss: 0.0624 2022-05-06 13:07:02,297 - mmseg - INFO - Iter [77950/80000] lr: 3.681e-08, eta: 0:20:20, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9002, aux.loss_ce: 0.0256, aux.acc_seg: 96.7021, loss: 0.0636 2022-05-06 13:07:28,926 - mmseg - INFO - Saving checkpoint at 78000 iterations 2022-05-06 13:07:48,837 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 13:07:48,845 - mmseg - INFO - Iter [78000/80000] lr: 3.591e-08, eta: 0:19:51, time: 0.930, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0369, decode.acc_seg: 97.9958, aux.loss_ce: 0.0251, aux.acc_seg: 96.8316, loss: 0.0620 2022-05-06 13:08:17,939 - mmseg - INFO - Iter [78050/80000] lr: 3.502e-08, eta: 0:19:21, time: 0.583, data_time: 0.048, memory: 58091, decode.loss_ce: 0.0393, decode.acc_seg: 97.9193, aux.loss_ce: 0.0265, aux.acc_seg: 96.7191, loss: 0.0658 2022-05-06 13:08:44,623 - mmseg - INFO - Iter [78100/80000] lr: 3.412e-08, eta: 0:18:51, time: 0.534, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0367, decode.acc_seg: 97.9777, aux.loss_ce: 0.0249, aux.acc_seg: 96.8023, loss: 0.0617 2022-05-06 13:09:11,021 - mmseg - INFO - Iter [78150/80000] lr: 3.322e-08, eta: 0:18:21, time: 0.528, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0363, decode.acc_seg: 98.0188, aux.loss_ce: 0.0249, aux.acc_seg: 96.8588, loss: 0.0611 2022-05-06 13:09:38,083 - mmseg - INFO - Iter [78200/80000] lr: 3.232e-08, eta: 0:17:51, time: 0.541, data_time: 0.007, memory: 58091, decode.loss_ce: 0.0358, decode.acc_seg: 98.0494, aux.loss_ce: 0.0239, aux.acc_seg: 96.9916, loss: 0.0597 2022-05-06 13:10:04,687 - mmseg - INFO - Iter [78250/80000] lr: 3.143e-08, eta: 0:17:22, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0389, decode.acc_seg: 97.8995, aux.loss_ce: 0.0267, aux.acc_seg: 96.6056, loss: 0.0655 2022-05-06 13:10:31,316 - mmseg - INFO - Iter [78300/80000] lr: 3.053e-08, eta: 0:16:52, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0356, decode.acc_seg: 98.0438, aux.loss_ce: 0.0244, aux.acc_seg: 96.9013, loss: 0.0601 2022-05-06 13:11:00,472 - mmseg - INFO - Iter [78350/80000] lr: 2.963e-08, eta: 0:16:22, time: 0.583, data_time: 0.051, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8731, aux.loss_ce: 0.0261, aux.acc_seg: 96.6429, loss: 0.0647 2022-05-06 13:11:26,946 - mmseg - INFO - Iter [78400/80000] lr: 2.873e-08, eta: 0:15:52, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0359, decode.acc_seg: 98.0273, aux.loss_ce: 0.0247, aux.acc_seg: 96.8391, loss: 0.0606 2022-05-06 13:11:53,596 - mmseg - INFO - Iter [78450/80000] lr: 2.784e-08, eta: 0:15:22, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0396, decode.acc_seg: 97.7623, aux.loss_ce: 0.0271, aux.acc_seg: 96.4366, loss: 0.0667 2022-05-06 13:12:20,038 - mmseg - INFO - Iter [78500/80000] lr: 2.694e-08, eta: 0:14:52, time: 0.529, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0363, decode.acc_seg: 97.9699, aux.loss_ce: 0.0244, aux.acc_seg: 96.8636, loss: 0.0607 2022-05-06 13:12:46,832 - mmseg - INFO - Iter [78550/80000] lr: 2.604e-08, eta: 0:14:23, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 98.0378, aux.loss_ce: 0.0251, aux.acc_seg: 96.9380, loss: 0.0622 2022-05-06 13:13:13,365 - mmseg - INFO - Iter [78600/80000] lr: 2.514e-08, eta: 0:13:53, time: 0.531, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0375, decode.acc_seg: 97.9402, aux.loss_ce: 0.0255, aux.acc_seg: 96.7440, loss: 0.0629 2022-05-06 13:13:42,422 - mmseg - INFO - Iter [78650/80000] lr: 2.425e-08, eta: 0:13:23, time: 0.581, data_time: 0.054, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9960, aux.loss_ce: 0.0251, aux.acc_seg: 96.8220, loss: 0.0618 2022-05-06 13:14:08,787 - mmseg - INFO - Iter [78700/80000] lr: 2.335e-08, eta: 0:12:53, time: 0.527, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9630, aux.loss_ce: 0.0257, aux.acc_seg: 96.7872, loss: 0.0634 2022-05-06 13:14:35,661 - mmseg - INFO - Iter [78750/80000] lr: 2.245e-08, eta: 0:12:23, time: 0.538, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0374, decode.acc_seg: 97.9670, aux.loss_ce: 0.0254, aux.acc_seg: 96.7992, loss: 0.0629 2022-05-06 13:15:02,294 - mmseg - INFO - Iter [78800/80000] lr: 2.155e-08, eta: 0:11:54, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0357, decode.acc_seg: 97.9722, aux.loss_ce: 0.0247, aux.acc_seg: 96.7607, loss: 0.0604 2022-05-06 13:15:28,750 - mmseg - INFO - Iter [78850/80000] lr: 2.066e-08, eta: 0:11:24, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0358, decode.acc_seg: 98.0431, aux.loss_ce: 0.0240, aux.acc_seg: 96.9549, loss: 0.0598 2022-05-06 13:15:55,393 - mmseg - INFO - Iter [78900/80000] lr: 1.976e-08, eta: 0:10:54, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.8812, aux.loss_ce: 0.0263, aux.acc_seg: 96.6893, loss: 0.0648 2022-05-06 13:16:24,539 - mmseg - INFO - Iter [78950/80000] lr: 1.886e-08, eta: 0:10:24, time: 0.583, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0377, decode.acc_seg: 97.9093, aux.loss_ce: 0.0257, aux.acc_seg: 96.7022, loss: 0.0634 2022-05-06 13:16:51,230 - mmseg - INFO - Saving checkpoint at 79000 iterations 2022-05-06 13:17:10,654 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 13:17:10,657 - mmseg - INFO - Iter [79000/80000] lr: 1.797e-08, eta: 0:09:55, time: 0.921, data_time: 0.008, memory: 58091, decode.loss_ce: 0.0372, decode.acc_seg: 97.9602, aux.loss_ce: 0.0251, aux.acc_seg: 96.8112, loss: 0.0624 2022-05-06 13:17:37,585 - mmseg - INFO - Iter [79050/80000] lr: 1.707e-08, eta: 0:09:25, time: 0.540, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0375, decode.acc_seg: 97.9566, aux.loss_ce: 0.0251, aux.acc_seg: 96.8597, loss: 0.0626 2022-05-06 13:18:04,268 - mmseg - INFO - Iter [79100/80000] lr: 1.617e-08, eta: 0:08:55, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.8719, aux.loss_ce: 0.0263, aux.acc_seg: 96.6326, loss: 0.0650 2022-05-06 13:18:30,634 - mmseg - INFO - Iter [79150/80000] lr: 1.527e-08, eta: 0:08:25, time: 0.527, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9357, aux.loss_ce: 0.0256, aux.acc_seg: 96.7973, loss: 0.0643 2022-05-06 13:18:57,265 - mmseg - INFO - Iter [79200/80000] lr: 1.438e-08, eta: 0:07:56, time: 0.533, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0416, decode.acc_seg: 97.8628, aux.loss_ce: 0.0270, aux.acc_seg: 96.7099, loss: 0.0686 2022-05-06 13:19:26,324 - mmseg - INFO - Iter [79250/80000] lr: 1.348e-08, eta: 0:07:26, time: 0.581, data_time: 0.053, memory: 58091, decode.loss_ce: 0.0386, decode.acc_seg: 97.9465, aux.loss_ce: 0.0257, aux.acc_seg: 96.8168, loss: 0.0644 2022-05-06 13:19:52,931 - mmseg - INFO - Iter [79300/80000] lr: 1.258e-08, eta: 0:06:56, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0366, decode.acc_seg: 97.9658, aux.loss_ce: 0.0248, aux.acc_seg: 96.8108, loss: 0.0613 2022-05-06 13:20:19,621 - mmseg - INFO - Iter [79350/80000] lr: 1.168e-08, eta: 0:06:26, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0365, decode.acc_seg: 97.9866, aux.loss_ce: 0.0249, aux.acc_seg: 96.8412, loss: 0.0614 2022-05-06 13:20:46,130 - mmseg - INFO - Iter [79400/80000] lr: 1.079e-08, eta: 0:05:56, time: 0.530, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0362, decode.acc_seg: 98.0137, aux.loss_ce: 0.0247, aux.acc_seg: 96.8458, loss: 0.0609 2022-05-06 13:21:12,737 - mmseg - INFO - Iter [79450/80000] lr: 9.889e-09, eta: 0:05:27, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0379, decode.acc_seg: 97.9100, aux.loss_ce: 0.0267, aux.acc_seg: 96.5475, loss: 0.0646 2022-05-06 13:21:39,513 - mmseg - INFO - Iter [79500/80000] lr: 8.992e-09, eta: 0:04:57, time: 0.536, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0387, decode.acc_seg: 97.9147, aux.loss_ce: 0.0263, aux.acc_seg: 96.6927, loss: 0.0650 2022-05-06 13:22:06,047 - mmseg - INFO - Iter [79550/80000] lr: 8.094e-09, eta: 0:04:27, time: 0.529, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0385, decode.acc_seg: 97.8602, aux.loss_ce: 0.0263, aux.acc_seg: 96.5930, loss: 0.0647 2022-05-06 13:22:35,251 - mmseg - INFO - Iter [79600/80000] lr: 7.197e-09, eta: 0:03:57, time: 0.586, data_time: 0.056, memory: 58091, decode.loss_ce: 0.0351, decode.acc_seg: 98.0417, aux.loss_ce: 0.0238, aux.acc_seg: 96.9125, loss: 0.0589 2022-05-06 13:23:01,872 - mmseg - INFO - Iter [79650/80000] lr: 6.300e-09, eta: 0:03:28, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0394, decode.acc_seg: 97.8404, aux.loss_ce: 0.0263, aux.acc_seg: 96.6321, loss: 0.0657 2022-05-06 13:23:28,652 - mmseg - INFO - Iter [79700/80000] lr: 5.402e-09, eta: 0:02:58, time: 0.535, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0397, decode.acc_seg: 97.7790, aux.loss_ce: 0.0268, aux.acc_seg: 96.5752, loss: 0.0665 2022-05-06 13:23:55,320 - mmseg - INFO - Iter [79750/80000] lr: 4.505e-09, eta: 0:02:28, time: 0.534, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0367, decode.acc_seg: 98.0140, aux.loss_ce: 0.0247, aux.acc_seg: 96.8761, loss: 0.0613 2022-05-06 13:24:21,922 - mmseg - INFO - Iter [79800/80000] lr: 3.607e-09, eta: 0:01:58, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0355, decode.acc_seg: 97.9516, aux.loss_ce: 0.0240, aux.acc_seg: 96.7888, loss: 0.0595 2022-05-06 13:24:48,531 - mmseg - INFO - Iter [79850/80000] lr: 2.710e-09, eta: 0:01:29, time: 0.532, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.9622, aux.loss_ce: 0.0249, aux.acc_seg: 96.7961, loss: 0.0620 2022-05-06 13:25:17,738 - mmseg - INFO - Iter [79900/80000] lr: 1.813e-09, eta: 0:00:59, time: 0.584, data_time: 0.057, memory: 58091, decode.loss_ce: 0.0370, decode.acc_seg: 97.8567, aux.loss_ce: 0.0254, aux.acc_seg: 96.5855, loss: 0.0624 2022-05-06 13:25:44,412 - mmseg - INFO - Iter [79950/80000] lr: 9.153e-10, eta: 0:00:29, time: 0.533, data_time: 0.004, memory: 58091, decode.loss_ce: 0.0364, decode.acc_seg: 98.0180, aux.loss_ce: 0.0251, aux.acc_seg: 96.7855, loss: 0.0615 2022-05-06 13:26:10,881 - mmseg - INFO - Saving checkpoint at 80000 iterations 2022-05-06 13:26:30,257 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 13:26:30,259 - mmseg - INFO - Iter [80000/80000] lr: 1.795e-11, eta: 0:00:00, time: 0.916, data_time: 0.005, memory: 58091, decode.loss_ce: 0.0360, decode.acc_seg: 98.0233, aux.loss_ce: 0.0246, aux.acc_seg: 96.8867, loss: 0.0606 2022-05-06 13:30:39,473 - mmseg - INFO - per class results: 2022-05-06 13:30:39,481 - mmseg - INFO - +-------------+-------+-------+ | Class | IoU | Acc | +-------------+-------+-------+ | aeroplane | 93.14 | 97.17 | | bag | 45.26 | 57.56 | | bed | 35.01 | 45.54 | | bedclothes | 45.35 | 66.77 | | bench | 32.98 | 41.99 | | bicycle | 84.55 | 93.72 | | bird | 94.12 | 98.14 | | boat | 85.76 | 92.3 | | book | 60.99 | 74.29 | | bottle | 88.65 | 96.92 | | building | 68.29 | 80.38 | | bus | 94.55 | 97.48 | | cabinet | 50.8 | 65.5 | | car | 93.96 | 97.06 | | cat | 93.25 | 98.56 | | ceiling | 59.9 | 75.3 | | chair | 65.14 | 78.89 | | cloth | 25.52 | 32.61 | | computer | 62.28 | 71.15 | | cow | 95.75 | 98.34 | | cup | 47.36 | 66.24 | | curtain | 60.92 | 75.18 | | dog | 91.9 | 98.05 | | door | 35.68 | 49.83 | | fence | 45.91 | 59.49 | | floor | 76.97 | 89.2 | | flower | 35.36 | 45.7 | | food | 42.17 | 51.56 | | grass | 83.4 | 92.36 | | ground | 57.38 | 71.04 | | horse | 94.6 | 97.76 | | keyboard | 90.43 | 95.43 | | light | 59.77 | 74.54 | | motorbike | 90.84 | 96.99 | | mountain | 58.81 | 73.44 | | mouse | 80.87 | 93.65 | | person | 90.61 | 97.05 | | plate | 30.32 | 41.55 | | platform | 58.83 | 76.18 | | pottedplant | 81.84 | 90.5 | | road | 53.46 | 71.03 | | rock | 56.25 | 64.1 | | sheep | 95.11 | 98.66 | | shelves | 35.65 | 46.26 | | sidewalk | 34.34 | 51.07 | | sign | 53.63 | 60.92 | | sky | 95.13 | 97.54 | | snow | 76.5 | 90.8 | | sofa | 60.18 | 69.26 | | table | 73.57 | 85.76 | | track | 73.06 | 84.28 | | train | 93.14 | 97.43 | | tree | 81.93 | 91.0 | | truck | 51.97 | 58.12 | | tvmonitor | 90.99 | 94.54 | | wall | 74.49 | 87.15 | | water | 92.14 | 96.35 | | window | 47.55 | 61.86 | | wood | 25.54 | 32.38 | +-------------+-------+-------+ 2022-05-06 13:30:39,481 - mmseg - INFO - Summary: 2022-05-06 13:30:39,481 - mmseg - INFO - +------+-------+-------+ | aAcc | mIoU | mAcc | +------+-------+-------+ | 86.7 | 67.01 | 76.85 | +------+-------+-------+ 2022-05-06 13:30:39,505 - mmseg - INFO - Exp name: upernet_beit_large_24_adapter_480_slide_80k_pascal_context_59_pt2ft_try2.py 2022-05-06 13:30:39,506 - mmseg - INFO - Iter(val) [638] aAcc: 0.8670, mIoU: 0.6701, mAcc: 0.7685, IoU.aeroplane: 0.9314, IoU.bag: 0.4526, IoU.bed: 0.3501, IoU.bedclothes: 0.4535, IoU.bench: 0.3298, IoU.bicycle: 0.8455, IoU.bird: 0.9412, IoU.boat: 0.8576, IoU.book: 0.6099, IoU.bottle: 0.8865, IoU.building: 0.6829, IoU.bus: 0.9455, IoU.cabinet: 0.5080, IoU.car: 0.9396, IoU.cat: 0.9325, IoU.ceiling: 0.5990, IoU.chair: 0.6514, IoU.cloth: 0.2552, IoU.computer: 0.6228, IoU.cow: 0.9575, IoU.cup: 0.4736, IoU.curtain: 0.6092, IoU.dog: 0.9190, IoU.door: 0.3568, IoU.fence: 0.4591, IoU.floor: 0.7697, IoU.flower: 0.3536, IoU.food: 0.4217, IoU.grass: 0.8340, IoU.ground: 0.5738, IoU.horse: 0.9460, IoU.keyboard: 0.9043, IoU.light: 0.5977, IoU.motorbike: 0.9084, IoU.mountain: 0.5881, IoU.mouse: 0.8087, IoU.person: 0.9061, IoU.plate: 0.3032, IoU.platform: 0.5883, IoU.pottedplant: 0.8184, IoU.road: 0.5346, IoU.rock: 0.5625, IoU.sheep: 0.9511, IoU.shelves: 0.3565, IoU.sidewalk: 0.3434, IoU.sign: 0.5363, IoU.sky: 0.9513, IoU.snow: 0.7650, IoU.sofa: 0.6018, IoU.table: 0.7357, IoU.track: 0.7306, IoU.train: 0.9314, IoU.tree: 0.8193, IoU.truck: 0.5197, IoU.tvmonitor: 0.9099, IoU.wall: 0.7449, IoU.water: 0.9214, IoU.window: 0.4755, IoU.wood: 0.2554, Acc.aeroplane: 0.9717, Acc.bag: 0.5756, Acc.bed: 0.4554, Acc.bedclothes: 0.6677, Acc.bench: 0.4199, Acc.bicycle: 0.9372, Acc.bird: 0.9814, Acc.boat: 0.9230, Acc.book: 0.7429, Acc.bottle: 0.9692, Acc.building: 0.8038, Acc.bus: 0.9748, Acc.cabinet: 0.6550, Acc.car: 0.9706, Acc.cat: 0.9856, Acc.ceiling: 0.7530, Acc.chair: 0.7889, Acc.cloth: 0.3261, Acc.computer: 0.7115, Acc.cow: 0.9834, Acc.cup: 0.6624, Acc.curtain: 0.7518, Acc.dog: 0.9805, Acc.door: 0.4983, Acc.fence: 0.5949, Acc.floor: 0.8920, Acc.flower: 0.4570, Acc.food: 0.5156, Acc.grass: 0.9236, Acc.ground: 0.7104, Acc.horse: 0.9776, Acc.keyboard: 0.9543, Acc.light: 0.7454, Acc.motorbike: 0.9699, Acc.mountain: 0.7344, Acc.mouse: 0.9365, Acc.person: 0.9705, Acc.plate: 0.4155, Acc.platform: 0.7618, Acc.pottedplant: 0.9050, Acc.road: 0.7103, Acc.rock: 0.6410, Acc.sheep: 0.9866, Acc.shelves: 0.4626, Acc.sidewalk: 0.5107, Acc.sign: 0.6092, Acc.sky: 0.9754, Acc.snow: 0.9080, Acc.sofa: 0.6926, Acc.table: 0.8576, Acc.track: 0.8428, Acc.train: 0.9743, Acc.tree: 0.9100, Acc.truck: 0.5812, Acc.tvmonitor: 0.9454, Acc.wall: 0.8715, Acc.water: 0.9635, Acc.window: 0.6186, Acc.wood: 0.3238