convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1/20230605_124607/20230605_124607.log

2023/06/05 12:46:14 - mmengine - INFO - 
------------------------------------------------------------
System environment:
    sys.platform: linux
    Python: 3.10.9 (main, Mar  8 2023, 10:47:38) [GCC 11.2.0]
    CUDA available: True
    numpy_random_seed: 98458905
    GPU 0,1,2,3: NVIDIA A100-SXM4-80GB
    CUDA_HOME: /mnt/petrelfs/share/cuda-11.6
    NVCC: Cuda compilation tools, release 11.6, V11.6.124
    GCC: gcc (GCC) 7.5.0
    PyTorch: 1.13.1
    PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.6
  - 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_61,code=sm_61;-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;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.3.2  (built against CUDA 11.5)
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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 -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, 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, USE_ROCM=OFF, 

    TorchVision: 0.14.1
    OpenCV: 4.7.0
    MMEngine: 0.7.3

Runtime environment:
    cudnn_benchmark: True
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: None
    deterministic: False
    Distributed launcher: slurm
    Distributed training: True
    GPU number: 4
------------------------------------------------------------

2023/06/05 12:46:18 - mmengine - INFO - Config:
optim_wrapper = dict(
    optimizer=dict(
        type='AdamW',
        lr=0.0001,
        weight_decay=0.05,
        eps=1e-08,
        betas=(0.9, 0.999),
        _scope_='mmpretrain'),
    paramwise_cfg=dict(
        norm_decay_mult=0.0,
        bias_decay_mult=0.0,
        flat_decay_mult=0.0,
        custom_keys=dict({
            '.absolute_pos_embed': dict(decay_mult=0.0),
            '.relative_position_bias_table': dict(decay_mult=0.0)
        })),
    type='AmpOptimWrapper',
    dtype='bfloat16',
    clip_grad=None)
param_scheduler = [
    dict(type='CosineAnnealingLR', eta_min=1e-05, by_epoch=False, begin=0)
]
train_cfg = dict(by_epoch=True, max_epochs=10, val_interval=1)
val_cfg = dict()
test_cfg = dict()
auto_scale_lr = dict(base_batch_size=4096)
model = dict(
    type='ImageClassifier',
    backbone=dict(
        frozen_stages=2,
        type='ConvNeXt',
        arch='small',
        drop_path_rate=0.4,
        init_cfg=dict(
            type='Pretrained',
            checkpoint=
            'https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth',
            prefix='backbone')),
    head=dict(
        type='LinearClsHead',
        num_classes=2,
        in_channels=768,
        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
        init_cfg=None),
    init_cfg=dict(
        type='TruncNormal', layer=['Conv2d', 'Linear'], std=0.02, bias=0.0),
    train_cfg=None)
dataset_type = 'CustomDataset'
data_preprocessor = dict(
    num_classes=2,
    mean=[123.675, 116.28, 103.53],
    std=[58.395, 57.12, 57.375],
    to_rgb=True)
bgr_mean = [103.53, 116.28, 123.675]
bgr_std = [57.375, 57.12, 58.395]
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RandomResizedCrop',
        scale=224,
        backend='pillow',
        interpolation='bicubic'),
    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
    dict(type='JPEG', compress_val=65, prob=0.1),
    dict(type='GaussianBlur', radius=1.5, prob=0.1),
    dict(type='PackInputs')
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='ResizeEdge',
        scale=256,
        edge='short',
        backend='pillow',
        interpolation='bicubic'),
    dict(type='CenterCrop', crop_size=224),
    dict(type='PackInputs')
]
train_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    batch_size=256,
    num_workers=10,
    dataset=dict(
        type='ConcatDataset',
        datasets=[
            dict(
                type='CustomDataset',
                data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
                ann_file=
                '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3fake8w.csv',
                pipeline=[
                    dict(type='LoadImageFromFile'),
                    dict(
                        type='RandomResizedCrop',
                        scale=224,
                        backend='pillow',
                        interpolation='bicubic'),
                    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
                    dict(type='JPEG', compress_val=65, prob=0.1),
                    dict(type='GaussianBlur', radius=1.5, prob=0.1),
                    dict(type='PackInputs')
                ]),
            dict(
                type='CustomDataset',
                data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
                ann_file=
                '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3real8w.csv',
                pipeline=[
                    dict(type='LoadImageFromFile'),
                    dict(
                        type='RandomResizedCrop',
                        scale=224,
                        backend='pillow',
                        interpolation='bicubic'),
                    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
                    dict(type='JPEG', compress_val=65, prob=0.1),
                    dict(type='GaussianBlur', radius=1.5, prob=0.1),
                    dict(type='PackInputs')
                ])
        ]),
    sampler=dict(type='DefaultSampler', shuffle=True))
val_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    batch_size=256,
    num_workers=10,
    dataset=dict(
        type='ConcatDataset',
        datasets=[
            dict(
                type='CustomDataset',
                data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
                ann_file=
                '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3fake8w.csv',
                pipeline=[
                    dict(type='LoadImageFromFile'),
                    dict(
                        type='RandomResizedCrop',
                        scale=224,
                        backend='pillow',
                        interpolation='bicubic'),
                    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
                    dict(type='JPEG', compress_val=65, prob=0.1),
                    dict(type='GaussianBlur', radius=1.5, prob=0.1),
                    dict(type='PackInputs')
                ]),
            dict(
                type='CustomDataset',
                data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
                ann_file=
                '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3real8w.csv',
                pipeline=[
                    dict(type='LoadImageFromFile'),
                    dict(
                        type='RandomResizedCrop',
                        scale=224,
                        backend='pillow',
                        interpolation='bicubic'),
                    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
                    dict(type='JPEG', compress_val=65, prob=0.1),
                    dict(type='GaussianBlur', radius=1.5, prob=0.1),
                    dict(type='PackInputs')
                ])
        ]),
    sampler=dict(type='DefaultSampler', shuffle=False))
val_evaluator = [
    dict(type='Accuracy', topk=1),
    dict(type='SingleLabelMetric', average=None)
]
test_dataloader = dict(
    pin_memory=True,
    persistent_workers=True,
    collate_fn=dict(type='default_collate'),
    batch_size=256,
    num_workers=10,
    dataset=dict(
        type='ConcatDataset',
        datasets=[
            dict(
                type='CustomDataset',
                data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
                ann_file=
                '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3fake8w.csv',
                pipeline=[
                    dict(type='LoadImageFromFile'),
                    dict(
                        type='RandomResizedCrop',
                        scale=224,
                        backend='pillow',
                        interpolation='bicubic'),
                    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
                    dict(type='JPEG', compress_val=65, prob=0.1),
                    dict(type='GaussianBlur', radius=1.5, prob=0.1),
                    dict(type='PackInputs')
                ]),
            dict(
                type='CustomDataset',
                data_root='/mnt/petrelfs/luzeyu/workspace/fakebench/dataset',
                ann_file=
                '/mnt/petrelfs/luzeyu/workspace/fakebench/dataset/meta/train/stylegan3real8w.csv',
                pipeline=[
                    dict(type='LoadImageFromFile'),
                    dict(
                        type='RandomResizedCrop',
                        scale=224,
                        backend='pillow',
                        interpolation='bicubic'),
                    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
                    dict(type='JPEG', compress_val=65, prob=0.1),
                    dict(type='GaussianBlur', radius=1.5, prob=0.1),
                    dict(type='PackInputs')
                ])
        ]),
    sampler=dict(type='DefaultSampler', shuffle=False))
test_evaluator = [
    dict(type='Accuracy', topk=1),
    dict(type='SingleLabelMetric', average=None)
]
custom_hooks = [dict(type='EMAHook', momentum=0.0001, priority='ABOVE_NORMAL')]
default_scope = 'mmpretrain'
default_hooks = dict(
    timer=dict(type='IterTimerHook'),
    logger=dict(type='LoggerHook', interval=100),
    param_scheduler=dict(type='ParamSchedulerHook'),
    checkpoint=dict(type='CheckpointHook', interval=1),
    sampler_seed=dict(type='DistSamplerSeedHook'),
    visualization=dict(type='VisualizationHook', enable=True))
env_cfg = dict(
    cudnn_benchmark=True,
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
    dist_cfg=dict(backend='nccl'))
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='UniversalVisualizer',
    vis_backends=[
        dict(type='LocalVisBackend'),
        dict(type='TensorboardVisBackend')
    ])
log_level = 'INFO'
load_from = None
resume = False
randomness = dict(seed=None, deterministic=False)
launcher = 'slurm'
work_dir = 'workdir/convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1'

2023/06/05 12:46:29 - mmengine - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH   ) RuntimeInfoHook                    
(ABOVE_NORMAL) EMAHook                            
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_load_checkpoint:
(ABOVE_NORMAL) EMAHook                            
 -------------------- 
before_train:
(VERY_HIGH   ) RuntimeInfoHook                    
(ABOVE_NORMAL) EMAHook                            
(NORMAL      ) IterTimerHook                      
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_train_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
(NORMAL      ) DistSamplerSeedHook                
 -------------------- 
before_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_train_iter:
(VERY_HIGH   ) RuntimeInfoHook                    
(ABOVE_NORMAL) EMAHook                            
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
after_train_epoch:
(NORMAL      ) IterTimerHook                      
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_val_epoch:
(ABOVE_NORMAL) EMAHook                            
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_val_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_val_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) VisualizationHook                  
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_val_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(ABOVE_NORMAL) EMAHook                            
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
(LOW         ) ParamSchedulerHook                 
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_save_checkpoint:
(ABOVE_NORMAL) EMAHook                            
 -------------------- 
after_train:
(VERY_LOW    ) CheckpointHook                     
 -------------------- 
before_test_epoch:
(ABOVE_NORMAL) EMAHook                            
(NORMAL      ) IterTimerHook                      
 -------------------- 
before_test_iter:
(NORMAL      ) IterTimerHook                      
 -------------------- 
after_test_iter:
(NORMAL      ) IterTimerHook                      
(NORMAL      ) VisualizationHook                  
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_test_epoch:
(VERY_HIGH   ) RuntimeInfoHook                    
(ABOVE_NORMAL) EMAHook                            
(NORMAL      ) IterTimerHook                      
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
after_run:
(BELOW_NORMAL) LoggerHook                         
 -------------------- 
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.downsample_layers.2.0.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.downsample_layers.2.0.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.downsample_layers.2.1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.downsample_layers.3.0.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.downsample_layers.3.0.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.downsample_layers.3.1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.0.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.0.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.0.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.0.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.0.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.0.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.1.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.1.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.1.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.1.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.1.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.1.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.2.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.2.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.2.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.2.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.2.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.2.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.3.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.3.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.3.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.3.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.3.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.3.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.4.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.4.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.4.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.4.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.4.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.4.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.5.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.5.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.5.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.5.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.5.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.5.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.6.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.6.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.6.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.6.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.6.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.6.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.7.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.7.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.7.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.7.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.7.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.7.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.8.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.8.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.8.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.8.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.8.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.8.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.9.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.9.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.9.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.9.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.9.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.9.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.10.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.10.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.10.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.10.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.10.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.10.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.11.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.11.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.11.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.11.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.11.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.11.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.12.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.12.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.12.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.12.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.12.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.12.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.13.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.13.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.13.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.13.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.13.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.13.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.14.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.14.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.14.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.14.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.14.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.14.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.15.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.15.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.15.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.15.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.15.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.15.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.16.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.16.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.16.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.16.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.16.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.16.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.17.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.17.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.17.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.17.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.17.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.17.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.18.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.18.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.18.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.18.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.18.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.18.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.19.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.19.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.19.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.19.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.19.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.19.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.20.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.20.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.20.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.20.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.20.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.20.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.21.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.21.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.21.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.21.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.21.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.21.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.22.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.22.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.22.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.22.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.22.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.22.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.23.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.23.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.23.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.23.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.23.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.23.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.24.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.24.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.24.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.24.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.24.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.24.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.25.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.25.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.25.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.25.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.25.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.25.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.26.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.26.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.26.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.26.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.26.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.2.26.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.0.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.0.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.0.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.0.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.0.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.0.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.1.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.1.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.1.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.1.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.1.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.1.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.2.gamma:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.2.depthwise_conv.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.2.norm.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.2.norm.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.2.pointwise_conv1.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.stages.3.2.pointwise_conv2.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.norm3.weight:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- backbone.norm3.bias:weight_decay=0.0
2023/06/05 12:46:34 - mmengine - INFO - paramwise_options -- head.fc.bias:weight_decay=0.0
2023/06/05 12:46:40 - mmengine - INFO - load backbone in model from: https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth
Name of parameter - Initialization information

backbone.downsample_layers.0.0.weight - torch.Size([96, 3, 4, 4]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.0.0.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.0.1.weight - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.0.1.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.1.0.weight - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.1.0.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.1.1.weight - torch.Size([192, 96, 2, 2]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.1.1.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.2.0.weight - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.2.0.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.2.1.weight - torch.Size([384, 192, 2, 2]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.2.1.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.3.0.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.3.0.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.3.1.weight - torch.Size([768, 384, 2, 2]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.downsample_layers.3.1.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.gamma - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.depthwise_conv.weight - torch.Size([96, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.depthwise_conv.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.norm.weight - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.norm.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.pointwise_conv1.weight - torch.Size([384, 96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.pointwise_conv1.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.pointwise_conv2.weight - torch.Size([96, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.0.pointwise_conv2.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.gamma - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.depthwise_conv.weight - torch.Size([96, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.depthwise_conv.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.norm.weight - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.norm.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.pointwise_conv1.weight - torch.Size([384, 96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.pointwise_conv1.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.pointwise_conv2.weight - torch.Size([96, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.1.pointwise_conv2.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.gamma - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.depthwise_conv.weight - torch.Size([96, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.depthwise_conv.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.norm.weight - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.norm.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.pointwise_conv1.weight - torch.Size([384, 96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.pointwise_conv1.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.pointwise_conv2.weight - torch.Size([96, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.0.2.pointwise_conv2.bias - torch.Size([96]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.gamma - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.depthwise_conv.weight - torch.Size([192, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.depthwise_conv.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.norm.weight - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.norm.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.pointwise_conv1.weight - torch.Size([768, 192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.pointwise_conv1.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.pointwise_conv2.weight - torch.Size([192, 768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.0.pointwise_conv2.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.gamma - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.depthwise_conv.weight - torch.Size([192, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.depthwise_conv.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.norm.weight - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.norm.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.pointwise_conv1.weight - torch.Size([768, 192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.pointwise_conv1.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.pointwise_conv2.weight - torch.Size([192, 768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.1.pointwise_conv2.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.gamma - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.depthwise_conv.weight - torch.Size([192, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.depthwise_conv.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.norm.weight - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.norm.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.pointwise_conv1.weight - torch.Size([768, 192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.pointwise_conv1.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.pointwise_conv2.weight - torch.Size([192, 768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.1.2.pointwise_conv2.bias - torch.Size([192]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.0.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.1.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.2.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.3.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.4.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.5.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.6.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.7.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.8.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.9.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.10.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.11.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.12.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.13.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.14.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.15.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.16.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.17.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.18.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.19.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.20.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.21.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.22.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.23.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.24.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.25.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.gamma - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.depthwise_conv.weight - torch.Size([384, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.depthwise_conv.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.norm.weight - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.norm.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.pointwise_conv1.weight - torch.Size([1536, 384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.pointwise_conv1.bias - torch.Size([1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.pointwise_conv2.weight - torch.Size([384, 1536]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.2.26.pointwise_conv2.bias - torch.Size([384]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.gamma - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.depthwise_conv.weight - torch.Size([768, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.depthwise_conv.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.norm.weight - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.norm.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.pointwise_conv1.weight - torch.Size([3072, 768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.pointwise_conv1.bias - torch.Size([3072]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.pointwise_conv2.weight - torch.Size([768, 3072]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.0.pointwise_conv2.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.gamma - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.depthwise_conv.weight - torch.Size([768, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.depthwise_conv.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.norm.weight - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.norm.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.pointwise_conv1.weight - torch.Size([3072, 768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.pointwise_conv1.bias - torch.Size([3072]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.pointwise_conv2.weight - torch.Size([768, 3072]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.1.pointwise_conv2.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.gamma - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.depthwise_conv.weight - torch.Size([768, 1, 7, 7]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.depthwise_conv.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.norm.weight - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.norm.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.pointwise_conv1.weight - torch.Size([3072, 768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.pointwise_conv1.bias - torch.Size([3072]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.pointwise_conv2.weight - torch.Size([768, 3072]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.stages.3.2.pointwise_conv2.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.norm3.weight - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

backbone.norm3.bias - torch.Size([768]): 
PretrainedInit: load from https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_in21k-pre_3rdparty_in1k_20221219-aeca4c93.pth 

head.fc.weight - torch.Size([2, 768]): 
TruncNormalInit: a=-2, b=2, mean=0, std=0.02, bias=0.0 

head.fc.bias - torch.Size([2]): 
TruncNormalInit: a=-2, b=2, mean=0, std=0.02, bias=0.0 
2023/06/05 12:46:40 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io
2023/06/05 12:46:40 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future.
2023/06/05 12:46:40 - mmengine - INFO - Checkpoints will be saved to /mnt/petrelfs/luzeyu/workspace/fakebench/mmpretrain/workdir/convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1.
2023/06/05 12:48:55 - mmengine - INFO - Epoch(train)  [1][100/171]  lr: 9.9258e-05  eta: 0:36:19  time: 1.3130  data_time: 0.7898  memory: 15587  loss: 0.0787
2023/06/05 12:50:28 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 12:50:28 - mmengine - INFO - Saving checkpoint at 1 epochs
2023/06/05 12:52:39 - mmengine - INFO - Epoch(val)  [1][100/171]    eta: 0:01:28  time: 0.4193  data_time: 0.0114  memory: 15587  
2023/06/05 12:55:58 - mmengine - INFO - Epoch(val) [1][171/171]    accuracy/top1: 55.3354  single-label/precision_classwise: [53.94961166381836, 58.16838836669922]  single-label/recall_classwise: [72.5013198852539, 38.190677642822266]  single-label/f1-score_classwise: [61.86459732055664, 46.108585357666016]  data_time: 1.1301  time: 1.5548
2023/06/05 12:58:10 - mmengine - INFO - Epoch(train)  [2][100/171]  lr: 9.4576e-05  eta: 0:31:51  time: 1.3027  data_time: 0.7853  memory: 15582  loss: 0.0410
2023/06/05 12:59:39 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 12:59:39 - mmengine - INFO - Saving checkpoint at 2 epochs
2023/06/05 13:01:51 - mmengine - INFO - Epoch(val)  [2][100/171]    eta: 0:01:28  time: 0.4147  data_time: 0.0073  memory: 15582  
2023/06/05 13:05:03 - mmengine - INFO - Epoch(val) [2][171/171]    accuracy/top1: 57.0644  single-label/precision_classwise: [55.60972595214844, 59.5088005065918]  single-label/recall_classwise: [69.76725769042969, 44.3773307800293]  single-label/f1-score_classwise: [61.88916015625, 50.84108352661133]  data_time: 1.1049  time: 1.5173
2023/06/05 13:07:17 - mmengine - INFO - Epoch(train)  [3][100/171]  lr: 8.6021e-05  eta: 0:27:52  time: 1.2462  data_time: 0.7296  memory: 15582  loss: 0.0267
2023/06/05 13:08:47 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:08:47 - mmengine - INFO - Saving checkpoint at 3 epochs
2023/06/05 13:10:56 - mmengine - INFO - Epoch(val)  [3][100/171]    eta: 0:01:26  time: 0.4151  data_time: 0.0074  memory: 15582  
2023/06/05 13:14:12 - mmengine - INFO - Epoch(val) [3][171/171]    accuracy/top1: 59.1678  single-label/precision_classwise: [57.864349365234375, 60.974544525146484]  single-label/recall_classwise: [67.26914978027344, 51.07648468017578]  single-label/f1-score_classwise: [62.21332550048828, 55.58834457397461]  data_time: 1.0999  time: 1.5125
2023/06/05 13:16:24 - mmengine - INFO - Epoch(train)  [4][100/171]  lr: 7.4429e-05  eta: 0:24:00  time: 1.1503  data_time: 0.5665  memory: 15582  loss: 0.0227
2023/06/05 13:17:55 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:17:55 - mmengine - INFO - Saving checkpoint at 4 epochs
2023/06/05 13:20:06 - mmengine - INFO - Epoch(val)  [4][100/171]    eta: 0:01:28  time: 0.4146  data_time: 0.0073  memory: 15582  
2023/06/05 13:23:24 - mmengine - INFO - Epoch(val) [4][171/171]    accuracy/top1: 61.0840  single-label/precision_classwise: [60.46040725708008, 61.78255081176758]  single-label/recall_classwise: [63.92573165893555, 58.245819091796875]  single-label/f1-score_classwise: [62.144798278808594, 59.96207809448242]  data_time: 1.1216  time: 1.5337
2023/06/05 13:25:37 - mmengine - INFO - Epoch(train)  [5][100/171]  lr: 6.0935e-05  eta: 0:20:15  time: 1.3597  data_time: 0.8400  memory: 15582  loss: 0.0196
2023/06/05 13:27:07 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:27:07 - mmengine - INFO - Saving checkpoint at 5 epochs
2023/06/05 13:29:17 - mmengine - INFO - Epoch(val)  [5][100/171]    eta: 0:01:27  time: 0.4153  data_time: 0.0076  memory: 15582  
2023/06/05 13:32:31 - mmengine - INFO - Epoch(val) [5][171/171]    accuracy/top1: 63.2538  single-label/precision_classwise: [63.82039260864258, 62.734127044677734]  single-label/recall_classwise: [61.09889221191406, 65.40599822998047]  single-label/f1-score_classwise: [62.429996490478516, 64.04220581054688]  data_time: 1.1051  time: 1.5179
2023/06/05 13:34:45 - mmengine - INFO - Epoch(train)  [6][100/171]  lr: 4.6860e-05  eta: 0:16:30  time: 1.2642  data_time: 0.7471  memory: 15582  loss: 0.0249
2023/06/05 13:35:48 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:36:16 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:36:16 - mmengine - INFO - Saving checkpoint at 6 epochs
2023/06/05 13:38:26 - mmengine - INFO - Epoch(val)  [6][100/171]    eta: 0:01:27  time: 0.4141  data_time: 0.0068  memory: 15582  
2023/06/05 13:41:43 - mmengine - INFO - Epoch(val) [6][171/171]    accuracy/top1: 65.1213  single-label/precision_classwise: [67.60926055908203, 63.2560920715332]  single-label/recall_classwise: [57.97425079345703, 72.25959014892578]  single-label/f1-score_classwise: [62.42214584350586, 67.45874786376953]  data_time: 1.1152  time: 1.5266
2023/06/05 13:43:54 - mmengine - INFO - Epoch(train)  [7][100/171]  lr: 3.3582e-05  eta: 0:12:45  time: 1.2457  data_time: 0.6590  memory: 15582  loss: 0.0133
2023/06/05 13:45:22 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:45:22 - mmengine - INFO - Saving checkpoint at 7 epochs
2023/06/05 13:47:31 - mmengine - INFO - Epoch(val)  [7][100/171]    eta: 0:01:27  time: 0.4144  data_time: 0.0072  memory: 15582  
2023/06/05 13:50:45 - mmengine - INFO - Epoch(val) [7][171/171]    accuracy/top1: 66.8487  single-label/precision_classwise: [72.02302551269531, 63.65269470214844]  single-label/recall_classwise: [55.034019470214844, 78.64872741699219]  single-label/f1-score_classwise: [62.39270782470703, 70.36055755615234]  data_time: 1.0949  time: 1.5062
2023/06/05 13:53:00 - mmengine - INFO - Epoch(train)  [8][100/171]  lr: 2.2401e-05  eta: 0:09:00  time: 1.1702  data_time: 0.2989  memory: 15582  loss: 0.0178
2023/06/05 13:54:27 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 13:54:27 - mmengine - INFO - Saving checkpoint at 8 epochs
2023/06/05 13:56:37 - mmengine - INFO - Epoch(val)  [8][100/171]    eta: 0:01:28  time: 0.4149  data_time: 0.0075  memory: 15582  
2023/06/05 13:59:52 - mmengine - INFO - Epoch(val) [8][171/171]    accuracy/top1: 68.0002  single-label/precision_classwise: [76.03317260742188, 63.76682662963867]  single-label/recall_classwise: [52.5141487121582, 83.46717834472656]  single-label/f1-score_classwise: [62.12214279174805, 72.29901885986328]  data_time: 1.1078  time: 1.5206
2023/06/05 14:02:06 - mmengine - INFO - Epoch(train)  [9][100/171]  lr: 1.4410e-05  eta: 0:05:16  time: 1.1970  data_time: 0.6773  memory: 15582  loss: 0.0133
2023/06/05 14:03:38 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 14:03:38 - mmengine - INFO - Saving checkpoint at 9 epochs
2023/06/05 14:05:49 - mmengine - INFO - Epoch(val)  [9][100/171]    eta: 0:01:27  time: 0.4148  data_time: 0.0075  memory: 15582  
2023/06/05 14:09:05 - mmengine - INFO - Epoch(val) [9][171/171]    accuracy/top1: 68.9658  single-label/precision_classwise: [80.15715789794922, 63.84469985961914]  single-label/recall_classwise: [50.35965347290039, 87.54890441894531]  single-label/f1-score_classwise: [61.85696029663086, 73.84107971191406]  data_time: 1.1153  time: 1.5259
2023/06/05 14:11:17 - mmengine - INFO - Epoch(train) [10][100/171]  lr: 1.0393e-05  eta: 0:01:32  time: 1.2602  data_time: 0.7340  memory: 15582  loss: 0.0136
2023/06/05 14:12:46 - mmengine - INFO - Exp name: convnext_small_4xb256_stylegan3_1m_lr1e-4_aug_5e-1_20230605_124607
2023/06/05 14:12:46 - mmengine - INFO - Saving checkpoint at 10 epochs
2023/06/05 14:14:57 - mmengine - INFO - Epoch(val) [10][100/171]    eta: 0:01:27  time: 0.4147  data_time: 0.0077  memory: 15582  
2023/06/05 14:18:14 - mmengine - INFO - Epoch(val) [10][171/171]    accuracy/top1: 69.6766  single-label/precision_classwise: [84.07218170166016, 63.845306396484375]  single-label/recall_classwise: [48.50525665283203, 90.82183837890625]  single-label/f1-score_classwise: [61.51790237426758, 74.98099517822266]  data_time: 1.1203  time: 1.5335