[填写这里]
I modified the imagnet related configuration file to run my own 4-category data set, and then modified the evaluation expression and found that the training process will not display the loss of each generation
相关信息
pip list | grep "mmcv\|mmcls\|^torch" 命令的输出
[填写这里]
3. 如果你是在训练过程中遇到的问题,请填写完整的训练日志和报错信息
[填写这里]
2022-05-24 09:27:02,125 - mmcls - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0]
CUDA available: False
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.7.1
PyTorch compiling details: PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CPU capability usage: AVX2
- Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS=-fvisibility-inlines-hidden -std=c++14 -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /tmp/build/80754af9/pytorch_1614404293469/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placeh/include -fdebug-prefix-map=/tmp/build/80754af9/pytorch_1614404293469/work=/usr/local/src/conda/pytorch-1.7.1 -fdebug-prefix-map=/tmp/build/80754af9/pytorch_1614404293469/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placeh=/usr/local/src/conda-prefix -Wno-deprecated-declarations -Wno-attributes -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=0, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=ON, USE_OPENMP=ON,
TorchVision: 0.8.0a0
OpenCV: 4.5.5
MMCV: 1.5.1
MMCV Compiler: GCC 7.5
MMCV CUDA Compiler: not available
MMClassification: 0.23.0+877ea30
------------------------------------------------------------
2022-05-24 09:27:02,126 - mmcls - INFO - Distributed training: False
2022-05-24 09:27:02,714 - mmcls - INFO - Config:
model = dict(
type='ImageClassifier',
backbone=dict(
type='Res2Net',
depth=50,
scales=8,
base_width=26,
deep_stem=False,
avg_down=False),
neck=dict(type='GlobalAveragePooling'),
head=dict(
type='LinearClsHead',
num_classes=4,
in_channels=2048,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
topk=(1, )))
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224, backend='pillow'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='Resize', size=(256, -1), backend='pillow'),
dict(type='CenterCrop', crop_size=224),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type='ImageNet',
data_prefix=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/train',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224, backend='pillow'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
],
classes=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/classmap.txt'
),
val=dict(
type='ImageNet',
data_prefix=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/val',
ann_file=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/val.txt',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='Resize', size=(256, -1), backend='pillow'),
dict(type='CenterCrop', crop_size=224),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
],
classes=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/classmap.txt'
),
test=dict(
type='ImageNet',
data_prefix=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/val',
ann_file=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/val.txt',
pipeline=[
dict(type='LoadImageFromFile'),
dict(type='Resize', size=(256, -1), backend='pillow'),
dict(type='CenterCrop', crop_size=224),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
],
classes=
'/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/classmap.txt'
))
evaluation = dict(
interval=1, metric='accuracy', metric_options=dict(topk=(1, )))
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(policy='step', step=[30, 60, 90])
runner = dict(type='EpochBasedRunner', max_epochs=100)
checkpoint_config = dict(interval=1)
log_config = dict(interval=500, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = '/home/xieweiming/mwx/mmclassification/checkpoints/res2net50-w26-s8_3rdparty_8xb32_in1k_20210927-f547a94b.pth'
resume_from = None
workflow = [('train', 1)]
work_dir = '4classes/res2net50_cutoutsmall_1_lr_0.01_80'
gpu_ids = [0]
2022-05-24 09:27:02,714 - mmcls - INFO - Set random seed to 1491118164, deterministic: False
2022-05-24 09:27:03,187 - mmcls - INFO - initialize LinearClsHead with init_cfg {'type': 'Normal', 'layer': 'Linear', 'std': 0.01}
Name of parameter - Initialization information
backbone.conv1.weight - torch.Size([64, 3, 7, 7]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.bn1.weight - torch.Size([64]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.bn1.bias - torch.Size([64]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.conv1.weight - torch.Size([208, 64, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bn1.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bn1.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.conv3.weight - torch.Size([256, 208, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bn3.weight - torch.Size([256]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer1.0.bn3.bias - torch.Size([256]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.downsample.0.weight - torch.Size([256, 64, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.downsample.1.weight - torch.Size([256]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.downsample.1.bias - torch.Size([256]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.0.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.1.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.2.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.3.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.4.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.5.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.convs.6.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.0.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.0.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.1.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.1.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.2.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.2.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.3.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.3.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.4.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.4.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.5.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.5.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.6.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.0.bns.6.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.conv1.weight - torch.Size([208, 256, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bn1.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bn1.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.conv3.weight - torch.Size([256, 208, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bn3.weight - torch.Size([256]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer1.1.bn3.bias - torch.Size([256]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.0.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.1.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.2.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.3.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.4.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.5.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.convs.6.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.0.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.0.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.1.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.1.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.2.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.2.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.3.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.3.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.4.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.4.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.5.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.5.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.6.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.1.bns.6.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.conv1.weight - torch.Size([208, 256, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bn1.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bn1.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.conv3.weight - torch.Size([256, 208, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bn3.weight - torch.Size([256]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer1.2.bn3.bias - torch.Size([256]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.0.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.1.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.2.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.3.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.4.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.5.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.convs.6.weight - torch.Size([26, 26, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.0.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.0.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.1.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.1.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.2.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.2.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.3.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.3.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.4.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.4.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.5.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.5.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.6.weight - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer1.2.bns.6.bias - torch.Size([26]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.conv1.weight - torch.Size([416, 256, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bn1.weight - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bn1.bias - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.conv3.weight - torch.Size([512, 416, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bn3.weight - torch.Size([512]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer2.0.bn3.bias - torch.Size([512]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.downsample.0.weight - torch.Size([512, 256, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.downsample.1.weight - torch.Size([512]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.downsample.1.bias - torch.Size([512]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.0.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.1.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.2.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.3.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.4.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.5.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.convs.6.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.0.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.0.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.1.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.1.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.2.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.2.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.3.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.3.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.4.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.4.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.5.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.5.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.6.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.0.bns.6.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.conv1.weight - torch.Size([416, 512, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bn1.weight - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bn1.bias - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.conv3.weight - torch.Size([512, 416, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bn3.weight - torch.Size([512]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer2.1.bn3.bias - torch.Size([512]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.0.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.1.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.2.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.3.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.4.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.5.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.convs.6.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.0.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.0.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.1.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.1.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.2.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.2.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.3.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.3.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.4.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.4.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.5.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.5.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.6.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.1.bns.6.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.conv1.weight - torch.Size([416, 512, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bn1.weight - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bn1.bias - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.conv3.weight - torch.Size([512, 416, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bn3.weight - torch.Size([512]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer2.2.bn3.bias - torch.Size([512]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.0.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.1.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.2.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.3.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.4.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.5.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.convs.6.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.0.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.0.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.1.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.1.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.2.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.2.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.3.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.3.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.4.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.4.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.5.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.5.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.6.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.2.bns.6.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.conv1.weight - torch.Size([416, 512, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bn1.weight - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bn1.bias - torch.Size([416]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.conv3.weight - torch.Size([512, 416, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bn3.weight - torch.Size([512]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer2.3.bn3.bias - torch.Size([512]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.0.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.1.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.2.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.3.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.4.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.5.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.convs.6.weight - torch.Size([52, 52, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.0.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.0.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.1.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.1.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.2.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.2.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.3.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.3.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.4.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.4.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.5.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.5.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.6.weight - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer2.3.bns.6.bias - torch.Size([52]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.conv1.weight - torch.Size([832, 512, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bn1.weight - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bn1.bias - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.conv3.weight - torch.Size([1024, 832, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bn3.weight - torch.Size([1024]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer3.0.bn3.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.downsample.0.weight - torch.Size([1024, 512, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.downsample.1.weight - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.downsample.1.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.0.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.1.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.2.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.3.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.4.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.5.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.convs.6.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.0.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.0.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.1.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.1.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.2.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.2.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.3.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.3.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.4.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.4.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.5.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.5.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.6.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.0.bns.6.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.conv1.weight - torch.Size([832, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bn1.weight - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bn1.bias - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.conv3.weight - torch.Size([1024, 832, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bn3.weight - torch.Size([1024]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer3.1.bn3.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.0.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.1.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.2.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.3.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.4.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.5.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.convs.6.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.0.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.0.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.1.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.1.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.2.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.2.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.3.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.3.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.4.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.4.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.5.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.5.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.6.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.1.bns.6.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.conv1.weight - torch.Size([832, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bn1.weight - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bn1.bias - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.conv3.weight - torch.Size([1024, 832, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bn3.weight - torch.Size([1024]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer3.2.bn3.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.0.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.1.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.2.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.3.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.4.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.5.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.convs.6.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.0.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.0.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.1.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.1.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.2.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.2.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.3.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.3.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.4.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.4.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.5.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.5.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.6.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.2.bns.6.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.conv1.weight - torch.Size([832, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bn1.weight - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bn1.bias - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.conv3.weight - torch.Size([1024, 832, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bn3.weight - torch.Size([1024]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer3.3.bn3.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.0.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.1.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.2.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.3.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.4.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.5.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.convs.6.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.0.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.0.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.1.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.1.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.2.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.2.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.3.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.3.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.4.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.4.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.5.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.5.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.6.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.3.bns.6.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.conv1.weight - torch.Size([832, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bn1.weight - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bn1.bias - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.conv3.weight - torch.Size([1024, 832, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bn3.weight - torch.Size([1024]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer3.4.bn3.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.0.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.1.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.2.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.3.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.4.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.5.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.convs.6.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.0.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.0.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.1.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.1.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.2.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.2.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.3.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.3.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.4.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.4.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.5.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.5.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.6.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.4.bns.6.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.conv1.weight - torch.Size([832, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bn1.weight - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bn1.bias - torch.Size([832]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.conv3.weight - torch.Size([1024, 832, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bn3.weight - torch.Size([1024]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer3.5.bn3.bias - torch.Size([1024]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.0.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.1.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.2.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.3.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.4.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.5.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.convs.6.weight - torch.Size([104, 104, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.0.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.0.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.1.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.1.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.2.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.2.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.3.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.3.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.4.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.4.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.5.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.5.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.6.weight - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer3.5.bns.6.bias - torch.Size([104]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.conv1.weight - torch.Size([1664, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bn1.weight - torch.Size([1664]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bn1.bias - torch.Size([1664]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.conv3.weight - torch.Size([2048, 1664, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bn3.weight - torch.Size([2048]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer4.0.bn3.bias - torch.Size([2048]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.downsample.0.weight - torch.Size([2048, 1024, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.downsample.1.weight - torch.Size([2048]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.downsample.1.bias - torch.Size([2048]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.0.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.1.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.2.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.3.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.4.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.5.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.convs.6.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.0.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.0.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.1.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.1.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.2.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.2.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.3.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.3.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.4.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.4.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.5.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.5.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.6.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.0.bns.6.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.conv1.weight - torch.Size([1664, 2048, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bn1.weight - torch.Size([1664]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bn1.bias - torch.Size([1664]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.conv3.weight - torch.Size([2048, 1664, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bn3.weight - torch.Size([2048]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer4.1.bn3.bias - torch.Size([2048]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.0.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.1.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.2.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.3.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.4.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.5.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.convs.6.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.0.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.0.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.1.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.1.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.2.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.2.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.3.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.3.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.4.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.4.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.5.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.5.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.6.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.1.bns.6.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.conv1.weight - torch.Size([1664, 2048, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bn1.weight - torch.Size([1664]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bn1.bias - torch.Size([1664]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.conv3.weight - torch.Size([2048, 1664, 1, 1]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bn3.weight - torch.Size([2048]):
Initialized by user-defined `init_weights` in Res2Net
backbone.layer4.2.bn3.bias - torch.Size([2048]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.0.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.1.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.2.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.3.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.4.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.5.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.convs.6.weight - torch.Size([208, 208, 3, 3]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.0.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.0.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.1.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.1.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.2.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.2.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.3.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.3.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.4.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.4.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.5.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.5.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.6.weight - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
backbone.layer4.2.bns.6.bias - torch.Size([208]):
The value is the same before and after calling `init_weights` of ImageClassifier
head.fc.weight - torch.Size([4, 2048]):
NormalInit: mean=0, std=0.01, bias=0
head.fc.bias - torch.Size([4]):
NormalInit: mean=0, std=0.01, bias=0
2022-05-24 09:27:03,891 - mmcls - INFO - load checkpoint from local path: /home/xieweiming/mwx/mmclassification/checkpoints/res2net50-w26-s8_3rdparty_8xb32_in1k_20210927-f547a94b.pth
2022-05-24 09:27:04,059 - mmcls - WARNING - The model and loaded state dict do not match exactly
size mismatch for head.fc.weight: copying a param with shape torch.Size([1000, 2048]) from checkpoint, the shape in current model is torch.Size([4, 2048]).
size mismatch for head.fc.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([4]).
2022-05-24 09:27:04,063 - mmcls - INFO - Start running, host: xieweiming@ubuntu, work_dir: /home/xieweiming/mwx/mmclassification/4classes/res2net50_cutoutsmall_1_lr_0.01_80
2022-05-24 09:27:04,064 - mmcls - INFO - Hooks will be executed in the following order:
before_run:
(VERY_HIGH ) StepLrUpdaterHook
(NORMAL ) CheckpointHook
(LOW ) EvalHook
(VERY_LOW ) TextLoggerHook
--------------------
before_train_epoch:
(VERY_HIGH ) StepLrUpdaterHook
(LOW ) IterTimerHook
(LOW ) EvalHook
(VERY_LOW ) TextLoggerHook
--------------------
before_train_iter:
(VERY_HIGH ) StepLrUpdaterHook
(LOW ) IterTimerHook
(LOW ) EvalHook
--------------------
after_train_iter:
(ABOVE_NORMAL) OptimizerHook
(NORMAL ) CheckpointHook
(LOW ) IterTimerHook
(LOW ) EvalHook
(VERY_LOW ) TextLoggerHook
--------------------
after_train_epoch:
(NORMAL ) CheckpointHook
(LOW ) EvalHook
(VERY_LOW ) TextLoggerHook
--------------------
before_val_epoch:
(LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook
--------------------
before_val_iter:
(LOW ) IterTimerHook
--------------------
after_val_iter:
(LOW ) IterTimerHook
--------------------
after_val_epoch:
(VERY_LOW ) TextLoggerHook
--------------------
after_run:
(VERY_LOW ) TextLoggerHook
--------------------
2022-05-24 09:27:04,064 - mmcls - INFO - workflow: [('train', 1)], max: 100 epochs
2022-05-24 09:27:04,064 - mmcls - INFO - Checkpoints will be saved to /home/xieweiming/mwx/mmclassification/4classes/res2net50_cutoutsmall_1_lr_0.01_80 by HardDiskBackend.
2022-05-24 10:00:37,627 - mmcls - INFO - Saving checkpoint at 1 epochs
2022-05-24 10:03:46,234 - mmcls - INFO - Epoch(val) [1][40] accuracy_top-1: 35.0274
2022-05-24 10:36:55,854 - mmcls - INFO - Saving checkpoint at 2 epochs
4. 如果你对 `mmcls` 文件夹下的代码做了其他相关的修改,请在这里写明
[填写这里]
推荐使用英语模板 General question,以便你的问题帮助更多人。
首先确认以下内容
描述你遇到的问题
[填写这里] I modified the imagnet related configuration file to run my own 4-category data set, and then modified the evaluation expression and found that the training process will not display the loss of each generation
相关信息
pip list | grep "mmcv\|mmcls\|^torch"
命令的输出 [填写这里]dataset settings
dataset_type = 'ImageNet' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='RandomResizedCrop', size=224, backend='pillow'), dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'), dict(type='Normalize', img_norm_cfg), dict(type='ImageToTensor', keys=['img']), dict(type='ToTensor', keys=['gt_label']), dict(type='Collect', keys=['img', 'gt_label']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict(type='Resize', size=(256, -1), backend='pillow'), dict(type='CenterCrop', crop_size=224), dict(type='Normalize', img_norm_cfg), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ] data = dict( samples_per_gpu=32, workers_per_gpu=2, train=dict( type=dataset_type, data_prefix="/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/train", classes="/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/classmap.txt", pipeline=train_pipeline), val=dict( type=dataset_type, data_prefix="/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/val", ann_file="/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/val.txt", classes="/home/xieweiming/mwx/mmclassification/data_4_cutout/imagenet/meta/classmap.txt", pipeline=test_pipeline), test=dict(
replace
data/val
withdata/test
for standard testevaluation = dict(interval=1, metric_options={'topk' : (1, )})