添加mmclassification-0.24.1代码，删除mmclassification-speed-benchmark

openmmlab_test/mmclassification-0.24.1/configs/vgg/vgg19bn_b32x8_imagenet.py

+_base_ = 'vgg19bn_8xb32_in1k.py'
+
+_deprecation_ = dict(
+    expected='vgg19bn_8xb32_in1k.py',
+    reference='https://github.com/open-mmlab/mmclassification/pull/508',
+)

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/README.md

+# Vision Transformer
+
+> [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://arxiv.org/pdf/2010.11929.pdf)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/142579081-b5718032-6581-472b-8037-ea66aaa9e278.png" width="70%"/>
+</div>
+
+## Results and models
+
+The training step of Vision Transformers is divided into two steps. The first
+step is training the model on a large dataset, like ImageNet-21k, and get the
+pre-trained model. And the second step is training the model on the target
+dataset, like ImageNet-1k, and get the fine-tuned model. Here, we provide both
+pre-trained models and fine-tuned models.
+
+### ImageNet-21k
+
+The pre-trained models on ImageNet-21k are used to fine-tune, and therefore don't have evaluation results.
+
+|   Model   | resolution | Params(M) | Flops(G) |                                                                 Download                                                                 |
+| :-------: | :--------: | :-------: | :------: | :--------------------------------------------------------------------------------------------------------------------------------------: |
+| ViT-B16\* |  224x224   |   86.86   |  33.03   | [model](https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-base-p16_3rdparty_pt-64xb64_in1k-224_20210928-02284250.pth)  |
+| ViT-B32\* |  224x224   |   88.30   |   8.56   | [model](https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-base-p32_3rdparty_pt-64xb64_in1k-224_20210928-eee25dd4.pth)  |
+| ViT-L16\* |  224x224   |  304.72   |  116.68  | [model](https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-large-p16_3rdparty_pt-64xb64_in1k-224_20210928-0001f9a1.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/google-research/vision_transformer#available-vit-models).*
+
+### ImageNet-1k
+
+|     Model     |   Pretrain   | resolution | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) |                              Config                              |                              Download                              |
+| :-----------: | :----------: | :--------: | :-------: | :------: | :-------: | :-------: | :--------------------------------------------------------------: | :----------------------------------------------------------------: |
+|   ViT-B16\*   | ImageNet-21k |  384x384   |   86.86   |  33.03   |   85.43   |   97.77   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vision_transformer/vit-base-p16_ft-64xb64_in1k-384.py) | [model](https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-98e8652b.pth) |
+|   ViT-B32\*   | ImageNet-21k |  384x384   |   88.30   |   8.56   |   84.01   |   97.08   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vision_transformer/vit-base-p32_ft-64xb64_in1k-384.py) | [model](https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p32_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-9cea8599.pth) |
+|   ViT-L16\*   | ImageNet-21k |  384x384   |  304.72   |  116.68  |   85.63   |   97.63   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vision_transformer/vit-large-p16_ft-64xb64_in1k-384.py) | [model](https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-large-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-b20ba619.pth) |
+| ViT-B16 (IPU) | ImageNet-21k |  224x224   |   86.86   |  33.03   |   81.22   |   95.56   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/vision_transformer/vit-base-p16_ft-4xb544-ipu_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/vit/vit-base-p16_ft-4xb544-ipu_in1k_20220603-c215811a.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/vit/vit-base-p16_ft-4xb544-ipu_in1k.log) |
+
+*Models with * are converted from the [official repo](https://github.com/google-research/vision_transformer#available-vit-models). The config files of these models are only for validation. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.*
+
+## Citation
+
+```
+@inproceedings{
+  dosovitskiy2021an,
+  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
+  author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
+  booktitle={International Conference on Learning Representations},
+  year={2021},
+  url={https://openreview.net/forum?id=YicbFdNTTy}
+}
+```

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/metafile.yml

+Collections:
+  - Name: Vision Transformer
+    Metadata:
+      Architecture:
+        - Attention Dropout
+        - Convolution
+        - Dense Connections
+        - Dropout
+        - GELU
+        - Layer Normalization
+        - Multi-Head Attention
+        - Scaled Dot-Product Attention
+        - Tanh Activation
+    Paper:
+      URL: https://arxiv.org/pdf/2010.11929.pdf
+      Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale'
+    README: configs/vision_transformer/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmclassification/blob/v0.17.0/mmcls/models/backbones/vision_transformer.py
+      Version: v0.17.0
+
+Models:
+  - Name: vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384
+    In Collection: Vision Transformer
+    Metadata:
+      FLOPs: 33030000000
+      Parameters: 86860000
+      Training Data:
+        - ImageNet-21k
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 85.43
+        Top 5 Accuracy: 97.77
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-98e8652b.pth
+    Converted From:
+      Weights: https://console.cloud.google.com/storage/browser/_details/vit_models/augreg/B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz
+      Code: https://github.com/google-research/vision_transformer/blob/88a52f8892c80c10de99194990a517b4d80485fd/vit_jax/models.py#L208
+    Config: configs/vision_transformer/vit-base-p16_ft-64xb64_in1k-384.py
+  - Name: vit-base-p32_in21k-pre-3rdparty_ft-64xb64_in1k-384
+    In Collection: Vision Transformer
+    Metadata:
+      FLOPs: 8560000000
+      Parameters: 88300000
+      Training Data:
+        - ImageNet-21k
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 84.01
+        Top 5 Accuracy: 97.08
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p32_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-9cea8599.pth
+    Converted From:
+      Weights: https://console.cloud.google.com/storage/browser/_details/vit_models/augreg/B_32-i21k-300ep-lr_0.001-aug_light1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz
+      Code: https://github.com/google-research/vision_transformer/blob/88a52f8892c80c10de99194990a517b4d80485fd/vit_jax/models.py#L208
+    Config: configs/vision_transformer/vit-base-p32_ft-64xb64_in1k-384.py
+  - Name: vit-large-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384
+    In Collection: Vision Transformer
+    Metadata:
+      FLOPs: 116680000000
+      Parameters: 304720000
+      Training Data:
+        - ImageNet-21k
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 85.63
+        Top 5 Accuracy: 97.63
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-large-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-b20ba619.pth
+    Converted From:
+      Weights: https://console.cloud.google.com/storage/browser/_details/vit_models/augreg/L_16-i21k-300ep-lr_0.001-aug_strong1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz
+      Code: https://github.com/google-research/vision_transformer/blob/88a52f8892c80c10de99194990a517b4d80485fd/vit_jax/models.py#L208
+    Config: configs/vision_transformer/vit-large-p16_ft-64xb64_in1k-384.py

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-base-p16_ft-4xb544-ipu_in1k.py

+_base_ = [
+    '../_base_/models/vit-base-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/default_runtime.py'
+]
+
+# specific to vit pretrain
+paramwise_cfg = dict(custom_keys={
+    '.cls_token': dict(decay_mult=0.0),
+    '.pos_embed': dict(decay_mult=0.0)
+})
+
+pretrained = 'https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-base-p16_3rdparty_pt-64xb64_in1k-224_20210928-02284250.pth'  # noqa
+
+model = dict(
+    head=dict(
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0, _delete_=True), ),
+    backbone=dict(
+        img_size=224,
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint=pretrained,
+            _delete_=True,
+            prefix='backbone')))
+
+img_norm_cfg = dict(
+    mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], 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='ToHalf', keys=['img']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', size=(224, -1), backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToHalf', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+# change batch size
+data = dict(
+    samples_per_gpu=17,
+    workers_per_gpu=16,
+    drop_last=True,
+    train=dict(pipeline=train_pipeline),
+    train_dataloader=dict(mode='async'),
+    val=dict(pipeline=test_pipeline, ),
+    val_dataloader=dict(samples_per_gpu=4, workers_per_gpu=1),
+    test=dict(pipeline=test_pipeline),
+    test_dataloader=dict(samples_per_gpu=4, workers_per_gpu=1))
+
+# remove clip-norm
+optimizer_config = dict()
+
+# optimizer
+optimizer = dict(
+    type='SGD',
+    lr=0.08,
+    weight_decay=1e-5,
+    momentum=0.9,
+    paramwise_cfg=paramwise_cfg,
+)
+
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    min_lr=0,
+    warmup='linear',
+    warmup_iters=800,
+    warmup_ratio=0.02,
+)
+
+# ipu cfg
+# model partition config
+ipu_model_cfg = dict(
+    train_split_edges=[
+        dict(layer_to_call='backbone.patch_embed', ipu_id=0),
+        dict(layer_to_call='backbone.layers.3', ipu_id=1),
+        dict(layer_to_call='backbone.layers.6', ipu_id=2),
+        dict(layer_to_call='backbone.layers.9', ipu_id=3)
+    ],
+    train_ckpt_nodes=['backbone.layers.{}'.format(i) for i in range(12)])
+
+# device config
+options_cfg = dict(
+    randomSeed=42,
+    partialsType='half',
+    train_cfg=dict(
+        executionStrategy='SameAsIpu',
+        Training=dict(gradientAccumulation=32),
+        availableMemoryProportion=[0.3, 0.3, 0.3, 0.3],
+    ),
+    eval_cfg=dict(deviceIterations=1, ),
+)
+
+# add model partition config and device config to runner
+runner = dict(
+    type='IterBasedRunner',
+    ipu_model_cfg=ipu_model_cfg,
+    options_cfg=options_cfg,
+    max_iters=5000)
+
+checkpoint_config = dict(interval=1000)
+
+fp16 = dict(loss_scale=256.0, velocity_accum_type='half', accum_type='half')

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-base-p16_ft-64xb64_in1k-384.py

+_base_ = [
+    '../_base_/models/vit-base-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(img_size=384))
+
+img_norm_cfg = dict(
+    mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', size=384, 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=(384, -1), backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline),
+)

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-base-p16_pt-64xb64_in1k-224.py

+_base_ = [
+    '../_base_/models/vit-base-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(
+        augments=dict(type='BatchMixup', alpha=0.2, num_classes=1000,
+                      prob=1.)))

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-base-p32_ft-64xb64_in1k-384.py

+_base_ = [
+    '../_base_/models/vit-base-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(img_size=384))
+
+img_norm_cfg = dict(
+    mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', size=384, 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=(384, -1), backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline),
+)

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-base-p32_pt-64xb64_in1k-224.py

+_base_ = [
+    '../_base_/models/vit-base-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(
+        augments=dict(type='BatchMixup', alpha=0.2, num_classes=1000,
+                      prob=1.)))

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-large-p16_ft-64xb64_in1k-384.py

+_base_ = [
+    '../_base_/models/vit-large-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(img_size=384))
+
+img_norm_cfg = dict(
+    mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', size=384, 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=(384, -1), backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline),
+)

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-large-p16_pt-64xb64_in1k-224.py

+_base_ = [
+    '../_base_/models/vit-large-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(
+        augments=dict(type='BatchMixup', alpha=0.2, num_classes=1000,
+                      prob=1.)))

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-large-p32_ft-64xb64_in1k-384.py

+# Refer to pytorch-image-models
+_base_ = [
+    '../_base_/models/vit-large-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(img_size=384))
+
+img_norm_cfg = dict(
+    mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', size=384, 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=(384, -1), backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    train=dict(pipeline=train_pipeline),
+    val=dict(pipeline=test_pipeline),
+    test=dict(pipeline=test_pipeline),
+)

openmmlab_test/mmclassification-0.24.1/configs/vision_transformer/vit-large-p32_pt-64xb64_in1k-224.py

+_base_ = [
+    '../_base_/models/vit-large-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(
+        augments=dict(type='BatchMixup', alpha=0.2, num_classes=1000,
+                      prob=1.)))

openmmlab_test/mmclassification-0.24.1/configs/wrn/README.md

+# Wide-ResNet
+
+> [Wide Residual Networks](https://arxiv.org/abs/1605.07146)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/156701329-2c7ec7bc-23da-401b-86bf-dea8567ccee8.png" width="90%"/>
+</div>
+
+## Results and models
+
+### ImageNet-1k
+
+|      Model      | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) |                                   Config                                   |                                   Download                                   |
+| :-------------: | :-------: | :------: | :-------: | :-------: | :------------------------------------------------------------------------: | :--------------------------------------------------------------------------: |
+|    WRN-50\*     |   68.88   |  11.44   |   78.48   |   94.08   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/wrn/wide-resnet50_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth) |
+|    WRN-101\*    |  126.89   |  22.81   |   78.84   |   94.28   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/wrn/wide-resnet101_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet101_3rdparty_8xb32_in1k_20220304-8d5f9d61.pth) |
+| WRN-50 (timm)\* |   68.88   |  11.44   |   81.45   |   95.53   | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/wrn/wide-resnet50_timm_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty-timm_8xb32_in1k_20220304-83ae4399.pth) |
+
+*Models with * are converted from the [TorchVision](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py) and [TIMM](https://github.com/rwightman/pytorch-image-models/blob/master). The config files of these models are only for inference. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.*
+
+## Citation
+
+```bibtex
+@INPROCEEDINGS{Zagoruyko2016WRN,
+    author = {Sergey Zagoruyko and Nikos Komodakis},
+    title = {Wide Residual Networks},
+    booktitle = {BMVC},
+    year = {2016}}
+```

openmmlab_test/mmclassification-0.24.1/configs/wrn/metafile.yml

+Collections:
+  - Name: Wide-ResNet
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Epochs: 100
+      Batch Size: 256
+      Architecture:
+        - 1x1 Convolution
+        - Batch Normalization
+        - Convolution
+        - Global Average Pooling
+        - Max Pooling
+        - ReLU
+        - Residual Connection
+        - Softmax
+        - Wide Residual Block
+    Paper:
+      URL: https://arxiv.org/abs/1605.07146
+      Title: "Wide Residual Networks"
+    README: configs/wrn/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/resnet.py#L383
+      Version: v0.20.1
+
+Models:
+  - Name: wide-resnet50_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 11440000000  # 11.44G
+      Parameters: 68880000  # 68.88M
+    In Collection: Wide-ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.48
+          Top 5 Accuracy: 94.08
+    Weights: https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth
+    Config: configs/wrn/wide-resnet50_8xb32_in1k.py
+    Converted From:
+      Weights: https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth
+      Code: https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py
+  - Name: wide-resnet101_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 22810000000  # 22.81G
+      Parameters: 126890000 # 126.89M
+    In Collection: Wide-ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.84
+          Top 5 Accuracy: 94.28
+    Weights: https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet101_3rdparty_8xb32_in1k_20220304-8d5f9d61.pth
+    Config: configs/wrn/wide-resnet101_8xb32_in1k.py
+    Converted From:
+      Weights: https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth
+      Code: https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py
+  - Name: wide-resnet50_3rdparty-timm_8xb32_in1k
+    Metadata:
+      FLOPs: 11440000000  # 11.44G
+      Parameters: 68880000  # 68.88M
+    In Collection: Wide-ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.45
+          Top 5 Accuracy: 95.53
+    Weights: https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty-timm_8xb32_in1k_20220304-83ae4399.pth
+    Config: configs/wrn/wide-resnet50_timm_8xb32_in1k.py
+    Converted From:
+      Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/wide_resnet50_racm-8234f177.pth
+      Code: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/resnet.py

openmmlab_test/mmclassification-0.24.1/configs/wrn/wide-resnet101_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/wide-resnet50.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(depth=101))

openmmlab_test/mmclassification-0.24.1/configs/wrn/wide-resnet50_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/wide-resnet50.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-0.24.1/configs/wrn/wide-resnet50_timm_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/wide-resnet50.py',
+    '../_base_/datasets/imagenet_bs32_pil_bicubic.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]