add part code

configs/repvgg/repvgg-A0_deploy_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(deploy=True))

configs/repvgg/repvgg-A1_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='A1'))

configs/repvgg/repvgg-A2_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='A2'), head=dict(in_channels=1408))

configs/repvgg/repvgg-B0_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B0'), head=dict(in_channels=1280))

configs/repvgg/repvgg-B1_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B1'), head=dict(in_channels=2048))

configs/repvgg/repvgg-B1g2_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B1g2'), head=dict(in_channels=2048))

configs/repvgg/repvgg-B1g4_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B1g4'), head=dict(in_channels=2048))

configs/repvgg/repvgg-B2_8xb32_in1k.py

+_base_ = './repvgg-A0_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B2'), head=dict(in_channels=2560))

configs/repvgg/repvgg-B2g4_8xb32_in1k.py

+_base_ = './repvgg-B3_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B2g4'), head=dict(in_channels=2560))

configs/repvgg/repvgg-B3_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/repvgg-B3_lbs-mixup_in1k.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(
+    paramwise_cfg=dict(
+        bias_decay_mult=0.0,
+        custom_keys={
+            'branch_3x3.norm': dict(decay_mult=0.0),
+            'branch_1x1.norm': dict(decay_mult=0.0),
+            'branch_norm.bias': dict(decay_mult=0.0),
+        }))
+
+data_preprocessor = dict(
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+bgr_mean = data_preprocessor['mean'][::-1]
+bgr_std = data_preprocessor['std'][::-1]
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(
+        type='RandAugment',
+        policies='timm_increasing',
+        num_policies=2,
+        total_level=10,
+        magnitude_level=7,
+        magnitude_std=0.5,
+        hparams=dict(pad_val=[round(x) for x in bgr_mean])),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+# schedule settings
+param_scheduler = dict(
+    type='CosineAnnealingLR',
+    T_max=200,
+    by_epoch=True,
+    begin=0,
+    end=200,
+    convert_to_iter_based=True)
+
+train_cfg = dict(by_epoch=True, max_epochs=200)
+
+default_hooks = dict(
+    checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))

configs/repvgg/repvgg-B3g4_8xb32_in1k.py

+_base_ = './repvgg-B3_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='B3g4'))

configs/repvgg/repvgg-D2se_8xb32_in1k.py

+_base_ = './repvgg-B3_8xb32_in1k.py'
+
+model = dict(backbone=dict(arch='D2se'), head=dict(in_channels=2560))
+
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.0001,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=295,
+        eta_min=1.0e-6,
+        by_epoch=True,
+        begin=5,
+        end=300)
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=300)
+
+default_hooks = dict(
+    checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))

configs/res2net/README.md

+# Res2Net
+
+> [Res2Net: A New Multi-scale Backbone Architecture](https://arxiv.org/abs/1904.01169)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/142573547-cde68abf-287b-46db-a848-5cffe3068faf.png" width="50%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('res2net50-w14-s8_3rdparty_8xb32_in1k', 'demo/bird.JPEG')
+print(predict['pred_class'])
+print(predict['pred_score'])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('res2net50-w14-s8_3rdparty_8xb32_in1k', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Test:
+
+```shell
+python tools/test.py configs/res2net/res2net50-w14-s8_8xb32_in1k.py https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w14-s8_3rdparty_8xb32_in1k_20210927-bc967bf1.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                                     |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                  Config                   |                               Download                                |
+| :---------------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :---------------------------------------: | :-------------------------------------------------------------------: |
+| `res2net50-w14-s8_3rdparty_8xb32_in1k`\*  | From scratch |   25.06    |   4.22    |   78.14   |   93.85   | [config](res2net50-w14-s8_8xb32_in1k.py)  | [model](https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w14-s8_3rdparty_8xb32_in1k_20210927-bc967bf1.pth) |
+| `res2net50-w26-s8_3rdparty_8xb32_in1k`\*  | From scratch |   48.40    |   8.39    |   79.20   |   94.36   | [config](res2net50-w26-s8_8xb32_in1k.py)  | [model](https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w26-s8_3rdparty_8xb32_in1k_20210927-f547a94b.pth) |
+| `res2net101-w26-s4_3rdparty_8xb32_in1k`\* | From scratch |   45.21    |   8.12    |   79.19   |   94.44   | [config](res2net101-w26-s4_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/res2net/res2net101-w26-s4_3rdparty_8xb32_in1k_20210927-870b6c36.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net.py#L181). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@article{gao2019res2net,
+  title={Res2Net: A New Multi-scale Backbone Architecture},
+  author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
+  journal={IEEE TPAMI},
+  year={2021},
+  doi={10.1109/TPAMI.2019.2938758},
+}
+```

configs/res2net/metafile.yml

+Collections:
+  - Name: Res2Net
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Architecture:
+        - Batch Normalization
+        - Convolution
+        - Global Average Pooling
+        - ReLU
+        - Res2Net Block
+    Paper:
+      Title: 'Res2Net: A New Multi-scale Backbone Architecture'
+      URL: https://arxiv.org/abs/1904.01169
+    README: configs/res2net/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.17.0/mmcls/models/backbones/res2net.py
+      Version: v0.17.0
+
+Models:
+  - Name: res2net50-w14-s8_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 4220000000
+      Parameters: 25060000
+    In Collection: Res2Net
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.14
+          Top 5 Accuracy: 93.85
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w14-s8_3rdparty_8xb32_in1k_20210927-bc967bf1.pth
+    Converted From:
+      Weights: https://1drv.ms/u/s!AkxDDnOtroRPdOTqhF8ne_aakDI?e=EVb8Ri
+      Code: https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net.py#L221
+    Config: configs/res2net/res2net50-w14-s8_8xb32_in1k.py
+  - Name: res2net50-w26-s8_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 8390000000
+      Parameters: 48400000
+    In Collection: Res2Net
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.20
+          Top 5 Accuracy: 94.36
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w26-s8_3rdparty_8xb32_in1k_20210927-f547a94b.pth
+    Converted From:
+      Weights: https://1drv.ms/u/s!AkxDDnOtroRPdTrAd_Afzc26Z7Q?e=slYqsR
+      Code: https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net.py#L201
+    Config: configs/res2net/res2net50-w26-s8_8xb32_in1k.py
+  - Name: res2net101-w26-s4_3rdparty_8xb32_in1k
+    Metadata:
+      FLOPs: 8120000000
+      Parameters: 45210000
+    In Collection: Res2Net
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.19
+          Top 5 Accuracy: 94.44
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/res2net/res2net101-w26-s4_3rdparty_8xb32_in1k_20210927-870b6c36.pth
+    Converted From:
+      Weights: https://1drv.ms/u/s!AkxDDnOtroRPcJRgTLkahL0cFYw?e=nwbnic
+      Code: https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net.py#L181
+    Config: configs/res2net/res2net101-w26-s4_8xb32_in1k.py

configs/res2net/res2net101-w26-s4_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/res2net101-w26-s4.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/res2net/res2net50-w14-s8_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/res2net50-w14-s8.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/res2net/res2net50-w26-s8_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/res2net50-w26-s8.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/resnest/README.md

+# ResNeSt
+
+> [ResNeSt: Split-Attention Networks](https://arxiv.org/abs/2004.08955)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/142573827-a8189607-614b-4385-b579-b0db148b3db7.png" width="60%"/>
+</div>
+
+## Citation
+
+```
+@misc{zhang2020resnest,
+      title={ResNeSt: Split-Attention Networks},
+      author={Hang Zhang and Chongruo Wu and Zhongyue Zhang and Yi Zhu and Haibin Lin and Zhi Zhang and Yue Sun and Tong He and Jonas Mueller and R. Manmatha and Mu Li and Alexander Smola},
+      year={2020},
+      eprint={2004.08955},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

configs/resnest/_randaug_policies.py

+policies = [
+    dict(type='AutoContrast', prob=0.5),
+    dict(type='Equalize', prob=0.5),
+    dict(type='Invert', prob=0.5),
+    dict(
+        type='Rotate',
+        magnitude_key='angle',
+        magnitude_range=(0, 30),
+        pad_val=0,
+        prob=0.5,
+        random_negative_prob=0.5),
+    dict(
+        type='Posterize',
+        magnitude_key='bits',
+        magnitude_range=(0, 4),
+        prob=0.5),
+    dict(
+        type='Solarize',
+        magnitude_key='thr',
+        magnitude_range=(0, 256),
+        prob=0.5),
+    dict(
+        type='SolarizeAdd',
+        magnitude_key='magnitude',
+        magnitude_range=(0, 110),
+        thr=128,
+        prob=0.5),
+    dict(
+        type='ColorTransform',
+        magnitude_key='magnitude',
+        magnitude_range=(-0.9, 0.9),
+        prob=0.5,
+        random_negative_prob=0.),
+    dict(
+        type='Contrast',
+        magnitude_key='magnitude',
+        magnitude_range=(-0.9, 0.9),
+        prob=0.5,
+        random_negative_prob=0.),
+    dict(
+        type='Brightness',
+        magnitude_key='magnitude',
+        magnitude_range=(-0.9, 0.9),
+        prob=0.5,
+        random_negative_prob=0.),
+    dict(
+        type='Sharpness',
+        magnitude_key='magnitude',
+        magnitude_range=(-0.9, 0.9),
+        prob=0.5,
+        random_negative_prob=0.),
+    dict(
+        type='Shear',
+        magnitude_key='magnitude',
+        magnitude_range=(0, 0.3),
+        pad_val=0,
+        prob=0.5,
+        direction='horizontal',
+        random_negative_prob=0.5),
+    dict(
+        type='Shear',
+        magnitude_key='magnitude',
+        magnitude_range=(0, 0.3),
+        pad_val=0,
+        prob=0.5,
+        direction='vertical',
+        random_negative_prob=0.5),
+    dict(
+        type='Cutout',
+        magnitude_key='shape',
+        magnitude_range=(1, 41),
+        pad_val=0,
+        prob=0.5),
+    dict(
+        type='Translate',
+        magnitude_key='magnitude',
+        magnitude_range=(0, 0.3),
+        pad_val=0,
+        prob=0.5,
+        direction='horizontal',
+        random_negative_prob=0.5,
+        interpolation='bicubic'),
+    dict(
+        type='Translate',
+        magnitude_key='magnitude',
+        magnitude_range=(0, 0.3),
+        pad_val=0,
+        prob=0.5,
+        direction='vertical',
+        random_negative_prob=0.5,
+        interpolation='bicubic')
+]

configs/resnest/resnest101_32xb64_in1k.py

+_base_ = [
+    '../_base_/models/resnest101.py',
+    '../_base_/datasets/imagenet_bs64.py',
+    '../_base_/default_runtime.py',
+    './_randaug_policies.py',
+]
+
+# dataset settings
+
+# lighting params, in order of BGR
+EIGVAL = [55.4625, 4.7940, 1.1475]
+EIGVEC = [
+    [-0.5836, -0.6948, 0.4203],
+    [-0.5808, -0.0045, -0.8140],
+    [-0.5675, 0.7192, 0.4009],
+]
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandAugment',
+        policies={{_base_.policies}},
+        num_policies=2,
+        magnitude_level=12),
+    dict(type='EfficientNetRandomCrop', scale=256, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='ColorJitter', brightness=0.4, contrast=0.4, saturation=0.4),
+    dict(
+        type='Lighting',
+        eigval=EIGVAL,
+        eigvec=EIGVEC,
+        alphastd=0.1,
+        to_rgb=False),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='EfficientNetCenterCrop', crop_size=256, backend='pillow'),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+# schedule settings
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.8, momentum=0.9, weight_decay=1e-4),
+    paramwise_cfg=dict(bias_decay_mult=0., norm_decay_mult=0.),
+)
+
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=1e-6,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=265,
+        by_epoch=True,
+        begin=5,
+        end=270,
+    )
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=270)
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (32 GPUs) x (64 samples per GPU)
+auto_scale_lr = dict(base_batch_size=2048)