first commit

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)

configs/resnest/resnest200_64xb32_in1k.py

+_base_ = [
+    '../_base_/models/resnest200.py',
+    '../_base_/datasets/imagenet_bs32.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=320, 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=320, backend='pillow'),
+    dict(type='PackInputs'),
+]
+
+# 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 = (64 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=2048)

configs/resnest/resnest269_64xb32_in1k.py

+_base_ = [
+    '../_base_/models/resnest269.py',
+    '../_base_/datasets/imagenet_bs32.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=416, 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=416, 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 = (64 GPUs) x (32 samples per GPU)
+auto_scale_lr = dict(base_batch_size=2048)

configs/resnest/resnest50_32xb64_in1k.py

+_base_ = [
+    '../_base_/models/resnest50.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=224, 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)

configs/resnet/README.md

+# ResNet
+
+> [Deep Residual Learning for Image Recognition](https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html)
+
+<!-- [ALGORITHM] -->
+
+## Introduction
+
+**Residual Networks**, or **ResNets**, learn residual functions with reference to the layer inputs, instead of
+learning unreferenced functions. In the mainstream previous works, like VGG, the neural networks are a stack
+of layers and every layer attempts to fit a desired underlying mapping. In ResNets, a few stacked layers are
+grouped as a block, and the layers in a block attempts to learn a residual mapping.
+
+Formally, denoting the desired underlying mapping of a block as $\mathcal{H}(x)$, split the underlying mapping
+into the sum of the identity and the residual mapping as $\mathcal{H}(x) = x + \mathcal{F}(x)$, and let the
+stacked non-linear layers fit the residual mapping $\mathcal{F}(x)$.
+
+Many works proved this method makes deep neural networks easier to optimize, and can gain accuracy from
+considerably increased depth. Recently, the residual structure is widely used in various models.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/142574068-60cfdeea-c4ec-4c49-abb2-5dc2facafc3b.png" width="40%"/>
+</div>
+
+## Abstract
+
+<details>
+
+<summary>Show the paper's abstract</summary>
+
+<br>
+Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers.
+
+The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
+</br>
+
+</details>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('resnet18_8xb16_cifar10', '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('resnet18_8xb16_cifar10', 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))
+```
+
+**Train/Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Train:
+
+```shell
+python tools/train.py configs/resnet/resnet18_8xb16_cifar10.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/resnet/resnet18_8xb16_cifar10.py https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                              |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                    Config                     |                                 Download                                 |
+| :--------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :-------------------------------------------: | :----------------------------------------------------------------------: |
+| `resnet18_8xb32_in1k`              | From scratch |   11.69    |   1.82    |   69.90   |   89.43   |       [config](resnet18_8xb32_in1k.py)        | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.json) |
+| `resnet34_8xb32_in1k`              | From scratch |    2.18    |   3.68    |   73.62   |   91.59   |       [config](resnet34_8xb32_in1k.py)        | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.json) |
+| `resnet50_8xb32_in1k`              | From scratch |   25.56    |   4.12    |   76.55   |   93.06   |       [config](resnet50_8xb32_in1k.py)        | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.json) |
+| `resnet101_8xb32_in1k`             | From scratch |   44.55    |   7.85    |   77.97   |   94.06   |       [config](resnet101_8xb32_in1k.py)       | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.json) |
+| `resnet152_8xb32_in1k`             | From scratch |   60.19    |   11.58   |   78.48   |   94.13   |       [config](resnet152_8xb32_in1k.py)       | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.json) |
+| `resnetv1d50_8xb32_in1k`           | From scratch |   25.58    |   4.36    |   77.54   |   93.57   |      [config](resnetv1d50_8xb32_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.json) |
+| `resnetv1d101_8xb32_in1k`          | From scratch |   44.57    |   8.09    |   78.93   |   94.48   |     [config](resnetv1d101_8xb32_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.json) |
+| `resnetv1d152_8xb32_in1k`          | From scratch |   60.21    |   11.82   |   79.41   |   94.70   |     [config](resnetv1d152_8xb32_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.json) |
+| `resnet50_8xb32-fp16_in1k`         | From scratch |   25.56    |   4.12    |   76.30   |   93.07   |     [config](resnet50_8xb32-fp16_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.json) |
+| `resnet50_8xb256-rsb-a1-600e_in1k` | From scratch |   25.56    |   4.12    |   80.12   |   94.78   | [config](resnet50_8xb256-rsb-a1-600e_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a1-600e_in1k_20211228-20e21305.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a1-600e_in1k_20211228-20e21305.json) |
+| `resnet50_8xb256-rsb-a2-300e_in1k` | From scratch |   25.56    |   4.12    |   79.55   |   94.37   | [config](resnet50_8xb256-rsb-a2-300e_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a2-300e_in1k_20211228-0fd8be6e.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a2-300e_in1k_20211228-0fd8be6e.json) |
+| `resnet50_8xb256-rsb-a3-100e_in1k` | From scratch |   25.56    |   4.12    |   78.30   |   93.80   | [config](resnet50_8xb256-rsb-a3-100e_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a3-100e_in1k_20211228-3493673c.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a3-100e_in1k_20211228-3493673c.json) |
+| `resnetv1c50_8xb32_in1k`           | From scratch |   25.58    |   4.36    |   77.01   |   93.58   |      [config](resnetv1c50_8xb32_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.json) |
+| `resnetv1c101_8xb32_in1k`          | From scratch |   44.57    |   8.09    |   78.30   |   94.27   |     [config](resnetv1c101_8xb32_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.json) |
+| `resnetv1c152_8xb32_in1k`          | From scratch |   60.21    |   11.82   |   78.76   |   94.41   |     [config](resnetv1c152_8xb32_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.json) |
+
+### Image Classification on CIFAR-10
+
+| Model                     |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) |                Config                |                                              Download                                               |
+| :------------------------ | :----------: | :--------: | :-------: | :-------: | :----------------------------------: | :-------------------------------------------------------------------------------------------------: |
+| `resnet18_8xb16_cifar10`  | From scratch |   11.17    |   0.56    |   94.82   | [config](resnet18_8xb16_cifar10.py)  | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.json) |
+| `resnet34_8xb16_cifar10`  | From scratch |   21.28    |   1.16    |   95.34   | [config](resnet34_8xb16_cifar10.py)  | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.json) |
+| `resnet50_8xb16_cifar10`  | From scratch |   23.52    |   1.31    |   95.55   | [config](resnet50_8xb16_cifar10.py)  | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.json) |
+| `resnet101_8xb16_cifar10` | From scratch |   42.51    |   2.52    |   95.58   | [config](resnet101_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.json) |
+| `resnet152_8xb16_cifar10` | From scratch |   58.16    |   3.74    |   95.76   | [config](resnet152_8xb16_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.json) |
+
+### Image Classification on CIFAR-100
+
+| Model                     |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                Config                |                                          Download                                          |
+| :------------------------ | :----------: | :--------: | :-------: | :-------: | :-------: | :----------------------------------: | :----------------------------------------------------------------------------------------: |
+| `resnet50_8xb16_cifar100` | From scratch |   23.71    |   1.31    |   79.90   |   95.19   | [config](resnet50_8xb16_cifar100.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.json) |
+
+### Image Classification on CUB-200-2011
+
+| Model               |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) |             Config             |                                                    Download                                                     |
+| :------------------ | :----------: | :--------: | :-------: | :-------: | :----------------------------: | :-------------------------------------------------------------------------------------------------------------: |
+| `resnet50_8xb8_cub` | From scratch |   23.92    |   16.48   |   88.45   | [config](resnet50_8xb8_cub.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.json) |
+
+## Citation
+
+```bibtex
+@inproceedings{he2016deep,
+  title={Deep residual learning for image recognition},
+  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={770--778},
+  year={2016}
+}
+```

configs/resnet/metafile.yml

+Collections:
+  - Name: ResNet
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Epochs: 100
+      Batch Size: 256
+      Architecture:
+        - ResNet
+    Paper:
+      URL: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html
+      Title: "Deep Residual Learning for Image Recognition"
+    README: configs/resnet/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.15.0/mmcls/models/backbones/resnet.py#L383
+      Version: v0.15.0
+
+Models:
+  - Name: resnet18_8xb16_cifar10
+    Metadata:
+      Training Data: CIFAR-10
+      Epochs: 200
+      Batch Size: 128
+      FLOPs: 560000000
+      Parameters: 11170000
+    In Collection: ResNet
+    Results:
+      - Dataset: CIFAR-10
+        Metrics:
+          Top 1 Accuracy: 94.82
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth
+    Config: configs/resnet/resnet18_8xb16_cifar10.py
+  - Name: resnet34_8xb16_cifar10
+    Metadata:
+      Training Data: CIFAR-10
+      Epochs: 200
+      Batch Size: 128
+      FLOPs: 1160000000
+      Parameters: 21280000
+    In Collection: ResNet
+    Results:
+      - Dataset: CIFAR-10
+        Metrics:
+          Top 1 Accuracy: 95.34
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.pth
+    Config: configs/resnet/resnet34_8xb16_cifar10.py
+  - Name: resnet50_8xb16_cifar10
+    Metadata:
+      Training Data: CIFAR-10
+      Epochs: 200
+      Batch Size: 128
+      FLOPs: 1310000000
+      Parameters: 23520000
+    In Collection: ResNet
+    Results:
+      - Dataset: CIFAR-10
+        Metrics:
+          Top 1 Accuracy: 95.55
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.pth
+    Config: configs/resnet/resnet50_8xb16_cifar10.py
+  - Name: resnet101_8xb16_cifar10
+    Metadata:
+      Training Data: CIFAR-10
+      Epochs: 200
+      Batch Size: 128
+      FLOPs: 2520000000
+      Parameters: 42510000
+    In Collection: ResNet
+    Results:
+      - Dataset: CIFAR-10
+        Metrics:
+          Top 1 Accuracy: 95.58
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.pth
+    Config: configs/resnet/resnet101_8xb16_cifar10.py
+  - Name: resnet152_8xb16_cifar10
+    Metadata:
+      Training Data: CIFAR-10
+      Epochs: 200
+      Batch Size: 128
+      FLOPs: 3740000000
+      Parameters: 58160000
+    In Collection: ResNet
+    Results:
+      - Dataset: CIFAR-10
+        Metrics:
+          Top 1 Accuracy: 95.76
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.pth
+    Config: configs/resnet/resnet152_8xb16_cifar10.py
+  - Name: resnet50_8xb16_cifar100
+    Metadata:
+      Training Data: CIFAR-100
+      Epochs: 200
+      Batch Size: 128
+      FLOPs: 1310000000
+      Parameters: 23710000
+    In Collection: ResNet
+    Results:
+      - Dataset: CIFAR-100
+        Metrics:
+          Top 1 Accuracy: 79.90
+          Top 5 Accuracy: 95.19
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth
+    Config: configs/resnet/resnet50_8xb16_cifar100.py
+  - Name: resnet18_8xb32_in1k
+    Metadata:
+      FLOPs: 1820000000
+      Parameters: 11690000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 69.90
+          Top 5 Accuracy: 89.43
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth
+    Config: configs/resnet/resnet18_8xb32_in1k.py
+  - Name: resnet34_8xb32_in1k
+    Metadata:
+      FLOPs: 3680000000
+      Parameters: 2180000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 73.62
+          Top 5 Accuracy: 91.59
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth
+    Config: configs/resnet/resnet34_8xb32_in1k.py
+  - Name: resnet50_8xb32_in1k
+    Metadata:
+      FLOPs: 4120000000
+      Parameters: 25560000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 76.55
+          Top 5 Accuracy: 93.06
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth
+    Config: configs/resnet/resnet50_8xb32_in1k.py
+  - Name: resnet101_8xb32_in1k
+    Metadata:
+      FLOPs: 7850000000
+      Parameters: 44550000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 77.97
+          Top 5 Accuracy: 94.06
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth
+    Config: configs/resnet/resnet101_8xb32_in1k.py
+  - Name: resnet152_8xb32_in1k
+    Metadata:
+      FLOPs: 11580000000
+      Parameters: 60190000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.48
+          Top 5 Accuracy: 94.13
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth
+    Config: configs/resnet/resnet152_8xb32_in1k.py
+  - Name: resnetv1d50_8xb32_in1k
+    Metadata:
+      FLOPs: 4360000000
+      Parameters: 25580000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 77.54
+          Top 5 Accuracy: 93.57
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth
+    Config: configs/resnet/resnetv1d50_8xb32_in1k.py
+  - Name: resnetv1d101_8xb32_in1k
+    Metadata:
+      FLOPs: 8090000000
+      Parameters: 44570000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.93
+          Top 5 Accuracy: 94.48
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth
+    Config: configs/resnet/resnetv1d101_8xb32_in1k.py
+  - Name: resnetv1d152_8xb32_in1k
+    Metadata:
+      FLOPs: 11820000000
+      Parameters: 60210000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.41
+          Top 5 Accuracy: 94.70
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth
+    Config: configs/resnet/resnetv1d152_8xb32_in1k.py
+  - Name: resnet50_8xb32-fp16_in1k
+    Metadata:
+      FLOPs: 4120000000
+      Parameters: 25560000
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+        - Mixed Precision Training
+    In Collection: ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 76.30
+          Top 5 Accuracy: 93.07
+    Weights: https://download.openmmlab.com/mmclassification/v0/fp16/resnet50_batch256_fp16_imagenet_20210320-b3964210.pth
+    Config: configs/resnet/resnet50_8xb32-fp16_in1k.py
+  - Name: resnet50_8xb256-rsb-a1-600e_in1k
+    Metadata:
+      FLOPs: 4120000000
+      Parameters: 25560000
+      Training Techniques:
+        - LAMB
+        - Weight Decay
+        - Cosine Annealing
+        - Mixup
+        - CutMix
+        - RepeatAugSampler
+        - RandAugment
+      Epochs: 600
+      Batch Size: 2048
+    In Collection: ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 80.12
+          Top 5 Accuracy: 94.78
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a1-600e_in1k_20211228-20e21305.pth
+    Config: configs/resnet/resnet50_8xb256-rsb-a1-600e_in1k.py
+  - Name: resnet50_8xb256-rsb-a2-300e_in1k
+    Metadata:
+      FLOPs: 4120000000
+      Parameters: 25560000
+      Training Techniques:
+        - LAMB
+        - Weight Decay
+        - Cosine Annealing
+        - Mixup
+        - CutMix
+        - RepeatAugSampler
+        - RandAugment
+      Epochs: 300
+      Batch Size: 2048
+    In Collection: ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.55
+          Top 5 Accuracy: 94.37
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a2-300e_in1k_20211228-0fd8be6e.pth
+    Config: configs/resnet/resnet50_8xb256-rsb-a2-300e_in1k.py
+  - Name: resnet50_8xb256-rsb-a3-100e_in1k
+    Metadata:
+      FLOPs: 4120000000
+      Parameters: 25560000
+      Training Techniques:
+        - LAMB
+        - Weight Decay
+        - Cosine Annealing
+        - Mixup
+        - CutMix
+        - RandAugment
+      Batch Size: 2048
+    In Collection: ResNet
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.30
+          Top 5 Accuracy: 93.80
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb256-rsb-a3-100e_in1k_20211228-3493673c.pth
+    Config: configs/resnet/resnet50_8xb256-rsb-a3-100e_in1k.py
+  - Name: resnetv1c50_8xb32_in1k
+    Metadata:
+      FLOPs: 4360000000
+      Parameters: 25580000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 77.01
+          Top 5 Accuracy: 93.58
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.pth
+    Config: configs/resnet/resnetv1c50_8xb32_in1k.py
+  - Name: resnetv1c101_8xb32_in1k
+    Metadata:
+      FLOPs: 8090000000
+      Parameters: 44570000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.30
+          Top 5 Accuracy: 94.27
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.pth
+    Config: configs/resnet/resnetv1c101_8xb32_in1k.py
+  - Name: resnetv1c152_8xb32_in1k
+    Metadata:
+      FLOPs: 11820000000
+      Parameters: 60210000
+    In Collection: ResNet
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.76
+          Top 5 Accuracy: 94.41
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.pth
+    Config: configs/resnet/resnetv1c152_8xb32_in1k.py
+  - Name: resnet50_8xb8_cub
+    Metadata:
+      FLOPs: 16480000000
+      Parameters: 23920000
+    In Collection: ResNet
+    Results:
+      - Dataset: CUB-200-2011
+        Metrics:
+          Top 1 Accuracy: 88.45
+        Task: Image Classification
+    Pretrain: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth
+    Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb8_cub_20220307-57840e60.pth
+    Config: configs/resnet/resnet50_8xb8_cub.py

configs/resnet/resnet101_8xb16_cifar10.py

+_base_ = [
+    '../_base_/models/resnet101_cifar.py',
+    '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet101_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/resnet101.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet152_8xb16_cifar10.py

+_base_ = [
+    '../_base_/models/resnet152_cifar.py',
+    '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet152_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/resnet152.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet18_8xb16_cifar10.py

+_base_ = [
+    '../_base_/models/resnet18_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet18_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/resnet18.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet34_8xb16_cifar10.py

+_base_ = [
+    '../_base_/models/resnet34_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet34_8xb32_in1k.py

+_base_ = [
+    '../_base_/models/resnet34.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

configs/resnet/resnet50_32xb64-warmup-coslr_in1k.py

+_base_ = [
+    '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py',
+    '../_base_/schedules/imagenet_bs2048_coslr.py',
+    '../_base_/default_runtime.py'
+]

configs/resnet/resnet50_32xb64-warmup-lbs_in1k.py

+_base_ = ['./resnet50_32xb64-warmup_in1k.py']
+model = dict(
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(
+            type='LabelSmoothLoss',
+            loss_weight=1.0,
+            label_smooth_val=0.1,
+            num_classes=1000),
+    ))