add part code

configs/deit/deit-small-distilled_4xb256_in1k.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DistilledVisionTransformer',
+        arch='deit-small',
+        img_size=224,
+        patch_size=16),
+    neck=None,
+    head=dict(
+        type='DeiTClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)
+
+# data settings
+train_dataloader = dict(batch_size=256)
+
+# schedule settings
+optim_wrapper = dict(
+    paramwise_cfg=dict(
+        norm_decay_mult=0.0,
+        bias_decay_mult=0.0,
+        custom_keys={
+            '.cls_token': dict(decay_mult=0.0),
+            '.pos_embed': dict(decay_mult=0.0)
+        }),
+    clip_grad=dict(max_norm=5.0),
+)

configs/deit/deit-small_4xb256_in1k.py

+# In small and tiny arch, remove drop path and EMA hook comparing with the
+# original config
+_base_ = [
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VisionTransformer',
+        arch='deit-small',
+        img_size=224,
+        patch_size=16),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)
+
+# data settings
+train_dataloader = dict(batch_size=256)
+
+# schedule settings
+optim_wrapper = dict(
+    paramwise_cfg=dict(
+        norm_decay_mult=0.0,
+        bias_decay_mult=0.0,
+        custom_keys={
+            '.cls_token': dict(decay_mult=0.0),
+            '.pos_embed': dict(decay_mult=0.0)
+        }),
+    clip_grad=dict(max_norm=5.0),
+)

configs/deit/deit-tiny-distilled_4xb256_in1k.py

+# The distillation config is only for evaluation.
+_base_ = [
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DistilledVisionTransformer',
+        arch='deit-tiny',
+        img_size=224,
+        patch_size=16),
+    neck=None,
+    head=dict(
+        type='DeiTClsHead',
+        num_classes=1000,
+        in_channels=192,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)
+
+# data settings
+train_dataloader = dict(batch_size=256)
+
+# schedule settings
+optim_wrapper = dict(
+    paramwise_cfg=dict(
+        norm_decay_mult=0.0,
+        bias_decay_mult=0.0,
+        custom_keys={
+            '.cls_token': dict(decay_mult=0.0),
+            '.pos_embed': dict(decay_mult=0.0)
+        }),
+    clip_grad=dict(max_norm=5.0),
+)

configs/deit/deit-tiny_4xb256_in1k.py

+# In small and tiny arch, remove drop path and EMA hook comparing with the
+# original config
+_base_ = [
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VisionTransformer',
+        arch='deit-tiny',
+        img_size=224,
+        patch_size=16),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=192,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)
+
+# data settings
+train_dataloader = dict(batch_size=256)
+
+# schedule settings
+optim_wrapper = dict(
+    paramwise_cfg=dict(
+        norm_decay_mult=0.0,
+        bias_decay_mult=0.0,
+        custom_keys={
+            '.cls_token': dict(decay_mult=0.0),
+            '.pos_embed': dict(decay_mult=0.0)
+        }),
+    clip_grad=dict(max_norm=5.0),
+)

configs/deit/metafile.yml

+Collections:
+  - Name: DeiT
+    Metadata:
+      Training Data: ImageNet-1k
+      Architecture:
+        - Layer Normalization
+        - Scaled Dot-Product Attention
+        - Attention Dropout
+        - Multi-Head Attention
+    Paper:
+      Title: Training data-efficient image transformers & distillation through attention
+      URL: https://arxiv.org/abs/2012.12877
+    README: configs/deit/README.md
+    Code:
+      URL: v0.19.0
+      Version: https://github.com/open-mmlab/mmpretrain/blob/v0.19.0/mmcls/models/backbones/deit.py
+
+Models:
+  - Name: deit-tiny_4xb256_in1k
+    Metadata:
+      FLOPs: 1258219200
+      Parameters: 5717416
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 74.5
+          Top 5 Accuracy: 92.24
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-tiny_pt-4xb256_in1k_20220218-13b382a0.pth
+    Config: configs/deit/deit-tiny_4xb256_in1k.py
+  - Name: deit-tiny-distilled_3rdparty_in1k
+    Metadata:
+      FLOPs: 1265371776
+      Parameters: 5910800
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 74.51
+          Top 5 Accuracy: 91.9
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-tiny-distilled_3rdparty_pt-4xb256_in1k_20211216-c429839a.pth
+    Config: configs/deit/deit-tiny-distilled_4xb256_in1k.py
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_tiny_distilled_patch16_224-b40b3cf7.pth
+      Code: https://github.com/facebookresearch/deit/blob/f5123946205daf72a88783dae94cabff98c49c55/models.py#L108
+  - Name: deit-small_4xb256_in1k
+    Metadata:
+      FLOPs: 4607954304
+      Parameters: 22050664
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 80.69
+          Top 5 Accuracy: 95.06
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-small_pt-4xb256_in1k_20220218-9425b9bb.pth
+    Config: configs/deit/deit-small_4xb256_in1k.py
+  - Name: deit-small-distilled_3rdparty_in1k
+    Metadata:
+      FLOPs: 4632876288
+      Parameters: 22436432
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.17
+          Top 5 Accuracy: 95.4
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-small-distilled_3rdparty_pt-4xb256_in1k_20211216-4de1d725.pth
+    Config: configs/deit/deit-small-distilled_4xb256_in1k.py
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_small_distilled_patch16_224-649709d9.pth
+      Code: https://github.com/facebookresearch/deit/blob/f5123946205daf72a88783dae94cabff98c49c55/models.py#L123
+  - Name: deit-base_16xb64_in1k
+    Metadata:
+      FLOPs: 17581972224
+      Parameters: 86567656
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.76
+          Top 5 Accuracy: 95.81
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-base_pt-16xb64_in1k_20220216-db63c16c.pth
+    Config: configs/deit/deit-base_16xb64_in1k.py
+  - Name: deit-base_3rdparty_in1k
+    Metadata:
+      FLOPs: 17581972224
+      Parameters: 86567656
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.79
+          Top 5 Accuracy: 95.59
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-base_3rdparty_pt-16xb64_in1k_20211124-6f40c188.pth
+    Config: configs/deit/deit-base_16xb64_in1k.py
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_base_patch16_224-b5f2ef4d.pth
+      Code: https://github.com/facebookresearch/deit/blob/f5123946205daf72a88783dae94cabff98c49c55/models.py#L93
+  - Name: deit-base-distilled_3rdparty_in1k
+    Metadata:
+      FLOPs: 17674283520
+      Parameters: 87338192
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.33
+          Top 5 Accuracy: 96.49
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-base-distilled_3rdparty_pt-16xb64_in1k_20211216-42891296.pth
+    Config: configs/deit/deit-base-distilled_16xb64_in1k.py
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_224-df68dfff.pth
+      Code: https://github.com/facebookresearch/deit/blob/f5123946205daf72a88783dae94cabff98c49c55/models.py#L138
+  - Name: deit-base_224px-pre_3rdparty_in1k-384px
+    Metadata:
+      FLOPs: 55538974464
+      Parameters: 86859496
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.04
+          Top 5 Accuracy: 96.31
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-base_3rdparty_ft-16xb32_in1k-384px_20211124-822d02f2.pth
+    Config: configs/deit/deit-base_16xb32_in1k-384px.py
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_base_patch16_384-8de9b5d1.pth
+      Code: https://github.com/facebookresearch/deit/blob/f5123946205daf72a88783dae94cabff98c49c55/models.py#L153
+  - Name: deit-base-distilled_224px-pre_3rdparty_in1k-384px
+    Metadata:
+      FLOPs: 55645294080
+      Parameters: 87630032
+    In Collection: DeiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.55
+          Top 5 Accuracy: 97.35
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit/deit-base-distilled_3rdparty_ft-16xb32_in1k-384px_20211216-e48d6000.pth
+    Config: configs/deit/deit-base-distilled_16xb32_in1k-384px.py
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_base_distilled_patch16_384-d0272ac0.pth
+      Code: https://github.com/facebookresearch/deit/blob/f5123946205daf72a88783dae94cabff98c49c55/models.py#L168

configs/deit3/README.md

+# DeiT III: Revenge of the ViT
+
+> [DeiT III: Revenge of the ViT](https://arxiv.org/abs/2204.07118)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the input data or of specific tasks. Recent works show that ViTs benefit from self-supervised pre-training, in particular BerT-like pre-training like BeiT. In this paper, we revisit the supervised training of ViTs. Our procedure builds upon and simplifies a recipe introduced for training ResNet-50. It includes a new simple data-augmentation procedure with only 3 augmentations, closer to the practice in self-supervised learning. Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT. It also reveals that the performance of our ViT trained with supervision is comparable to that of more recent architectures. Our results could serve as better baselines for recent self-supervised approaches demonstrated on ViT.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/24734142/192964480-46726469-21d9-4e45-a06a-87c6a57c3367.png" width="90%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('deit3-small-p16_3rdparty_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('deit3-small-p16_3rdparty_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/deit3/deit3-small-p16_64xb64_in1k.py https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k_20221008-0f7c70cf.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                                             |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                     Config                     |                         Download                         |
+| :------------------------------------------------ | :----------: | :--------: | :-------: | :-------: | :-------: | :--------------------------------------------: | :------------------------------------------------------: |
+| `deit3-small-p16_3rdparty_in1k`\*                 | From scratch |   22.06    |   4.61    |   81.35   |   95.31   |    [config](deit3-small-p16_64xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k_20221008-0f7c70cf.pth) |
+| `deit3-small-p16_3rdparty_in1k-384px`\*           | From scratch |   22.21    |   15.52   |   83.43   |   96.68   | [config](deit3-small-p16_64xb64_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k-384px_20221008-a2c1a0c7.pth) |
+| `deit3-small-p16_in21k-pre_3rdparty_in1k`\*       | ImageNet-21k |   22.06    |   4.61    |   83.06   |   96.77   |    [config](deit3-small-p16_64xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_in21k-pre_3rdparty_in1k_20221009-dcd90827.pth) |
+| `deit3-small-p16_in21k-pre_3rdparty_in1k-384px`\* | ImageNet-21k |   22.21    |   15.52   |   84.84   |   97.48   | [config](deit3-small-p16_64xb64_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_in21k-pre_3rdparty_in1k-384px_20221009-de116dd7.pth) |
+| `deit3-medium-p16_3rdparty_in1k`\*                | From scratch |   38.85    |   8.00    |   82.99   |   96.22   |   [config](deit3-medium-p16_64xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-medium-p16_3rdparty_in1k_20221008-3b21284d.pth) |
+| `deit3-medium-p16_in21k-pre_3rdparty_in1k`\*      | ImageNet-21k |   38.85    |   8.00    |   84.56   |   97.19   |   [config](deit3-medium-p16_64xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-medium-p16_in21k-pre_3rdparty_in1k_20221009-472f11e2.pth) |
+| `deit3-base-p16_3rdparty_in1k`\*                  | From scratch |   86.59    |   17.58   |   83.80   |   96.55   |    [config](deit3-base-p16_64xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_3rdparty_in1k_20221008-60b8c8bf.pth) |
+| `deit3-base-p16_3rdparty_in1k-384px`\*            | From scratch |   86.88    |   55.54   |   85.08   |   97.25   | [config](deit3-base-p16_64xb32_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_3rdparty_in1k-384px_20221009-e19e36d4.pth) |
+| `deit3-base-p16_in21k-pre_3rdparty_in1k`\*        | ImageNet-21k |   86.59    |   17.58   |   85.70   |   97.75   |    [config](deit3-base-p16_64xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_in21k-pre_3rdparty_in1k_20221009-87983ca1.pth) |
+| `deit3-base-p16_in21k-pre_3rdparty_in1k-384px`\*  | ImageNet-21k |   86.88    |   55.54   |   86.73   |   98.11   | [config](deit3-base-p16_64xb32_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_in21k-pre_3rdparty_in1k-384px_20221009-5e4e37b9.pth) |
+| `deit3-large-p16_3rdparty_in1k`\*                 | From scratch |   304.37   |   61.60   |   84.87   |   97.01   |    [config](deit3-large-p16_64xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_3rdparty_in1k_20221009-03b427ea.pth) |
+| `deit3-large-p16_3rdparty_in1k-384px`\*           | From scratch |   304.76   |  191.21   |   85.82   |   97.60   | [config](deit3-large-p16_64xb16_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_3rdparty_in1k-384px_20221009-4317ce62.pth) |
+| `deit3-large-p16_in21k-pre_3rdparty_in1k`\*       | ImageNet-21k |   304.37   |   61.60   |   86.97   |   98.24   |    [config](deit3-large-p16_64xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_in21k-pre_3rdparty_in1k_20221009-d8d27084.pth) |
+| `deit3-large-p16_in21k-pre_3rdparty_in1k-384px`\* | ImageNet-21k |   304.76   |  191.21   |   87.73   |   98.51   | [config](deit3-large-p16_64xb16_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_in21k-pre_3rdparty_in1k-384px_20221009-75fea03f.pth) |
+| `deit3-huge-p14_3rdparty_in1k`\*                  | From scratch |   632.13   |  167.40   |   85.21   |   97.36   |    [config](deit3-huge-p14_64xb32_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-huge-p14_3rdparty_in1k_20221009-e107bcb7.pth) |
+| `deit3-huge-p14_in21k-pre_3rdparty_in1k`\*        | ImageNet-21k |   632.13   |  167.40   |   87.19   |   98.26   |    [config](deit3-huge-p14_64xb32_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-huge-p14_in21k-pre_3rdparty_in1k_20221009-19b8a535.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@article{Touvron2022DeiTIR,
+  title={DeiT III: Revenge of the ViT},
+  author={Hugo Touvron and Matthieu Cord and Herve Jegou},
+  journal={arXiv preprint arXiv:2204.07118},
+  year={2022},
+}
+```

configs/deit3/deit3-base-p16_64xb32_in1k-384px.py

+_base_ = [
+    '../_base_/models/deit3/deit3-base-p16-384.py',
+    '../_base_/datasets/imagenet_bs64_deit3_384.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=32)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# 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/deit3/deit3-base-p16_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/deit3/deit3-base-p16-224.py',
+    '../_base_/datasets/imagenet_bs64_deit3_224.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=64)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (64 GPUs) x (64 samples per GPU)
+auto_scale_lr = dict(base_batch_size=4096)

configs/deit3/deit3-huge-p14_64xb32_in1k.py

+_base_ = [
+    '../_base_/models/deit3/deit3-huge-p14-224.py',
+    '../_base_/datasets/imagenet_bs64_deit3_224.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=32)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# 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/deit3/deit3-large-p16_64xb16_in1k-384px.py

+_base_ = [
+    '../_base_/models/deit3/deit3-large-p16-384.py',
+    '../_base_/datasets/imagenet_bs64_deit3_384.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=16)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (64 GPUs) x (16 samples per GPU)
+auto_scale_lr = dict(base_batch_size=1025)

configs/deit3/deit3-large-p16_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/deit3/deit3-large-p16-224.py',
+    '../_base_/datasets/imagenet_bs64_deit3_224.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=64)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (64 GPUs) x (64 samples per GPU)
+auto_scale_lr = dict(base_batch_size=4096)

configs/deit3/deit3-medium-p16_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/deit3/deit3-medium-p16-224.py',
+    '../_base_/datasets/imagenet_bs64_deit3_224.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=64)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (64 GPUs) x (64 samples per GPU)
+auto_scale_lr = dict(base_batch_size=4096)

configs/deit3/deit3-small-p16_64xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/deit3/deit3-small-p16-384.py',
+    '../_base_/datasets/imagenet_bs64_deit3_384.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=64)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (64 GPUs) x (64 samples per GPU)
+auto_scale_lr = dict(base_batch_size=4096)

configs/deit3/deit3-small-p16_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/deit3/deit3-small-p16-224.py',
+    '../_base_/datasets/imagenet_bs64_deit3_224.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# dataset setting
+train_dataloader = dict(batch_size=64)
+
+# schedule settings
+optim_wrapper = dict(optimizer=dict(lr=1e-5, weight_decay=0.1))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (64 GPUs) x (64 samples per GPU)
+auto_scale_lr = dict(base_batch_size=4096)

configs/deit3/metafile.yml

+Collections:
+  - Name: DeiT3
+    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/abs/2204.07118
+      Title: 'DeiT III: Revenge of the ViT'
+    README: configs/deit3/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v1.0.0rc2/mmcls/models/backbones/deit3.py
+      Version: v1.0.0rc2
+
+Models:
+  - Name: deit3-small-p16_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 4607954304
+      Parameters: 22059496
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 81.35
+        Top 5 Accuracy: 95.31
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k_20221008-0f7c70cf.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_small_224_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-small-p16_64xb64_in1k.py
+  - Name: deit3-small-p16_3rdparty_in1k-384px
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 15517663104
+      Parameters: 22205416
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 83.43
+        Top 5 Accuracy: 96.68
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k-384px_20221008-a2c1a0c7.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_small_384_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-small-p16_64xb64_in1k-384px.py
+  - Name: deit3-small-p16_in21k-pre_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 4607954304
+      Parameters: 22059496
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 83.06
+        Top 5 Accuracy: 96.77
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_in21k-pre_3rdparty_in1k_20221009-dcd90827.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_small_224_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-small-p16_64xb64_in1k.py
+  - Name: deit3-small-p16_in21k-pre_3rdparty_in1k-384px
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 15517663104
+      Parameters: 22205416
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 84.84
+        Top 5 Accuracy: 97.48
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_in21k-pre_3rdparty_in1k-384px_20221009-de116dd7.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_small_384_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-small-p16_64xb64_in1k-384px.py
+  - Name: deit3-medium-p16_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 8003064320
+      Parameters: 38849512
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 82.99
+        Top 5 Accuracy: 96.22
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-medium-p16_3rdparty_in1k_20221008-3b21284d.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_medium_224_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-medium-p16_64xb64_in1k.py
+  - Name: deit3-medium-p16_in21k-pre_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 8003064320
+      Parameters: 38849512
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 84.56
+        Top 5 Accuracy: 97.19
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-medium-p16_in21k-pre_3rdparty_in1k_20221009-472f11e2.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_medium_224_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-medium-p16_64xb64_in1k.py
+  - Name: deit3-base-p16_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 17581972224
+      Parameters: 86585320
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 83.80
+        Top 5 Accuracy: 96.55
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_3rdparty_in1k_20221008-60b8c8bf.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_base_224_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-base-p16_64xb64_in1k.py
+  - Name: deit3-base-p16_3rdparty_in1k-384px
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 55538974464
+      Parameters: 86877160
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 85.08
+        Top 5 Accuracy: 97.25
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_3rdparty_in1k-384px_20221009-e19e36d4.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_base_384_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-base-p16_64xb32_in1k-384px.py
+  - Name: deit3-base-p16_in21k-pre_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 17581972224
+      Parameters: 86585320
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 85.70
+        Top 5 Accuracy: 97.75
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_in21k-pre_3rdparty_in1k_20221009-87983ca1.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_base_224_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-base-p16_64xb64_in1k.py
+  - Name: deit3-base-p16_in21k-pre_3rdparty_in1k-384px
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 55538974464
+      Parameters: 86877160
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 86.73
+        Top 5 Accuracy: 98.11
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_in21k-pre_3rdparty_in1k-384px_20221009-5e4e37b9.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_base_384_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-base-p16_64xb32_in1k-384px.py
+  - Name: deit3-large-p16_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 61603111936
+      Parameters: 304374760
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 84.87
+        Top 5 Accuracy: 97.01
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_3rdparty_in1k_20221009-03b427ea.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_large_224_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-large-p16_64xb64_in1k.py
+  - Name: deit3-large-p16_3rdparty_in1k-384px
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 191210034176
+      Parameters: 304763880
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 85.82
+        Top 5 Accuracy: 97.60
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_3rdparty_in1k-384px_20221009-4317ce62.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_large_384_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-large-p16_64xb16_in1k-384px.py
+  - Name: deit3-large-p16_in21k-pre_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 61603111936
+      Parameters: 304374760
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 86.97
+        Top 5 Accuracy: 98.24
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_in21k-pre_3rdparty_in1k_20221009-d8d27084.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_large_224_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-large-p16_64xb64_in1k.py
+  - Name: deit3-large-p16_in21k-pre_3rdparty_in1k-384px
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 191210034176
+      Parameters: 304763880
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 87.73
+        Top 5 Accuracy: 98.51
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_in21k-pre_3rdparty_in1k-384px_20221009-75fea03f.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_large_384_21k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-large-p16_64xb16_in1k-384px.py
+  - Name: deit3-huge-p14_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 167400741120
+      Parameters: 632126440
+      Training Data:
+        - ImageNet-1k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 85.21
+        Top 5 Accuracy: 97.36
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-huge-p14_3rdparty_in1k_20221009-e107bcb7.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_huge_224_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-huge-p14_64xb32_in1k.py
+  - Name: deit3-huge-p14_in21k-pre_3rdparty_in1k
+    In Collection: DeiT3
+    Metadata:
+      FLOPs: 167400741120
+      Parameters: 632126440
+      Training Data:
+        - ImageNet-21k
+    Results:
+    - Dataset: ImageNet-1k
+      Task: Image Classification
+      Metrics:
+        Top 1 Accuracy: 87.19
+        Top 5 Accuracy: 98.26
+    Weights: https://download.openmmlab.com/mmclassification/v0/deit3/deit3-huge-p14_in21k-pre_3rdparty_in1k_20221009-19b8a535.pth
+    Converted From:
+      Weights: https://dl.fbaipublicfiles.com/deit/deit_3_huge_224_1k.pth
+      Code: https://github.com/facebookresearch/deit/blob/main/models_v2.py#L171
+    Config: configs/deit3/deit3-huge-p14_64xb32_in1k.py

configs/densecl/README.md

+# DenseCL
+
+> [Dense contrastive learning for self-supervised visual pre-training](https://arxiv.org/abs/2011.09157)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning (DenseCL), which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/36138628/149721111-bab03a6d-a30d-418e-b338-43c3689cfc65.png" width="900" />
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('resnet50_densecl-pre_8xb32-linear-steplr-100e_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('densecl_resnet50_8xb32-coslr-200e_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))
+```
+
+**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/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/densecl/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Pretrained models
+
+| Model                                    | Params (M) | Flops (G) |                       Config                        |                                          Download                                          |
+| :--------------------------------------- | :--------: | :-------: | :-------------------------------------------------: | :----------------------------------------------------------------------------------------: |
+| `densecl_resnet50_8xb32-coslr-200e_in1k` |   64.85    |   4.11    | [config](densecl_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.json) |
+
+### Image Classification on ImageNet-1k
+
+| Model                                     |                   Pretrain                   | Params (M) | Flops (G) | Top-1 (%) |                   Config                   |                   Download                    |
+| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
+| `resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k` | [DENSECL](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth) |   25.56    |   4.11    |   63.50   | [config](benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.json) |
+
+## Citation
+
+```bibtex
+@inproceedings{wang2021dense,
+  title={Dense contrastive learning for self-supervised visual pre-training},
+  author={Wang, Xinlong and Zhang, Rufeng and Shen, Chunhua and Kong, Tao and Li, Lei},
+  booktitle={CVPR},
+  year={2021}
+}
+```

configs/densecl/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py

+_base_ = [
+    '../../_base_/models/resnet50.py',
+    '../../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../../_base_/schedules/imagenet_sgd_steplr_100e.py',
+    '../../_base_/default_runtime.py',
+]
+
+model = dict(
+    backbone=dict(
+        frozen_stages=4,
+        init_cfg=dict(type='Pretrained', checkpoint='', prefix='backbone.')))
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=30., momentum=0.9, weight_decay=0.))
+
+# runtime settings
+default_hooks = dict(
+    checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))

configs/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs32_mocov2.py',
+    '../_base_/schedules/imagenet_sgd_coslr_200e.py',
+    '../_base_/default_runtime.py',
+]
+
+# model settings
+model = dict(
+    type='DenseCL',
+    queue_len=65536,
+    feat_dim=128,
+    momentum=0.001,
+    loss_lambda=0.5,
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        norm_cfg=dict(type='BN'),
+        zero_init_residual=False),
+    neck=dict(
+        type='DenseCLNeck',
+        in_channels=2048,
+        hid_channels=2048,
+        out_channels=128,
+        num_grid=None),
+    head=dict(
+        type='ContrastiveHead',
+        loss=dict(type='CrossEntropyLoss'),
+        temperature=0.2),
+)
+find_unused_parameters = True
+
+# runtime settings
+default_hooks = dict(
+    # only keeps the latest 3 checkpoints
+    checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/densecl/metafile.yml

+Collections:
+  - Name: DenseCL
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Architecture:
+        - ResNet
+    Paper:
+      Title: Dense contrastive learning for self-supervised visual pre-training
+      URL: https://arxiv.org/abs/2011.09157
+    README: configs/densecl/README.md
+
+Models:
+  - Name: densecl_resnet50_8xb32-coslr-200e_in1k
+    Metadata:
+      Epochs: 200
+      Batch Size: 256
+      FLOPs: 4109364224
+      Parameters: 64850560
+      Training Data: ImageNet-1k
+    In Collection: DenseCL
+    Results: null
+    Weights: https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth
+    Config: configs/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py
+    Downstream:
+      - resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k
+  - Name: resnet50_densecl-pre_8xb32-linear-steplr-100e_in1k
+    Metadata:
+      Epochs: 100
+      Batch Size: 256
+      FLOPs: 4109464576
+      Parameters: 25557032
+      Training Data: ImageNet-1k
+    In Collection: DenseCL
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 63.5
+    Weights: https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth
+    Config: configs/densecl/benchmarks/resnet50_8xb32-linear-steplr-100e_in1k.py

configs/densenet/README.md

+# DenseNet
+
+> [Densely Connected Convolutional Networks](https://arxiv.org/abs/1608.06993)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less computation to achieve high performance.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/42952108/162675098-9a670883-b13a-4a5a-a9c9-06c39c616a0a.png" width="100%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('densenet121_3rdparty_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('densenet121_3rdparty_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/densenet/densenet121_4xb256_in1k.py https://download.openmmlab.com/mmclassification/v0/densenet/densenet121_4xb256_in1k_20220426-07450f99.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                         |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                Config                |                                        Download                                        |
+| :---------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :----------------------------------: | :------------------------------------------------------------------------------------: |
+| `densenet121_3rdparty_in1k`\* | From scratch |    7.98    |   2.88    |   74.96   |   92.21   | [config](densenet121_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet121_4xb256_in1k_20220426-07450f99.pth) |
+| `densenet169_3rdparty_in1k`\* | From scratch |   14.15    |   3.42    |   76.08   |   93.11   | [config](densenet169_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet169_4xb256_in1k_20220426-a2889902.pth) |
+| `densenet201_3rdparty_in1k`\* | From scratch |   20.01    |   4.37    |   77.32   |   93.64   | [config](densenet201_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet201_4xb256_in1k_20220426-05cae4ef.pth) |
+| `densenet161_3rdparty_in1k`\* | From scratch |   28.68    |   7.82    |   77.61   |   93.83   | [config](densenet161_4xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/densenet/densenet161_4xb256_in1k_20220426-ee6a80a9.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@misc{https://doi.org/10.48550/arxiv.1608.06993,
+      doi = {10.48550/ARXIV.1608.06993},
+      url = {https://arxiv.org/abs/1608.06993},
+      author = {Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q.},
+      keywords = {Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
+      title = {Densely Connected Convolutional Networks},
+      publisher = {arXiv},
+      year = {2016},
+      copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```