upload mmpretrain

configs/spark/spark_sparse-resnet50_8xb512-amp-coslr-1600e_in1k.py

+_base_ = 'spark_sparse-resnet50_8xb512-amp-coslr-800e_in1k.py'
+
+# learning rate scheduler
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1e-4,
+        by_epoch=True,
+        begin=0,
+        end=40,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=1560,
+        by_epoch=True,
+        begin=40,
+        end=1600,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingWeightDecay',
+        eta_min=0.2,
+        T_max=1600,
+        by_epoch=True,
+        begin=0,
+        end=1600,
+        convert_to_iter_based=True)
+]
+
+# runtime settings
+train_cfg = dict(max_epochs=1600)

configs/spark/spark_sparse-resnet50_8xb512-amp-coslr-800e_in1k.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs512_mae.py',
+    '../_base_/default_runtime.py',
+]
+
+# dataset 8 x 512
+train_dataloader = dict(batch_size=512, num_workers=8)
+
+# model settings
+model = dict(
+    type='SparK',
+    input_size=224,
+    downsample_raito=32,
+    mask_ratio=0.6,
+    enc_dec_norm_cfg=dict(type='SparseSyncBatchNorm2d'),
+    enc_dec_norm_dim=2048,
+    backbone=dict(
+        type='SparseResNet',
+        depth=50,
+        out_indices=(0, 1, 2, 3),
+        drop_path_rate=0.05),
+    neck=dict(
+        type='SparKLightDecoder',
+        feature_dim=512,
+        upsample_ratio=32,  # equal to downsample_raito
+        mid_channels=0,
+        last_act=False),
+    head=dict(
+        type='SparKPretrainHead',
+        loss=dict(type='PixelReconstructionLoss', criterion='L2')))
+
+# optimizer wrapper
+optimizer = dict(
+    type='Lamb', lr=2e-4 * 4096 / 512, betas=(0.9, 0.95), weight_decay=0.04)
+optim_wrapper = dict(
+    type='AmpOptimWrapper',
+    optimizer=optimizer,
+    clip_grad=dict(max_norm=5.0),
+    paramwise_cfg=dict(
+        bias_decay_mult=0.0,
+        flat_decay_mult=0.0,
+        custom_keys={
+            'mask_token': dict(decay_mult=0.),
+        }))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1e-4,
+        by_epoch=True,
+        begin=0,
+        end=40,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=760,
+        by_epoch=True,
+        begin=40,
+        end=800,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingWeightDecay',
+        eta_min=0.2,
+        T_max=800,
+        by_epoch=True,
+        begin=0,
+        end=800,
+        convert_to_iter_based=True)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=800)
+default_hooks = dict(
+    logger=dict(type='LoggerHook', interval=100),
+    # only keeps the latest 3 checkpoints
+    checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=2))
+
+# randomness
+randomness = dict(seed=0, diff_rank_seed=True)

configs/swav/README.md

+# SwAV
+
+> [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://arxiv.org/abs/2006.09882)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or “views”) of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a “swapped” prediction mechanism where we predict the code of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements.
+
+<div align=center>
+<img  src="https://user-images.githubusercontent.com/36138628/149724517-9f1e7bdf-04c7-43e3-92f4-2b8fc1399123.png" width="500" />
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('resnet50_swav-pre_8xb32-linear-coslr-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('swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px', 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/swav/swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/swav/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Pretrained models
+
+| Model                                                  | Params (M) | Flops (G) |                             Config                             |                             Download                              |
+| :----------------------------------------------------- | :--------: | :-------: | :------------------------------------------------------------: | :---------------------------------------------------------------: |
+| `swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px` |   28.35    |   4.11    | [config](swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.json) |
+
+### Image Classification on ImageNet-1k
+
+| Model                                     |                   Pretrain                   | Params (M) | Flops (G) | Top-1 (%) |                   Config                   |                   Download                    |
+| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
+| `resnet50_swav-pre_8xb32-linear-coslr-100e_in1k` | [SWAV](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth) |   25.56    |   4.11    |   70.50   | [config](benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.json) |
+
+## Citation
+
+```bibtex
+@article{caron2020unsupervised,
+  title={Unsupervised Learning of Visual Features by Contrasting Cluster Assignments},
+  author={Caron, Mathilde and Misra, Ishan and Mairal, Julien and Goyal, Priya and Bojanowski, Piotr and Joulin, Armand},
+  booktitle={NeurIPS},
+  year={2020}
+}
+```

configs/swav/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py

+_base_ = [
+    '../../_base_/models/resnet50.py',
+    '../../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../../_base_/schedules/imagenet_lars_coslr_90e.py',
+    '../../_base_/default_runtime.py',
+]
+
+model = dict(
+    backbone=dict(
+        frozen_stages=4,
+        init_cfg=dict(type='Pretrained', checkpoint='', prefix='backbone.')))
+
+# dataset summary
+train_dataloader = dict(batch_size=512)
+
+# runtime settings
+default_hooks = dict(
+    checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))

configs/swav/metafile.yml

+Collections:
+  - Name: SwAV
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - LARS
+      Training Resources: 8x V100 GPUs
+      Architecture:
+        - ResNet
+        - SwAV
+    Paper:
+      Title: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
+      URL: https://arxiv.org/abs/2006.09882
+    README: configs/swav/README.md
+
+Models:
+  - Name: swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px
+    Metadata:
+      Epochs: 200
+      Batch Size: 256
+      FLOPs: 4109364224
+      Parameters: 28354752
+      Training Data: ImageNet-1k
+    In Collection: SwAV
+    Results: null
+    Weights: https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth
+    Config: configs/swav/swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py
+    Downstream:
+      - resnet50_swav-pre_8xb32-linear-coslr-100e_in1k
+  - Name: resnet50_swav-pre_8xb32-linear-coslr-100e_in1k
+    Metadata:
+      Epochs: 100
+      Batch Size: 256
+      FLOPs: 4109464576
+      Parameters: 25557032
+      Training Data: ImageNet-1k
+    In Collection: SwAV
+    Results:
+      - Task: Image Classification
+        Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 70.5
+    Weights: https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth
+    Config: configs/swav/benchmarks/resnet50_8xb512-linear-coslr-90e_in1k.py

configs/swav/swav_resnet50_8xb32-mcrop-coslr-200e_in1k-224px-96px.py

+_base_ = [
+    '../_base_/schedules/imagenet_lars_coslr_200e.py',
+    '../_base_/default_runtime.py',
+]
+
+# dataset settings
+dataset_type = 'ImageNet'
+data_root = 'data/imagenet/'
+data_preprocessor = dict(
+    type='SelfSupDataPreprocessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    to_rgb=True)
+
+num_crops = [2, 6]
+color_distort_strength = 1.0
+view_pipeline1 = [
+    dict(
+        type='RandomResizedCrop',
+        scale=224,
+        crop_ratio_range=(0.14, 1.),
+        backend='pillow'),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.8 * color_distort_strength,
+                contrast=0.8 * color_distort_strength,
+                saturation=0.8 * color_distort_strength,
+                hue=0.2 * color_distort_strength)
+        ],
+        prob=0.8),
+    dict(
+        type='RandomGrayscale',
+        prob=0.2,
+        keep_channels=True,
+        channel_weights=(0.114, 0.587, 0.2989)),
+    dict(
+        type='GaussianBlur',
+        magnitude_range=(0.1, 2.0),
+        magnitude_std='inf',
+        prob=0.5),
+    dict(type='RandomFlip', prob=0.5),
+]
+view_pipeline2 = [
+    dict(
+        type='RandomResizedCrop',
+        scale=96,
+        crop_ratio_range=(0.05, 0.14),
+        backend='pillow'),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.8 * color_distort_strength,
+                contrast=0.8 * color_distort_strength,
+                saturation=0.8 * color_distort_strength,
+                hue=0.2 * color_distort_strength)
+        ],
+        prob=0.8),
+    dict(
+        type='RandomGrayscale',
+        prob=0.2,
+        keep_channels=True,
+        channel_weights=(0.114, 0.587, 0.2989)),
+    dict(
+        type='GaussianBlur',
+        magnitude_range=(0.1, 2.0),
+        magnitude_std='inf',
+        prob=0.5),
+    dict(type='RandomFlip', prob=0.5),
+]
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiView',
+        num_views=num_crops,
+        transforms=[view_pipeline1, view_pipeline2]),
+    dict(type='PackInputs')
+]
+
+batch_size = 32
+train_dataloader = dict(
+    batch_size=batch_size,
+    num_workers=8,
+    drop_last=True,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    collate_fn=dict(type='default_collate'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))
+
+# model settings
+model = dict(
+    type='SwAV',
+    data_preprocessor=dict(
+        mean=(123.675, 116.28, 103.53),
+        std=(58.395, 57.12, 57.375),
+        to_rgb=True),
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        norm_cfg=dict(type='SyncBN'),
+        zero_init_residual=True),
+    neck=dict(
+        type='SwAVNeck',
+        in_channels=2048,
+        hid_channels=2048,
+        out_channels=128,
+        with_avg_pool=True),
+    head=dict(
+        type='SwAVHead',
+        loss=dict(
+            type='SwAVLoss',
+            feat_dim=128,  # equal to neck['out_channels']
+            epsilon=0.05,
+            temperature=0.1,
+            num_crops=num_crops,
+        )))
+
+# optimizer
+optim_wrapper = dict(type='OptimWrapper', optimizer=dict(type='LARS', lr=0.6))
+find_unused_parameters = True
+
+# learning policy
+param_scheduler = [
+    dict(
+        type='CosineAnnealingLR',
+        T_max=200,
+        eta_min=6e-4,
+        by_epoch=True,
+        begin=0,
+        end=200,
+        convert_to_iter_based=True)
+]
+
+# runtime settings
+default_hooks = dict(
+    # only keeps the latest 3 checkpoints
+    checkpoint=dict(type='CheckpointHook', interval=10, max_keep_ckpts=3))
+
+# additional hooks
+custom_hooks = [
+    dict(
+        type='SwAVHook',
+        priority='VERY_HIGH',
+        batch_size=batch_size,
+        epoch_queue_starts=15,
+        crops_for_assign=[0, 1],
+        feat_dim=128,
+        queue_length=3840,
+        frozen_layers_cfg=dict(prototypes=5005))
+]

configs/swin_transformer/README.md

+# Swin-Transformer
+
+> [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
+
+<!-- [ALGORITHM] -->
+
+## Introduction
+
+**Swin Transformer** (the name **Swin** stands for Shifted window) is initially described in [the paper](https://arxiv.org/pdf/2103.14030.pdf), which capably serves as a general-purpose backbone for computer vision. It is basically a hierarchical Transformer whose representation is computed with shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection.
+
+Swin Transformer achieves strong performance on COCO object detection (58.7 box AP and 51.1 mask AP on test-dev) and ADE20K semantic segmentation (53.5 mIoU on val), surpassing previous models by a large margin.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/142576715-14668c6b-5cb8-4de8-ac51-419fae773c90.png" width="90%"/>
+</div>
+
+## Abstract
+
+<details>
+
+<summary>Show the paper's abstract</summary>
+
+<br>
+This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text. To address these differences, we propose a hierarchical Transformer whose representation is computed with **Shifted windows**. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and +2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones. The hierarchical design and the shifted window approach also prove beneficial for all-MLP architectures.
+</br>
+
+</details>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('swin-tiny_16xb64_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('swin-tiny_16xb64_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/swin_transformer/swin-tiny_16xb64_in1k.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/swin_transformer/swin-tiny_16xb64_in1k.py https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                                      |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                  Config                   |                               Download                               |
+| :----------------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :---------------------------------------: | :------------------------------------------------------------------: |
+| `swin-tiny_16xb64_in1k`                    | From scratch |   28.29    |   4.36    |   81.18   |   95.61   |    [config](swin-tiny_16xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925.json) |
+| `swin-small_16xb64_in1k`                   | From scratch |   49.61    |   8.52    |   83.02   |   96.29   |    [config](swin-small_16xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219-7f9d988b.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219.json) |
+| `swin-base_16xb64_in1k`                    | From scratch |   87.77    |   15.14   |   83.36   |   96.44   |    [config](swin-base_16xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742-93230b0d.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742.json) |
+| `swin-tiny_3rdparty_in1k`\*                | From scratch |   28.29    |   4.36    |   81.18   |   95.52   |    [config](swin-tiny_16xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_tiny_patch4_window7_224-160bb0a5.pth) |
+| `swin-small_3rdparty_in1k`\*               | From scratch |   49.61    |   8.52    |   83.21   |   96.25   |    [config](swin-small_16xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_small_patch4_window7_224-cc7a01c9.pth) |
+| `swin-base_3rdparty_in1k`\*                | From scratch |   87.77    |   15.14   |   83.42   |   96.44   |    [config](swin-base_16xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window7_224-4670dd19.pth) |
+| `swin-base_3rdparty_in1k-384`\*            | From scratch |   87.90    |   44.49   |   84.49   |   96.95   | [config](swin-base_16xb64_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384-02c598a4.pth) |
+| `swin-base_in21k-pre-3rdparty_in1k`\*      | From scratch |   87.77    |   15.14   |   85.16   |   97.50   |    [config](swin-base_16xb64_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window7_224_22kto1k-f967f799.pth) |
+| `swin-base_in21k-pre-3rdparty_in1k-384`\*  | From scratch |   87.90    |   44.49   |   86.44   |   98.05   | [config](swin-base_16xb64_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384_22kto1k-d59b0d1d.pth) |
+| `swin-large_in21k-pre-3rdparty_in1k`\*     | From scratch |   196.53   |   34.04   |   86.24   |   97.88   |    [config](swin-large_16xb64_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window7_224_22kto1k-5f0996db.pth) |
+| `swin-large_in21k-pre-3rdparty_in1k-384`\* | From scratch |   196.74   |  100.04   |   87.25   |   98.25   | [config](swin-large_16xb64_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window12_384_22kto1k-0a40944b.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+### Image Classification on CUB-200-2011
+
+| Model                       |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) |                 Config                 |                                            Download                                             |
+| :-------------------------- | :----------: | :--------: | :-------: | :-------: | :------------------------------------: | :---------------------------------------------------------------------------------------------: |
+| `swin-large_8xb8_cub-384px` | From scratch |   195.51   |  100.04   |   91.87   | [config](swin-large_8xb8_cub-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin-large_8xb8_cub_384px_20220307-1bbaee6a.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin-large_8xb8_cub_384px_20220307-1bbaee6a.json) |
+
+## Citation
+
+```bibtex
+@article{liu2021Swin,
+  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
+  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
+  journal={arXiv preprint arXiv:2103.14030},
+  year={2021}
+}
+```

configs/swin_transformer/metafile.yml

+Collections:
+  - Name: Swin-Transformer
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - AdamW
+        - Weight Decay
+      Training Resources: 16x V100 GPUs
+      Epochs: 300
+      Batch Size: 1024
+      Architecture:
+        - Shift Window Multihead Self Attention
+    Paper:
+      URL: https://arxiv.org/abs/2103.14030
+      Title: "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows"
+    README: configs/swin_transformer/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.15.0/mmcls/models/backbones/swin_transformer.py#L176
+      Version: v0.15.0
+
+Models:
+  - Name: swin-tiny_16xb64_in1k
+    Metadata:
+      FLOPs: 4360000000
+      Parameters: 28290000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.18
+          Top 5 Accuracy: 95.61
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth
+    Config: configs/swin_transformer/swin-tiny_16xb64_in1k.py
+  - Name: swin-small_16xb64_in1k
+    Metadata:
+      FLOPs: 8520000000
+      Parameters: 49610000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.02
+          Top 5 Accuracy: 96.29
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219-7f9d988b.pth
+    Config: configs/swin_transformer/swin-small_16xb64_in1k.py
+  - Name: swin-base_16xb64_in1k
+    Metadata:
+      FLOPs: 15140000000
+      Parameters: 87770000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.36
+          Top 5 Accuracy: 96.44
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742-93230b0d.pth
+    Config: configs/swin_transformer/swin-base_16xb64_in1k.py
+  - Name: swin-tiny_3rdparty_in1k
+    Metadata:
+      FLOPs: 4360000000
+      Parameters: 28290000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.18
+          Top 5 Accuracy: 95.52
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_tiny_patch4_window7_224-160bb0a5.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_tiny_patch4_window7_224.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-tiny_16xb64_in1k.py
+  - Name: swin-small_3rdparty_in1k
+    Metadata:
+      FLOPs: 8520000000
+      Parameters: 49610000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.21
+          Top 5 Accuracy: 96.25
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_small_patch4_window7_224-cc7a01c9.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_small_patch4_window7_224.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-small_16xb64_in1k.py
+  - Name: swin-base_3rdparty_in1k
+    Metadata:
+      FLOPs: 15140000000
+      Parameters: 87770000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.42
+          Top 5 Accuracy: 96.44
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window7_224-4670dd19.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-base_16xb64_in1k.py
+  - Name: swin-base_3rdparty_in1k-384
+    Metadata:
+      FLOPs: 44490000000
+      Parameters: 87900000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.49
+          Top 5 Accuracy: 96.95
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384-02c598a4.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-base_16xb64_in1k-384px.py
+  - Name: swin-base_in21k-pre-3rdparty_in1k
+    Metadata:
+      FLOPs: 15140000000
+      Parameters: 87770000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.16
+          Top 5 Accuracy: 97.50
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window7_224_22kto1k-f967f799.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window7_224_22kto1k.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-base_16xb64_in1k.py
+  - Name: swin-base_in21k-pre-3rdparty_in1k-384
+    Metadata:
+      FLOPs: 44490000000
+      Parameters: 87900000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 86.44
+          Top 5 Accuracy: 98.05
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384_22kto1k-d59b0d1d.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_base_patch4_window12_384_22kto1k.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-base_16xb64_in1k-384px.py
+  - Name: swin-large_in21k-pre-3rdparty_in1k
+    Metadata:
+      FLOPs: 34040000000
+      Parameters: 196530000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 86.24
+          Top 5 Accuracy: 97.88
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window7_224_22kto1k-5f0996db.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window7_224_22kto1k.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-large_16xb64_in1k.py
+  - Name: swin-large_in21k-pre-3rdparty_in1k-384
+    Metadata:
+      FLOPs: 100040000000
+      Parameters: 196740000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 87.25
+          Top 5 Accuracy: 98.25
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window12_384_22kto1k-0a40944b.pth
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v1.0.0/swin_large_patch4_window12_384_22kto1k.pth
+      Code: https://github.com/microsoft/Swin-Transformer/blob/777f6c66604bb5579086c4447efe3620344d95a9/models/swin_transformer.py#L458
+    Config: configs/swin_transformer/swin-large_16xb64_in1k-384px.py
+  - Name: swin-large_8xb8_cub-384px
+    Metadata:
+      FLOPs: 100040000000
+      Parameters: 195510000
+    In Collection: Swin-Transformer
+    Results:
+      - Dataset: CUB-200-2011
+        Metrics:
+          Top 1 Accuracy: 91.87
+        Task: Image Classification
+    Pretrain: https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-large_3rdparty_in21k-384px.pth
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin-large_8xb8_cub_384px_20220307-1bbaee6a.pth
+    Config: configs/swin_transformer/swin-large_8xb8_cub-384px.py

configs/swin_transformer/swin-base_16xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/swin_transformer/base_384.py',
+    '../_base_/datasets/imagenet_bs64_swin_384.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(clip_grad=dict(max_norm=5.0))

configs/swin_transformer/swin-base_16xb64_in1k.py

+_base_ = [
+    '../_base_/models/swin_transformer/base_224.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(clip_grad=dict(max_norm=5.0))

configs/swin_transformer/swin-large_16xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/swin_transformer/large_384.py',
+    '../_base_/datasets/imagenet_bs64_swin_384.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(clip_grad=dict(max_norm=5.0))

configs/swin_transformer/swin-large_16xb64_in1k.py

+_base_ = [
+    '../_base_/models/swin_transformer/large_224.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(clip_grad=dict(max_norm=5.0))

configs/swin_transformer/swin-large_8xb8_cub-384px.py

+_base_ = [
+    '../_base_/models/swin_transformer/large_384.py',
+    '../_base_/datasets/cub_bs8_384.py',
+    '../_base_/schedules/cub_bs64.py',
+    '../_base_/default_runtime.py',
+]
+
+# model settings
+checkpoint = 'https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin-large_3rdparty_in21k-384px.pth'  # noqa
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        init_cfg=dict(
+            type='Pretrained', checkpoint=checkpoint, prefix='backbone')),
+    head=dict(num_classes=200, ))
+
+# schedule settings
+optim_wrapper = dict(
+    optimizer=dict(
+        _delete_=True,
+        type='AdamW',
+        lr=5e-6,
+        weight_decay=0.0005,
+        eps=1e-8,
+        betas=(0.9, 0.999)),
+    paramwise_cfg=dict(
+        norm_decay_mult=0.0,
+        bias_decay_mult=0.0,
+        custom_keys={
+            '.absolute_pos_embed': dict(decay_mult=0.0),
+            '.relative_position_bias_table': dict(decay_mult=0.0)
+        }),
+    clip_grad=dict(max_norm=5.0),
+)
+
+default_hooks = dict(
+    # log every 20 intervals
+    logger=dict(type='LoggerHook', interval=20),
+    # save last three checkpoints
+    checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))

configs/swin_transformer/swin-small_16xb64_in1k.py

+_base_ = [
+    '../_base_/models/swin_transformer/small_224.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(clip_grad=dict(max_norm=5.0))

configs/swin_transformer/swin-tiny_16xb64_in1k.py

+_base_ = [
+    '../_base_/models/swin_transformer/tiny_224.py',
+    '../_base_/datasets/imagenet_bs64_swin_224.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+# schedule settings
+optim_wrapper = dict(clip_grad=dict(max_norm=5.0))

configs/swin_transformer_v2/README.md

+# Swin-Transformer V2
+
+> [Swin Transformer V2: Scaling Up Capacity and Resolution](https://arxiv.org/abs/2111.09883)
+
+<!-- [ALGORITHM] -->
+
+## Introduction
+
+**Swin Transformer V2** is a work on the scale up visual model based on [Swin Transformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer). In the visual field, We can not increase the performance by just simply scaling up the visual model like NLP models. The possible reasons mentioned in the article are:
+
+- Training instability when increasing the vision model
+- Migrating the model trained at low resolution to a larger scale resolution task
+- Too mush GPU memory
+
+To solve it, The following method improvements are proposed in the paper:
+
+- post normalization: layer normalization after self-attention layer and MLP block
+- scaled cosine attention approach: use cosine similarity to calculate the relationship between token pairs
+- log-spaced continuous position bias: redefine relative position encoding
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/42952108/180748696-ee7ed23d-7fee-4ccf-9eb5-f117db228a42.png" width="100%"/>
+</div>
+
+## Abstract
+
+<details>
+
+<summary>Show the detailed Abstract</summary>
+
+<br>
+
+Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images. Through these techniques, this paper successfully trained a 3 billion-parameter Swin Transformer V2 model, which is the largest dense vision model to date, and makes it capable of training with images of up to 1,536×1,536 resolution. It set new performance records on 4 representative vision tasks, including ImageNet-V2 image classification, COCO object detection, ADE20K semantic segmentation, and Kinetics-400 video action classification. Also note our training is much more efficient than that in Google's billion-level visual models, which consumes 40 times less labelled data and 40 times less training time.
+
+</br>
+
+</details>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('swinv2-tiny-w8_3rdparty_in1k-256px', '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('swinv2-tiny-w8_3rdparty_in1k-256px', 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/swin_transformer_v2/swinv2-tiny-w8_16xb64_in1k-256px.py https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w8_3rdparty_in1k-256px_20220803-e318968f.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Pretrained models
+
+| Model                                     | Params (M) | Flops (G) |                      Config                      |                                           Download                                           |
+| :---------------------------------------- | :--------: | :-------: | :----------------------------------------------: | :------------------------------------------------------------------------------------------: |
+| `swinv2-base-w12_3rdparty_in21k-192px`\*  |   87.92    |   8.51    | [config](swinv2-base-w12_8xb128_in21k-192px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-base-w12_3rdparty_in21k-192px_20220803-f7dc9763.pth) |
+| `swinv2-large-w12_3rdparty_in21k-192px`\* |   196.74   |   19.04   | [config](swinv2-large-w12_8xb128_in21k-192px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-large-w12_3rdparty_in21k-192px_20220803-d9073fee.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/microsoft/Swin-Transformer). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+### Image Classification on ImageNet-1k
+
+| Model                                             |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                       Config                       |                       Download                       |
+| :------------------------------------------------ | :----------: | :--------: | :-------: | :-------: | :-------: | :------------------------------------------------: | :--------------------------------------------------: |
+| `swinv2-tiny-w8_3rdparty_in1k-256px`\*            | From scratch |   28.35    |   4.35    |   81.76   |   95.87   |   [config](swinv2-tiny-w8_16xb64_in1k-256px.py)    | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w8_3rdparty_in1k-256px_20220803-e318968f.pth) |
+| `swinv2-tiny-w16_3rdparty_in1k-256px`\*           | From scratch |   28.35    |   4.40    |   82.81   |   96.23   |   [config](swinv2-tiny-w16_16xb64_in1k-256px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w16_3rdparty_in1k-256px_20220803-9651cdd7.pth) |
+| `swinv2-small-w8_3rdparty_in1k-256px`\*           | From scratch |   49.73    |   8.45    |   83.74   |   96.60   |   [config](swinv2-small-w8_16xb64_in1k-256px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-small-w8_3rdparty_in1k-256px_20220803-b01a4332.pth) |
+| `swinv2-small-w16_3rdparty_in1k-256px`\*          | From scratch |   49.73    |   8.57    |   84.13   |   96.83   |  [config](swinv2-small-w16_16xb64_in1k-256px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-small-w16_3rdparty_in1k-256px_20220803-b707d206.pth) |
+| `swinv2-base-w8_3rdparty_in1k-256px`\*            | From scratch |   87.92    |   14.99   |   84.20   |   96.86   |   [config](swinv2-base-w8_16xb64_in1k-256px.py)    | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w8_3rdparty_in1k-256px_20220803-8ff28f2b.pth) |
+| `swinv2-base-w16_3rdparty_in1k-256px`\*           | From scratch |   87.92    |   15.14   |   84.60   |   97.05   |   [config](swinv2-base-w16_16xb64_in1k-256px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w16_3rdparty_in1k-256px_20220803-5a1886b7.pth) |
+| `swinv2-base-w16_in21k-pre_3rdparty_in1k-256px`\* | ImageNet-21k |   87.92    |   15.14   |   86.17   |   97.88   | [config](swinv2-base-w16_in21k-pre_16xb64_in1k-256px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w16_in21k-pre_3rdparty_in1k-256px_20220803-8d7aa8ad.pth) |
+| `swinv2-base-w24_in21k-pre_3rdparty_in1k-384px`\* | ImageNet-21k |   87.92    |   34.07   |   87.14   |   98.23   | [config](swinv2-base-w24_in21k-pre_16xb64_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w24_in21k-pre_3rdparty_in1k-384px_20220803-44eb70f8.pth) |
+| `swinv2-large-w16_in21k-pre_3rdparty_in1k-256px`\* | ImageNet-21k |   196.75   |   33.86   |   86.93   |   98.06   | [config](swinv2-large-w16_in21k-pre_16xb64_in1k-256px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-large-w16_in21k-pre_3rdparty_in1k-256px_20220803-c40cbed7.pth) |
+| `swinv2-large-w24_in21k-pre_3rdparty_in1k-384px`\* | ImageNet-21k |   196.75   |   76.20   |   87.59   |   98.27   | [config](swinv2-large-w24_in21k-pre_16xb64_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-large-w24_in21k-pre_3rdparty_in1k-384px_20220803-3b36c165.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/microsoft/Swin-Transformer). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2111.09883,
+  doi = {10.48550/ARXIV.2111.09883},
+  url = {https://arxiv.org/abs/2111.09883},
+  author = {Liu, Ze and Hu, Han and Lin, Yutong and Yao, Zhuliang and Xie, Zhenda and Wei, Yixuan and Ning, Jia and Cao, Yue and Zhang, Zheng and Dong, Li and Wei, Furu and Guo, Baining},
+  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
+  title = {Swin Transformer V2: Scaling Up Capacity and Resolution},
+  publisher = {arXiv},
+  year = {2021},
+  copyright = {Creative Commons Attribution 4.0 International}
+}
+```

configs/swin_transformer_v2/metafile.yml

+Collections:
+  - Name: Swin-Transformer V2
+    Metadata:
+      Training Data: ImageNet-1k
+      Training Techniques:
+        - AdamW
+        - Weight Decay
+      Training Resources: 16x V100 GPUs
+      Epochs: 300
+      Batch Size: 1024
+      Architecture:
+        - Shift Window Multihead Self Attention
+    Paper:
+      URL: https://arxiv.org/abs/2111.09883
+      Title: "Swin Transformer V2: Scaling Up Capacity and Resolution"
+    README: configs/swin_transformer_v2/README.md
+
+Models:
+  - Name: swinv2-tiny-w8_3rdparty_in1k-256px
+    Metadata:
+      FLOPs: 4350000000
+      Parameters: 28350000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.76
+          Top 5 Accuracy: 95.87
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w8_3rdparty_in1k-256px_20220803-e318968f.pth
+    Config: configs/swin_transformer_v2/swinv2-tiny-w8_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_tiny_patch4_window8_256.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-tiny-w16_3rdparty_in1k-256px
+    Metadata:
+      FLOPs: 4400000000
+      Parameters: 28350000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.81
+          Top 5 Accuracy: 96.23
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w16_3rdparty_in1k-256px_20220803-9651cdd7.pth
+    Config: configs/swin_transformer_v2/swinv2-tiny-w16_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_tiny_patch4_window16_256.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-small-w8_3rdparty_in1k-256px
+    Metadata:
+      FLOPs: 8450000000
+      Parameters: 49730000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.74
+          Top 5 Accuracy: 96.6
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-small-w8_3rdparty_in1k-256px_20220803-b01a4332.pth
+    Config: configs/swin_transformer_v2/swinv2-small-w8_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_small_patch4_window8_256.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-small-w16_3rdparty_in1k-256px
+    Metadata:
+      FLOPs: 8570000000
+      Parameters: 49730000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.13
+          Top 5 Accuracy: 96.83
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-small-w16_3rdparty_in1k-256px_20220803-b707d206.pth
+    Config: configs/swin_transformer_v2/swinv2-small-w16_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_small_patch4_window16_256.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-base-w8_3rdparty_in1k-256px
+    Metadata:
+      FLOPs: 14990000000
+      Parameters: 87920000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.2
+          Top 5 Accuracy: 96.86
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w8_3rdparty_in1k-256px_20220803-8ff28f2b.pth
+    Config: configs/swin_transformer_v2/swinv2-base-w8_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_base_patch4_window8_256.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-base-w16_3rdparty_in1k-256px
+    Metadata:
+      FLOPs: 15140000000
+      Parameters: 87920000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.6
+          Top 5 Accuracy: 97.05
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w16_3rdparty_in1k-256px_20220803-5a1886b7.pth
+    Config: configs/swin_transformer_v2/swinv2-base-w16_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_base_patch4_window16_256.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-base-w16_in21k-pre_3rdparty_in1k-256px
+    Metadata:
+      Training Data: ImageNet-21k
+      FLOPs: 15140000000
+      Parameters: 87920000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 86.17
+          Top 5 Accuracy: 97.88
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w16_in21k-pre_3rdparty_in1k-256px_20220803-8d7aa8ad.pth
+    Config: configs/swin_transformer_v2/swinv2-base-w16_in21k-pre_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_base_patch4_window12to16_192to256_22kto1k_ft.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-base-w24_in21k-pre_3rdparty_in1k-384px
+    Metadata:
+      Training Data: ImageNet-21k
+      FLOPs: 34070000000
+      Parameters: 87920000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 87.14
+          Top 5 Accuracy: 98.23
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w24_in21k-pre_3rdparty_in1k-384px_20220803-44eb70f8.pth
+    Config: configs/swin_transformer_v2/swinv2-base-w24_in21k-pre_16xb64_in1k-384px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_base_patch4_window12to24_192to384_22kto1k_ft.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-large-w16_in21k-pre_3rdparty_in1k-256px
+    Metadata:
+      Training Data: ImageNet-21k
+      FLOPs: 33860000000
+      Parameters: 196750000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 86.93
+          Top 5 Accuracy: 98.06
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-large-w16_in21k-pre_3rdparty_in1k-256px_20220803-c40cbed7.pth
+    Config: configs/swin_transformer_v2/swinv2-large-w16_in21k-pre_16xb64_in1k-256px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_large_patch4_window12to16_192to256_22kto1k_ft.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-large-w24_in21k-pre_3rdparty_in1k-384px
+    Metadata:
+      Training Data: ImageNet-21k
+      FLOPs: 76200000000
+      Parameters: 196750000
+    In Collection: Swin-Transformer V2
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 87.59
+          Top 5 Accuracy: 98.27
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-large-w24_in21k-pre_3rdparty_in1k-384px_20220803-3b36c165.pth
+    Config: configs/swin_transformer_v2/swinv2-large-w24_in21k-pre_16xb64_in1k-384px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_large_patch4_window12to24_192to384_22kto1k_ft.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-base-w12_3rdparty_in21k-192px
+    Metadata:
+      Training Data: ImageNet-21k
+      FLOPs: 8510000000
+      Parameters: 87920000
+    In Collection: Swin-Transformer V2
+    Results: null
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-base-w12_3rdparty_in21k-192px_20220803-f7dc9763.pth
+    Config: configs/swin_transformer_v2/swinv2-base-w12_8xb128_in21k-192px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_base_patch4_window12_192_22k.pth
+      Code: https://github.com/microsoft/Swin-Transformer
+  - Name: swinv2-large-w12_3rdparty_in21k-192px
+    Metadata:
+      Training Data: ImageNet-21k
+      FLOPs: 19040000000
+      Parameters: 196740000
+    In Collection: Swin-Transformer V2
+    Results: null
+    Weights: https://download.openmmlab.com/mmclassification/v0/swin-v2/pretrain/swinv2-large-w12_3rdparty_in21k-192px_20220803-d9073fee.pth
+    Config: configs/swin_transformer_v2/swinv2-large-w12_8xb128_in21k-192px.py
+    Converted From:
+      Weights: https://github.com/SwinTransformer/storage/releases/download/v2.0.0/swinv2_large_patch4_window12_192_22k.pth
+      Code: https://github.com/microsoft/Swin-Transformer

configs/swin_transformer_v2/swinv2-base-w12_8xb128_in21k-192px.py

+_base_ = [
+    '../_base_/models/swin_transformer_v2/base_256.py',
+    '../_base_/datasets/imagenet21k_bs128.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+# model settings
+model = dict(
+    backbone=dict(img_size=192, window_size=[12, 12, 12, 6]),
+    head=dict(num_classes=21841),
+)
+
+# dataset settings
+data_preprocessor = dict(num_classes=21841)
+
+_base_['train_pipeline'][1]['scale'] = 192  # RandomResizedCrop
+_base_['test_pipeline'][1]['scale'] = 219  # ResizeEdge
+_base_['test_pipeline'][2]['crop_size'] = 192  # CenterCrop

configs/swin_transformer_v2/swinv2-base-w16_16xb64_in1k-256px.py

+_base_ = [
+    '../_base_/models/swin_transformer_v2/base_256.py',
+    '../_base_/datasets/imagenet_bs64_swin_256.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(backbone=dict(window_size=[16, 16, 16, 8]))

configs/swin_transformer_v2/swinv2-base-w16_in21k-pre_16xb64_in1k-256px.py

+_base_ = [
+    '../_base_/models/swin_transformer_v2/base_256.py',
+    '../_base_/datasets/imagenet_bs64_swin_256.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        window_size=[16, 16, 16, 8],
+        drop_path_rate=0.2,
+        pretrained_window_sizes=[12, 12, 12, 6]))