first commit

configs/vision_transformer/metafile.yml

+Collections:
+  - Name: Vision Transformer
+    Metadata:
+      Architecture:
+        - Attention Dropout
+        - Convolution
+        - Dense Connections
+        - Dropout
+        - GELU
+        - Layer Normalization
+        - Multi-Head Attention
+        - Scaled Dot-Product Attention
+        - Tanh Activation
+    Paper:
+      Title: 'An Image is Worth 16x16 Words: Transformers for Image Recognition at
+        Scale'
+      URL: https://arxiv.org/abs/2010.11929
+    README: configs/vision_transformer/README.md
+    Code:
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v0.17.0/mmcls/models/backbones/vision_transformer.py
+      Version: v0.17.0
+
+Models:
+  - Name: vit-base-p32_in21k-pre_3rdparty_in1k-384px
+    Metadata:
+      FLOPs: 13056716544
+      Parameters: 88297192
+      Training Data:
+        - ImageNet-21k
+        - ImageNet-1k
+    In Collection: Vision Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Task: Image Classification
+        Metrics:
+          Top 1 Accuracy: 84.01
+          Top 5 Accuracy: 97.08
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p32_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-9cea8599.pth
+    Config: configs/vision_transformer/vit-base-p32_64xb64_in1k-384px.py
+    Converted From:
+      Weights: https://console.cloud.google.com/storage/browser/_details/vit_models/augreg/B_32-i21k-300ep-lr_0.001-aug_light1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz
+      Code: https://github.com/google-research/vision_transformer/blob/88a52f8892c80c10de99194990a517b4d80485fd/vit_jax/models.py#L208
+  - Name: vit-base-p16_32xb128-mae_in1k
+    Metadata:
+      FLOPs: 17581972224
+      Parameters: 86567656
+      Training Data:
+        - ImageNet-1k
+    In Collection: Vision Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Task: Image Classification
+        Metrics:
+          Top 1 Accuracy: 82.37
+          Top 5 Accuracy: 96.15
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/vit-base-p16_pt-32xb128-mae_in1k_20220623-4c544545.pth
+    Config: configs/vision_transformer/vit-base-p16_32xb128-mae_in1k.py
+  - Name: vit-base-p16_in21k-pre_3rdparty_in1k-384px
+    Metadata:
+      FLOPs: 55538974464
+      Parameters: 86859496
+      Training Data:
+        - ImageNet-21k
+        - ImageNet-1k
+    In Collection: Vision Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Task: Image Classification
+        Metrics:
+          Top 1 Accuracy: 85.43
+          Top 5 Accuracy: 97.77
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-98e8652b.pth
+    Config: configs/vision_transformer/vit-base-p16_64xb64_in1k-384px.py
+    Converted From:
+      Weights: https://console.cloud.google.com/storage/browser/_details/vit_models/augreg/B_16-i21k-300ep-lr_0.001-aug_medium1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.03-res_384.npz
+      Code: https://github.com/google-research/vision_transformer/blob/88a52f8892c80c10de99194990a517b4d80485fd/vit_jax/models.py#L208
+  - Name: vit-large-p16_in21k-pre_3rdparty_in1k-384px
+    Metadata:
+      FLOPs: 191210034176
+      Parameters: 304715752
+      Training Data:
+        - ImageNet-21k
+        - ImageNet-1k
+    In Collection: Vision Transformer
+    Results:
+      - Dataset: ImageNet-1k
+        Task: Image Classification
+        Metrics:
+          Top 1 Accuracy: 85.63
+          Top 5 Accuracy: 97.63
+    Weights: https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-large-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-b20ba619.pth
+    Config: configs/vision_transformer/vit-large-p16_64xb64_in1k-384px.py
+    Converted From:
+      Weights: https://console.cloud.google.com/storage/browser/_details/vit_models/augreg/L_16-i21k-300ep-lr_0.001-aug_strong1-wd_0.1-do_0.0-sd_0.0--imagenet2012-steps_20k-lr_0.01-res_384.npz
+      Code: https://github.com/google-research/vision_transformer/blob/88a52f8892c80c10de99194990a517b4d80485fd/vit_jax/models.py#L208

configs/vision_transformer/vit-base-p16_32xb128-mae_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='VisionTransformer',
+        arch='base',
+        img_size=224,
+        patch_size=16,
+        drop_path_rate=0.1),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=768,
+        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)
+    ]))
+
+# dataset settings
+train_dataloader = dict(batch_size=128)
+
+# schedule settings
+optim_wrapper = dict(
+    optimizer=dict(
+        type='AdamW',
+        lr=1e-4 * 4096 / 256,
+        weight_decay=0.3,
+        eps=1e-8,
+        betas=(0.9, 0.95)),
+    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)
+        }))
+
+# runtime settings
+custom_hooks = [dict(type='EMAHook', momentum=1e-4)]
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+# base_batch_size = (32 GPUs) x (128 samples per GPU)
+auto_scale_lr = dict(base_batch_size=4096)

configs/vision_transformer/vit-base-p16_4xb544-ipu_in1k.py

+_base_ = [
+    '../_base_/models/vit-base-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/default_runtime.py'
+]
+
+# specific to vit pretrain
+paramwise_cfg = dict(custom_keys={
+    '.cls_token': dict(decay_mult=0.0),
+    '.pos_embed': dict(decay_mult=0.0)
+})
+
+pretrained = 'https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-base-p16_3rdparty_pt-64xb64_in1k-224_20210928-02284250.pth'  # noqa
+
+model = dict(
+    head=dict(
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0, _delete_=True), ),
+    backbone=dict(
+        img_size=224,
+        init_cfg=dict(
+            type='Pretrained',
+            checkpoint=pretrained,
+            _delete_=True,
+            prefix='backbone')))
+
+img_norm_cfg = dict(
+    mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=224, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='ToHalf', keys=['img']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(224, -1), keep_ratio=True, backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToHalf', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+# change batch size
+data = dict(
+    samples_per_gpu=17,
+    workers_per_gpu=16,
+    drop_last=True,
+    train=dict(pipeline=train_pipeline),
+    train_dataloader=dict(mode='async'),
+    val=dict(pipeline=test_pipeline, ),
+    val_dataloader=dict(samples_per_gpu=4, workers_per_gpu=1),
+    test=dict(pipeline=test_pipeline),
+    test_dataloader=dict(samples_per_gpu=4, workers_per_gpu=1))
+
+# optimizer
+optimizer = dict(
+    type='SGD',
+    lr=0.08,
+    weight_decay=1e-5,
+    momentum=0.9,
+    paramwise_cfg=paramwise_cfg,
+)
+
+# learning policy
+param_scheduler = [
+    dict(type='LinearLR', start_factor=0.02, by_epoch=False, begin=0, end=800),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=4200,
+        by_epoch=False,
+        begin=800,
+        end=5000)
+]
+
+# ipu cfg
+# model partition config
+ipu_model_cfg = dict(
+    train_split_edges=[
+        dict(layer_to_call='backbone.patch_embed', ipu_id=0),
+        dict(layer_to_call='backbone.layers.3', ipu_id=1),
+        dict(layer_to_call='backbone.layers.6', ipu_id=2),
+        dict(layer_to_call='backbone.layers.9', ipu_id=3)
+    ],
+    train_ckpt_nodes=['backbone.layers.{}'.format(i) for i in range(12)])
+
+# device config
+options_cfg = dict(
+    randomSeed=42,
+    partialsType='half',
+    train_cfg=dict(
+        executionStrategy='SameAsIpu',
+        Training=dict(gradientAccumulation=32),
+        availableMemoryProportion=[0.3, 0.3, 0.3, 0.3],
+    ),
+    eval_cfg=dict(deviceIterations=1, ),
+)
+
+# add model partition config and device config to runner
+runner = dict(
+    type='IterBasedRunner',
+    ipu_model_cfg=ipu_model_cfg,
+    options_cfg=options_cfg,
+    max_iters=5000)
+
+default_hooks = dict(checkpoint=dict(type='CheckpointHook', interval=1000))
+
+fp16 = dict(loss_scale=256.0, velocity_accum_type='half', accum_type='half')

configs/vision_transformer/vit-base-p16_64xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/vit-base-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(backbone=dict(img_size=384))
+
+# dataset setting
+data_preprocessor = dict(
+    mean=[127.5, 127.5, 127.5],
+    std=[127.5, 127.5, 127.5],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=384, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-base-p16_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/vit-base-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
+)
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-base-p16_8xb64-lora_in1k-384px.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs64_pil_resize.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='LoRAModel',
+        module=dict(
+            type='VisionTransformer',
+            arch='b',
+            img_size=384,
+            patch_size=16,
+            drop_rate=0.1,
+            init_cfg=dict(type='Pretrained', checkpoint='',
+                          prefix='backbone')),
+        alpha=16,
+        rank=16,
+        drop_rate=0.1,
+        targets=[dict(type='qkv')]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1,
+            mode='classy_vision'),
+        init_cfg=[dict(type='TruncNormal', layer='Linear', std=2e-5)],
+    ))
+
+# dataset setting
+data_preprocessor = dict(
+    mean=[127.5, 127.5, 127.5],
+    std=[127.5, 127.5, 127.5],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=384, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1e-4,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=45,
+        by_epoch=True,
+        begin=5,
+        end=50,
+        eta_min=1e-6,
+        convert_to_iter_based=True)
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=50)
+default_hooks = dict(
+    # save checkpoint per epoch.
+    checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-base-p32_64xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/vit-base-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(backbone=dict(img_size=384))
+
+# dataset setting
+data_preprocessor = dict(
+    mean=[127.5, 127.5, 127.5],
+    std=[127.5, 127.5, 127.5],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=384, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-base-p32_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/vit-base-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
+)
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-large-p16_64xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/vit-large-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(backbone=dict(img_size=384))
+
+# dataset setting
+data_preprocessor = dict(
+    mean=[127.5, 127.5, 127.5],
+    std=[127.5, 127.5, 127.5],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=384, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-large-p16_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/vit-large-p16.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
+)
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-large-p32_64xb64_in1k-384px.py

+_base_ = [
+    '../_base_/models/vit-large-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(backbone=dict(img_size=384))
+
+# dataset setting
+data_preprocessor = dict(
+    mean=[127.5, 127.5, 127.5],
+    std=[127.5, 127.5, 127.5],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='RandomResizedCrop', scale=384, backend='pillow'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/vision_transformer/vit-large-p32_64xb64_in1k.py

+_base_ = [
+    '../_base_/models/vit-large-p32.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
+    '../_base_/schedules/imagenet_bs4096_AdamW.py',
+    '../_base_/default_runtime.py'
+]
+
+# model setting
+model = dict(
+    head=dict(hidden_dim=3072),
+    train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
+)
+
+# schedule setting
+optim_wrapper = dict(clip_grad=dict(max_norm=1.0))

configs/wrn/README.md

+# Wide-ResNet
+
+> [Wide Residual Networks](https://arxiv.org/abs/1605.07146)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/156701329-2c7ec7bc-23da-401b-86bf-dea8567ccee8.png" width="90%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('wide-resnet50_3rdparty_8xb32_in1k', 'demo/bird.JPEG')
+print(predict['pred_class'])
+print(predict['pred_score'])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('wide-resnet50_3rdparty_8xb32_in1k', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Test:
+
+```shell
+python tools/test.py configs/wrn/wide-resnet50_8xb32_in1k.py https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Classification on ImageNet-1k
+
+| Model                                      |   Pretrain   | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) |                   Config                   |                              Download                               |
+| :----------------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :----------------------------------------: | :-----------------------------------------------------------------: |
+| `wide-resnet50_3rdparty_8xb32_in1k`\*      | From scratch |   68.88    |   11.44   |   78.48   |   94.08   |   [config](wide-resnet50_8xb32_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth) |
+| `wide-resnet101_3rdparty_8xb32_in1k`\*     | From scratch |   126.89   |   22.81   |   78.84   |   94.28   |   [config](wide-resnet101_8xb32_in1k.py)   | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet101_3rdparty_8xb32_in1k_20220304-8d5f9d61.pth) |
+| `wide-resnet50_3rdparty-timm_8xb32_in1k`\* | From scratch |   68.88    |   11.44   |   81.45   |   95.53   | [config](wide-resnet50_timm_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty-timm_8xb32_in1k_20220304-83ae4399.pth) |
+
+*Models with * are converted from the [timm](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/resnet.py). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@INPROCEEDINGS{Zagoruyko2016WRN,
+    author = {Sergey Zagoruyko and Nikos Komodakis},
+    title = {Wide Residual Networks},
+    booktitle = {BMVC},
+    year = {2016}}
+```

configs/wrn/metafile.yml

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

configs/wrn/wide-resnet101_8xb32_in1k.py

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

configs/wrn/wide-resnet50_8xb32_in1k.py

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

configs/wrn/wide-resnet50_timm_8xb32_in1k.py

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

configs/xcit/README.md

+# XCiT
+
+> [XCiT: Cross-Covariance Image Transformers](https://arxiv.org/abs/2106.09681)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/26739999/218900814-64a44606-150b-4757-aec8-7015c77a9fd1.png" width="60%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('xcit-nano-12-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/xcit/xcit-nano-12-p16_8xb128_in1k.py https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty_in1k_20230213-ed776c38.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Pretrained models
+
+| Model                                           | Params (M) | Flops (G) |                      Config                       |                                       Download                                        |
+| :---------------------------------------------- | :--------: | :-------: | :-----------------------------------------------: | :-----------------------------------------------------------------------------------: |
+| `xcit-nano-12-p16_3rdparty_in1k`\*              |    3.05    |   0.56    |     [config](xcit-nano-12-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty_in1k_20230213-ed776c38.pth) |
+| `xcit-nano-12-p16_3rdparty-dist_in1k`\*         |    3.05    |   0.56    |     [config](xcit-nano-12-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k_20230213-fb247f7b.pth) |
+| `xcit-tiny-12-p16_3rdparty_in1k`\*              |    6.72    |   1.24    |     [config](xcit-tiny-12-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty_in1k_20230213-82c547ca.pth) |
+| `xcit-tiny-12-p16_3rdparty-dist_in1k`\*         |    6.72    |   1.24    |     [config](xcit-tiny-12-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k_20230213-d5fde0a3.pth) |
+| `xcit-nano-12-p16_3rdparty-dist_in1k-384px`\*   |    3.05    |   1.64    |  [config](xcit-nano-12-p16_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k-384px_20230213-712db4d4.pth) |
+| `xcit-nano-12-p8_3rdparty_in1k`\*               |    3.05    |   2.16    |     [config](xcit-nano-12-p8_8xb128_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty_in1k_20230213-3370c293.pth) |
+| `xcit-nano-12-p8_3rdparty-dist_in1k`\*          |    3.05    |   2.16    |     [config](xcit-nano-12-p8_8xb128_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k_20230213-2f87d2b3.pth) |
+| `xcit-tiny-24-p16_3rdparty_in1k`\*              |   12.12    |   2.34    |     [config](xcit-tiny-24-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty_in1k_20230213-366c1cd0.pth) |
+| `xcit-tiny-24-p16_3rdparty-dist_in1k`\*         |   12.12    |   2.34    |     [config](xcit-tiny-24-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k_20230213-b472e80a.pth) |
+| `xcit-tiny-12-p16_3rdparty-dist_in1k-384px`\*   |    6.72    |   3.64    |  [config](xcit-tiny-12-p16_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k-384px_20230213-00a20023.pth) |
+| `xcit-tiny-12-p8_3rdparty_in1k`\*               |    6.71    |   4.81    |     [config](xcit-tiny-12-p8_8xb128_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty_in1k_20230213-8b02f8f5.pth) |
+| `xcit-tiny-12-p8_3rdparty-dist_in1k`\*          |    6.71    |   4.81    |     [config](xcit-tiny-12-p8_8xb128_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k_20230213-f3f9b44f.pth) |
+| `xcit-small-12-p16_3rdparty_in1k`\*             |   26.25    |   4.81    |    [config](xcit-small-12-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty_in1k_20230213-d36779d2.pth) |
+| `xcit-small-12-p16_3rdparty-dist_in1k`\*        |   26.25    |   4.81    |    [config](xcit-small-12-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k_20230213-c95bbae1.pth) |
+| `xcit-nano-12-p8_3rdparty-dist_in1k-384px`\*    |    3.05    |   6.34    |  [config](xcit-nano-12-p8_8xb128_in1k-384px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k-384px_20230213-09d925ef.pth) |
+| `xcit-tiny-24-p16_3rdparty-dist_in1k-384px`\*   |   12.12    |   6.87    |  [config](xcit-tiny-24-p16_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k-384px_20230213-20e13917.pth) |
+| `xcit-small-24-p16_3rdparty_in1k`\*             |   47.67    |   9.10    |    [config](xcit-small-24-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty_in1k_20230213-40febe38.pth) |
+| `xcit-small-24-p16_3rdparty-dist_in1k`\*        |   47.67    |   9.10    |    [config](xcit-small-24-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k_20230213-130d7262.pth) |
+| `xcit-tiny-24-p8_3rdparty_in1k`\*               |   12.11    |   9.21    |     [config](xcit-tiny-24-p8_8xb128_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty_in1k_20230213-4b9ba392.pth) |
+| `xcit-tiny-24-p8_3rdparty-dist_in1k`\*          |   12.11    |   9.21    |     [config](xcit-tiny-24-p8_8xb128_in1k.py)      | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k_20230213-ad9c44b0.pth) |
+| `xcit-tiny-12-p8_3rdparty-dist_in1k-384px`\*    |    6.71    |   14.13   |  [config](xcit-tiny-12-p8_8xb128_in1k-384px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k-384px_20230213-a072174a.pth) |
+| `xcit-small-12-p16_3rdparty-dist_in1k-384px`\*  |   26.25    |   14.14   | [config](xcit-small-12-p16_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k-384px_20230213-ba36c982.pth) |
+| `xcit-medium-24-p16_3rdparty_in1k`\*            |   84.40    |   16.13   |    [config](xcit-medium-24-p16_8xb128_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty_in1k_20230213-ad0aa92e.pth) |
+| `xcit-medium-24-p16_3rdparty-dist_in1k`\*       |   84.40    |   16.13   |    [config](xcit-medium-24-p16_8xb128_in1k.py)    | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k_20230213-aca5cd0c.pth) |
+| `xcit-small-12-p8_3rdparty_in1k`\*              |   26.21    |   18.69   |     [config](xcit-small-12-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty_in1k_20230213-9e364ce3.pth) |
+| `xcit-small-12-p8_3rdparty-dist_in1k`\*         |   26.21    |   18.69   |     [config](xcit-small-12-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k_20230213-71886580.pth) |
+| `xcit-small-24-p16_3rdparty-dist_in1k-384px`\*  |   47.67    |   26.72   | [config](xcit-small-24-p16_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k-384px_20230213-28fa2d0e.pth) |
+| `xcit-tiny-24-p8_3rdparty-dist_in1k-384px`\*    |   12.11    |   27.05   |  [config](xcit-tiny-24-p8_8xb128_in1k-384px.py)   | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k-384px_20230213-30d5e5ec.pth) |
+| `xcit-small-24-p8_3rdparty_in1k`\*              |   47.63    |   35.81   |     [config](xcit-small-24-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty_in1k_20230213-280ebcc7.pth) |
+| `xcit-small-24-p8_3rdparty-dist_in1k`\*         |   47.63    |   35.81   |     [config](xcit-small-24-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k_20230213-f2773c78.pth) |
+| `xcit-large-24-p16_3rdparty_in1k`\*             |   189.10   |   35.86   |    [config](xcit-large-24-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty_in1k_20230214-d29d2529.pth) |
+| `xcit-large-24-p16_3rdparty-dist_in1k`\*        |   189.10   |   35.86   |    [config](xcit-large-24-p16_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k_20230214-4fea599c.pth) |
+| `xcit-medium-24-p16_3rdparty-dist_in1k-384px`\* |   84.40    |   47.39   | [config](xcit-medium-24-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k-384px_20230214-6c23a201.pth) |
+| `xcit-small-12-p8_3rdparty-dist_in1k-384px`\*   |   26.21    |   54.92   |  [config](xcit-small-12-p8_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k-384px_20230214-9f2178bc.pth) |
+| `xcit-medium-24-p8_3rdparty_in1k`\*             |   84.32    |   63.52   |    [config](xcit-medium-24-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty_in1k_20230214-c362850b.pth) |
+| `xcit-medium-24-p8_3rdparty-dist_in1k`\*        |   84.32    |   63.52   |    [config](xcit-medium-24-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k_20230214-625c953b.pth) |
+| `xcit-small-24-p8_3rdparty-dist_in1k-384px`\*   |   47.63    |  105.24   |  [config](xcit-small-24-p8_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k-384px_20230214-57298eca.pth) |
+| `xcit-large-24-p16_3rdparty-dist_in1k-384px`\*  |   189.10   |  105.35   | [config](xcit-large-24-p16_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k-384px_20230214-bd515a34.pth) |
+| `xcit-large-24-p8_3rdparty_in1k`\*              |   188.93   |  141.23   |     [config](xcit-large-24-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty_in1k_20230214-08f2f664.pth) |
+| `xcit-large-24-p8_3rdparty-dist_in1k`\*         |   188.93   |  141.23   |     [config](xcit-large-24-p8_8xb128_in1k.py)     | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k_20230214-8c092b34.pth) |
+| `xcit-medium-24-p8_3rdparty-dist_in1k-384px`\*  |   84.32    |  186.67   | [config](xcit-medium-24-p8_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k-384px_20230214-5db925e0.pth) |
+| `xcit-large-24-p8_3rdparty-dist_in1k-384px`\*   |   188.93   |  415.00   |  [config](xcit-large-24-p8_8xb128_in1k-384px.py)  | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k-384px_20230214-9f718b1a.pth) |
+
+*Models with * are converted from the [official repo](https://github.com/facebookresearch/xcit). The config files of these models are only for inference. We haven't reproduce the training results.*
+
+## Citation
+
+```bibtex
+@article{el2021xcit,
+  title={XCiT: Cross-Covariance Image Transformers},
+  author={El-Nouby, Alaaeldin and Touvron, Hugo and Caron, Mathilde and Bojanowski, Piotr and Douze, Matthijs and Joulin, Armand and Laptev, Ivan and Neverova, Natalia and Synnaeve, Gabriel and Verbeek, Jakob and others},
+  journal={arXiv preprint arXiv:2106.09681},
+  year={2021}
+}
+```

configs/xcit/metafile.yml

+Collections:
+  - Name: XCiT
+    Metadata:
+      Architecture:
+        - Class Attention
+        - Local Patch Interaction
+        - Cross-Covariance Attention
+    Paper:
+      Title: 'XCiT: Cross-Covariance Image Transformers'
+      URL: https://arxiv.org/abs/2106.09681
+    README: configs/xcit/README.md
+
+Models:
+  - Name: xcit-nano-12-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 557074560
+      Parameters: 3053224
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 70.35
+          Top 5 Accuracy: 89.98
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty_in1k_20230213-ed776c38.pth
+    Config: configs/xcit/xcit-nano-12-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p16_224.pth
+  - Name: xcit-nano-12-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 557074560
+      Parameters: 3053224
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 72.36
+          Top 5 Accuracy: 91.02
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k_20230213-fb247f7b.pth
+    Config: configs/xcit/xcit-nano-12-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p16_224_dist.pth
+  - Name: xcit-tiny-12-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 1239698112
+      Parameters: 6716272
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 77.21
+          Top 5 Accuracy: 93.62
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty_in1k_20230213-82c547ca.pth
+    Config: configs/xcit/xcit-tiny-12-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p16_224.pth
+  - Name: xcit-tiny-12-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 1239698112
+      Parameters: 6716272
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 78.7
+          Top 5 Accuracy: 94.12
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k_20230213-d5fde0a3.pth
+    Config: configs/xcit/xcit-tiny-12-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p16_224_dist.pth
+  - Name: xcit-nano-12-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 1636347520
+      Parameters: 3053224
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 74.93
+          Top 5 Accuracy: 92.42
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k-384px_20230213-712db4d4.pth
+    Config: configs/xcit/xcit-nano-12-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p16_384_dist.pth
+  - Name: xcit-nano-12-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 2156861056
+      Parameters: 3049016
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 73.8
+          Top 5 Accuracy: 92.08
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty_in1k_20230213-3370c293.pth
+    Config: configs/xcit/xcit-nano-12-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p8_224.pth
+  - Name: xcit-nano-12-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 2156861056
+      Parameters: 3049016
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 76.17
+          Top 5 Accuracy: 93.08
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k_20230213-2f87d2b3.pth
+    Config: configs/xcit/xcit-nano-12-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p8_224_dist.pth
+  - Name: xcit-tiny-24-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 2339305152
+      Parameters: 12116896
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.47
+          Top 5 Accuracy: 94.85
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty_in1k_20230213-366c1cd0.pth
+    Config: configs/xcit/xcit-tiny-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p16_224.pth
+  - Name: xcit-tiny-24-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 2339305152
+      Parameters: 12116896
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 80.51
+          Top 5 Accuracy: 95.17
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k_20230213-b472e80a.pth
+    Config: configs/xcit/xcit-tiny-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p16_224_dist.pth
+  - Name: xcit-tiny-12-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 3641468352
+      Parameters: 6716272
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 80.58
+          Top 5 Accuracy: 95.38
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k-384px_20230213-00a20023.pth
+    Config: configs/xcit/xcit-tiny-12-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p16_384_dist.pth
+  - Name: xcit-tiny-12-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 4807399872
+      Parameters: 6706504
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 79.75
+          Top 5 Accuracy: 94.88
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty_in1k_20230213-8b02f8f5.pth
+    Config: configs/xcit/xcit-tiny-12-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p8_224.pth
+  - Name: xcit-tiny-12-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 4807399872
+      Parameters: 6706504
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.26
+          Top 5 Accuracy: 95.46
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k_20230213-f3f9b44f.pth
+    Config: configs/xcit/xcit-tiny-12-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p8_224_dist.pth
+  - Name: xcit-small-12-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 4814951808
+      Parameters: 26253304
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.87
+          Top 5 Accuracy: 95.77
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty_in1k_20230213-d36779d2.pth
+    Config: configs/xcit/xcit-small-12-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p16_224.pth
+  - Name: xcit-small-12-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 4814951808
+      Parameters: 26253304
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.12
+          Top 5 Accuracy: 96.41
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k_20230213-c95bbae1.pth
+    Config: configs/xcit/xcit-small-12-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p16_224_dist.pth
+  - Name: xcit-nano-12-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 6337760896
+      Parameters: 3049016
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 77.69
+          Top 5 Accuracy: 94.09
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k-384px_20230213-09d925ef.pth
+    Config: configs/xcit/xcit-nano-12-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p8_384_dist.pth
+  - Name: xcit-tiny-24-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 6872966592
+      Parameters: 12116896
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.43
+          Top 5 Accuracy: 96.2
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k-384px_20230213-20e13917.pth
+    Config: configs/xcit/xcit-tiny-24-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p16_384_dist.pth
+  - Name: xcit-small-24-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 9095064960
+      Parameters: 47671384
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.38
+          Top 5 Accuracy: 95.93
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty_in1k_20230213-40febe38.pth
+    Config: configs/xcit/xcit-small-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p16_224.pth
+  - Name: xcit-small-24-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 9095064960
+      Parameters: 47671384
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.7
+          Top 5 Accuracy: 96.61
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k_20230213-130d7262.pth
+    Config: configs/xcit/xcit-small-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p16_224_dist.pth
+  - Name: xcit-tiny-24-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 9205828032
+      Parameters: 12107128
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 81.7
+          Top 5 Accuracy: 95.9
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty_in1k_20230213-4b9ba392.pth
+    Config: configs/xcit/xcit-tiny-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p8_224.pth
+  - Name: xcit-tiny-24-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 9205828032
+      Parameters: 12107128
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.62
+          Top 5 Accuracy: 96.16
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k_20230213-ad9c44b0.pth
+    Config: configs/xcit/xcit-tiny-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p8_224_dist.pth
+  - Name: xcit-tiny-12-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 14126142912
+      Parameters: 6706504
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.46
+          Top 5 Accuracy: 96.22
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k-384px_20230213-a072174a.pth
+    Config: configs/xcit/xcit-tiny-12-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p8_384_dist.pth
+  - Name: xcit-small-12-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 14143179648
+      Parameters: 26253304
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.74
+          Top 5 Accuracy: 97.19
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k-384px_20230213-ba36c982.pth
+    Config: configs/xcit/xcit-small-12-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p16_384_dist.pth
+  - Name: xcit-medium-24-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 16129561088
+      Parameters: 84395752
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.56
+          Top 5 Accuracy: 95.82
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty_in1k_20230213-ad0aa92e.pth
+    Config: configs/xcit/xcit-medium-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p16_224.pth
+  - Name: xcit-medium-24-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 16129561088
+      Parameters: 84395752
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.15
+          Top 5 Accuracy: 96.82
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k_20230213-aca5cd0c.pth
+    Config: configs/xcit/xcit-medium-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p16_224_dist.pth
+  - Name: xcit-small-12-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 18691601280
+      Parameters: 26213032
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.21
+          Top 5 Accuracy: 96.41
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty_in1k_20230213-9e364ce3.pth
+    Config: configs/xcit/xcit-small-12-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p8_224.pth
+  - Name: xcit-small-12-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 18691601280
+      Parameters: 26213032
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.97
+          Top 5 Accuracy: 96.81
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k_20230213-71886580.pth
+    Config: configs/xcit/xcit-small-12-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p8_224_dist.pth
+  - Name: xcit-small-24-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 26721471360
+      Parameters: 47671384
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.1
+          Top 5 Accuracy: 97.32
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k-384px_20230213-28fa2d0e.pth
+    Config: configs/xcit/xcit-small-24-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p16_384_dist.pth
+  - Name: xcit-tiny-24-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 27052135872
+      Parameters: 12107128
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.77
+          Top 5 Accuracy: 96.72
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k-384px_20230213-30d5e5ec.pth
+    Config: configs/xcit/xcit-tiny-24-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p8_384_dist.pth
+  - Name: xcit-small-24-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 35812053888
+      Parameters: 47631112
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.62
+          Top 5 Accuracy: 96.51
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty_in1k_20230213-280ebcc7.pth
+    Config: configs/xcit/xcit-small-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p8_224.pth
+  - Name: xcit-small-24-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 35812053888
+      Parameters: 47631112
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.68
+          Top 5 Accuracy: 97.07
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k_20230213-f2773c78.pth
+    Config: configs/xcit/xcit-small-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p8_224_dist.pth
+  - Name: xcit-large-24-p16_3rdparty_in1k
+    Metadata:
+      FLOPs: 35855948544
+      Parameters: 189096136
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 82.97
+          Top 5 Accuracy: 95.86
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty_in1k_20230214-d29d2529.pth
+    Config: configs/xcit/xcit-large-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p16_224.pth
+  - Name: xcit-large-24-p16_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 35855948544
+      Parameters: 189096136
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.61
+          Top 5 Accuracy: 97.07
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k_20230214-4fea599c.pth
+    Config: configs/xcit/xcit-large-24-p16_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p16_224_dist.pth
+  - Name: xcit-medium-24-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 47388932608
+      Parameters: 84395752
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.47
+          Top 5 Accuracy: 97.49
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k-384px_20230214-6c23a201.pth
+    Config: configs/xcit/xcit-medium-24-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p16_384_dist.pth
+  - Name: xcit-small-12-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 54923537280
+      Parameters: 26213032
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.12
+          Top 5 Accuracy: 97.31
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k-384px_20230214-9f2178bc.pth
+    Config: configs/xcit/xcit-small-12-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p8_384_dist.pth
+  - Name: xcit-medium-24-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 63524706816
+      Parameters: 84323624
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 83.61
+          Top 5 Accuracy: 96.23
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty_in1k_20230214-c362850b.pth
+    Config: configs/xcit/xcit-medium-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p8_224.pth
+  - Name: xcit-medium-24-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 63524706816
+      Parameters: 84323624
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.0
+          Top 5 Accuracy: 97.16
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k_20230214-625c953b.pth
+    Config: configs/xcit/xcit-medium-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p8_224_dist.pth
+  - Name: xcit-small-24-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 105236704128
+      Parameters: 47631112
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.57
+          Top 5 Accuracy: 97.6
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k-384px_20230214-57298eca.pth
+    Config: configs/xcit/xcit-small-24-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p8_384_dist.pth
+  - Name: xcit-large-24-p16_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 105345095424
+      Parameters: 189096136
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.78
+          Top 5 Accuracy: 97.6
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k-384px_20230214-bd515a34.pth
+    Config: configs/xcit/xcit-large-24-p16_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p16_384_dist.pth
+  - Name: xcit-large-24-p8_3rdparty_in1k
+    Metadata:
+      FLOPs: 141225699072
+      Parameters: 188932648
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 84.23
+          Top 5 Accuracy: 96.58
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty_in1k_20230214-08f2f664.pth
+    Config: configs/xcit/xcit-large-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p8_224.pth
+  - Name: xcit-large-24-p8_3rdparty-dist_in1k
+    Metadata:
+      FLOPs: 141225699072
+      Parameters: 188932648
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.14
+          Top 5 Accuracy: 97.32
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k_20230214-8c092b34.pth
+    Config: configs/xcit/xcit-large-24-p8_8xb128_in1k.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p8_224_dist.pth
+  - Name: xcit-medium-24-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 186672626176
+      Parameters: 84323624
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 85.87
+          Top 5 Accuracy: 97.61
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k-384px_20230214-5db925e0.pth
+    Config: configs/xcit/xcit-medium-24-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p8_384_dist.pth
+  - Name: xcit-large-24-p8_3rdparty-dist_in1k-384px
+    Metadata:
+      FLOPs: 415003137792
+      Parameters: 188932648
+      Training Data: ImageNet-1k
+    In Collection: XCiT
+    Results:
+      - Dataset: ImageNet-1k
+        Metrics:
+          Top 1 Accuracy: 86.13
+          Top 5 Accuracy: 97.75
+        Task: Image Classification
+    Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k-384px_20230214-9f718b1a.pth
+    Config: configs/xcit/xcit-large-24-p8_8xb128_in1k-384px.py
+    Converted From:
+      Code: https://github.com/facebookresearch/xcit
+      Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p8_384_dist.pth

configs/xcit/xcit-large-24-p16_8xb128_in1k-384px.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs64_swin_384.py',
+    '../_base_/schedules/imagenet_bs1024_adamw_swin.py',
+    '../_base_/default_runtime.py',
+]
+
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='XCiT',
+        patch_size=16,
+        embed_dims=768,
+        depth=24,
+        num_heads=16,
+        mlp_ratio=4,
+        qkv_bias=True,
+        layer_scale_init_value=1e-5,
+        tokens_norm=True,
+        out_type='cls_token',
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)
+
+# dataset settings
+train_dataloader = dict(batch_size=128)