add mmpretrain/ part

mmpretrain/configs/_base_/datasets/imagenet_bs32_simclr.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmcv.transforms import (LoadImageFromFile, RandomApply, RandomFlip,
+                             RandomGrayscale)
+from mmengine.dataset import DefaultSampler, default_collate
+
+from mmpretrain.datasets import (ColorJitter, GaussianBlur, ImageNet,
+                                 MultiView, PackInputs, RandomResizedCrop)
+from mmpretrain.models import SelfSupDataPreprocessor
+
+# 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)
+
+view_pipeline = [
+    dict(type=RandomResizedCrop, scale=224, backend='pillow'),
+    dict(type=RandomFlip, prob=0.5),
+    dict(
+        type=RandomApply,
+        transforms=[
+            dict(
+                type=ColorJitter,
+                brightness=0.8,
+                contrast=0.8,
+                saturation=0.8,
+                hue=0.2)
+        ],
+        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),
+]
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(type=MultiView, num_views=2, transforms=[view_pipeline]),
+    dict(type=PackInputs)
+]
+
+train_dataloader = dict(
+    batch_size=32,
+    num_workers=4,
+    persistent_workers=True,
+    sampler=dict(type=DefaultSampler, shuffle=True),
+    collate_fn=dict(type=default_collate),
+    dataset=dict(
+        type=ImageNet,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

mmpretrain/configs/_base_/datasets/imagenet_bs512_mae.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmcv.transforms import LoadImageFromFile, RandomFlip
+from mmengine.dataset.sampler import DefaultSampler
+
+from mmpretrain.datasets import ImageNet, PackInputs, RandomResizedCrop
+from mmpretrain.models import SelfSupDataPreprocessor
+
+# 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)
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=RandomResizedCrop,
+        scale=224,
+        crop_ratio_range=(0.2, 1.0),
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=RandomFlip, prob=0.5),
+    dict(type=PackInputs)
+]
+
+train_dataloader = dict(
+    batch_size=512,
+    num_workers=8,
+    persistent_workers=True,
+    sampler=dict(type=DefaultSampler, shuffle=True),
+    collate_fn=dict(type='default_collate'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        split='train',
+        pipeline=train_pipeline))

mmpretrain/configs/_base_/datasets/imagenet_bs64_pil_resize.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.dataset import DefaultSampler
+
+from mmpretrain.datasets import (CenterCrop, ImageNet, LoadImageFromFile,
+                                 PackInputs, RandomFlip, RandomResizedCrop,
+                                 ResizeEdge)
+from mmpretrain.evaluation import Accuracy
+
+# dataset settings
+dataset_type = ImageNet
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(type=RandomResizedCrop, scale=224, backend='pillow'),
+    dict(type=RandomFlip, prob=0.5, direction='horizontal'),
+    dict(type=PackInputs),
+]
+
+test_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(type=ResizeEdge, scale=256, edge='short', backend='pillow'),
+    dict(type=CenterCrop, crop_size=224),
+    dict(type=PackInputs),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='train',
+        pipeline=train_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='val',
+        pipeline=test_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=False),
+)
+val_evaluator = dict(type=Accuracy, topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

mmpretrain/configs/_base_/datasets/imagenet_bs64_pil_resize_autoaug.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.dataset import DefaultSampler
+
+from mmpretrain.datasets import (CenterCrop, ImageNet, LoadImageFromFile,
+                                 PackInputs, RandomFlip, RandomResizedCrop,
+                                 ResizeEdge)
+from mmpretrain.datasets.transforms import AutoAugment
+from mmpretrain.evaluation import Accuracy
+
+# dataset settings
+dataset_type = ImageNet
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+bgr_mean = data_preprocessor['mean'][::-1]
+bgr_std = data_preprocessor['std'][::-1]
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=RandomResizedCrop,
+        scale=224,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=RandomFlip, prob=0.5, direction='horizontal'),
+    dict(
+        type=AutoAugment,
+        policies='imagenet',
+        hparams=dict(
+            pad_val=[round(x) for x in bgr_mean], interpolation='bicubic')),
+    dict(type=PackInputs),
+]
+
+test_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=ResizeEdge,
+        scale=256,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=CenterCrop, crop_size=224),
+    dict(type=PackInputs),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='train',
+        pipeline=train_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='val',
+        pipeline=test_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=False),
+)
+val_evaluator = dict(type=Accuracy, topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

mmpretrain/configs/_base_/datasets/imagenet_bs64_swin_224.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.dataset import DefaultSampler
+
+from mmpretrain.datasets import (CenterCrop, ImageNet, LoadImageFromFile,
+                                 PackInputs, RandAugment, RandomErasing,
+                                 RandomFlip, RandomResizedCrop, ResizeEdge)
+from mmpretrain.evaluation import Accuracy
+
+# dataset settings
+dataset_type = ImageNet
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+bgr_mean = data_preprocessor['mean'][::-1]
+bgr_std = data_preprocessor['std'][::-1]
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=RandomResizedCrop,
+        scale=224,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=RandomFlip, prob=0.5, direction='horizontal'),
+    dict(
+        type=RandAugment,
+        policies='timm_increasing',
+        num_policies=2,
+        total_level=10,
+        magnitude_level=9,
+        magnitude_std=0.5,
+        hparams=dict(
+            pad_val=[round(x) for x in bgr_mean], interpolation='bicubic')),
+    dict(
+        type=RandomErasing,
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=bgr_mean,
+        fill_std=bgr_std),
+    dict(type=PackInputs),
+]
+
+test_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=ResizeEdge,
+        scale=256,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=CenterCrop, crop_size=224),
+    dict(type=PackInputs),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='train',
+        pipeline=train_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='val',
+        pipeline=test_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=False),
+)
+val_evaluator = dict(type=Accuracy, topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

mmpretrain/configs/_base_/datasets/imagenet_bs64_swin_256.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.dataset import DefaultSampler
+
+from mmpretrain.datasets import (CenterCrop, ImageNet, LoadImageFromFile,
+                                 PackInputs, RandAugment, RandomErasing,
+                                 RandomFlip, RandomResizedCrop, ResizeEdge)
+from mmpretrain.evaluation import Accuracy
+
+# dataset settings
+dataset_type = ImageNet
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+bgr_mean = data_preprocessor['mean'][::-1]
+bgr_std = data_preprocessor['std'][::-1]
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=RandomResizedCrop,
+        scale=256,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=RandomFlip, prob=0.5, direction='horizontal'),
+    dict(
+        type=RandAugment,
+        policies='timm_increasing',
+        num_policies=2,
+        total_level=10,
+        magnitude_level=9,
+        magnitude_std=0.5,
+        hparams=dict(
+            pad_val=[round(x) for x in bgr_mean], interpolation='bicubic')),
+    dict(
+        type=RandomErasing,
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=bgr_mean,
+        fill_std=bgr_std),
+    dict(type=PackInputs),
+]
+
+test_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=ResizeEdge,
+        scale=292,  # ( 256 / 224 * 256 )
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=CenterCrop, crop_size=256),
+    dict(type=PackInputs),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='train',
+        pipeline=train_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        split='val',
+        pipeline=test_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=False),
+)
+val_evaluator = dict(type=Accuracy, topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

mmpretrain/configs/_base_/datasets/imagenet_bs64_swin_384.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.dataset import DefaultSampler
+
+from mmpretrain.datasets import (ImageNet, LoadImageFromFile, PackInputs,
+                                 RandomFlip, RandomResizedCrop, Resize)
+from mmpretrain.evaluation import Accuracy
+
+# dataset settings
+dataset_type = ImageNet
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(
+        type=RandomResizedCrop,
+        scale=384,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type=RandomFlip, prob=0.5, direction='horizontal'),
+    dict(type=PackInputs),
+]
+
+test_pipeline = [
+    dict(type=LoadImageFromFile),
+    dict(type=Resize, scale=384, backend='pillow', interpolation='bicubic'),
+    dict(type=PackInputs),
+]
+
+train_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        ann_file='meta/train.txt',
+        data_prefix='train',
+        pipeline=train_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet',
+        ann_file='meta/val.txt',
+        data_prefix='val',
+        pipeline=test_pipeline),
+    sampler=dict(type=DefaultSampler, shuffle=False),
+)
+val_evaluator = dict(type=Accuracy, topk=(1, 5))
+
+# If you want standard test, please manually configure the test dataset
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

mmpretrain/configs/_base_/default_runtime.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook,
+                            LoggerHook, ParamSchedulerHook)
+from mmengine.visualization import LocalVisBackend
+
+from mmpretrain.engine.hooks import VisualizationHook
+from mmpretrain.visualization import UniversalVisualizer
+
+# configure default hooks
+default_hooks = dict(
+    # record the time of every iteration.
+    timer=dict(type=IterTimerHook),
+
+    # print log every 100 iterations.
+    logger=dict(type=LoggerHook, interval=100),
+
+    # enable the parameter scheduler.
+    param_scheduler=dict(type=ParamSchedulerHook),
+
+    # save checkpoint per epoch.
+    checkpoint=dict(type=CheckpointHook, interval=1),
+
+    # set sampler seed in distributed evrionment.
+    sampler_seed=dict(type=DistSamplerSeedHook),
+
+    # validation results visualization, set True to enable it.
+    visualization=dict(type=VisualizationHook, enable=False),
+)
+
+# configure environment
+env_cfg = dict(
+    # whether to enable cudnn benchmark
+    cudnn_benchmark=False,
+
+    # set multi process parameters
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+
+    # set distributed parameters
+    dist_cfg=dict(backend='nccl'),
+)
+
+# set visualizer
+vis_backends = [dict(type=LocalVisBackend)]
+visualizer = dict(type=UniversalVisualizer, vis_backends=vis_backends)
+
+# set log level
+log_level = 'INFO'
+
+# load from which checkpoint
+load_from = None
+
+# whether to resume training from the loaded checkpoint
+resume = False
+
+# Defaults to use random seed and disable `deterministic`
+randomness = dict(seed=None, deterministic=False)
+
+# Do not need to specify default_scope with new config. Therefore set it to
+# None to avoid BC-breaking.
+default_scope = None

mmpretrain/configs/_base_/models/convnext_base.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.model import TruncNormalInit
+
+from mmpretrain.models import (ConvNeXt, CutMix, ImageClassifier,
+                               LabelSmoothLoss, LinearClsHead, Mixup)
+
+# Model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(type=ConvNeXt, arch='base', drop_path_rate=0.5),
+    head=dict(
+        type=LinearClsHead,
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type=LabelSmoothLoss, label_smooth_val=0.1, mode='original'),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type=TruncNormalInit, layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type=Mixup, alpha=0.8),
+        dict(type=CutMix, alpha=1.0),
+    ]),
+)

mmpretrain/configs/_base_/models/mae_hivit_base_p16.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmpretrain.models import (MAE, MAEHiViT, MAEPretrainDecoder,
+                               MAEPretrainHead, PixelReconstructionLoss)
+
+# model settings
+model = dict(
+    type=MAE,
+    backbone=dict(type=MAEHiViT, patch_size=16, arch='base', mask_ratio=0.75),
+    neck=dict(
+        type=MAEPretrainDecoder,
+        patch_size=16,
+        in_chans=3,
+        embed_dim=512,
+        decoder_embed_dim=512,
+        decoder_depth=6,
+        decoder_num_heads=16,
+        mlp_ratio=4.,
+    ),
+    head=dict(
+        type=MAEPretrainHead,
+        norm_pix=True,
+        patch_size=16,
+        loss=dict(type=PixelReconstructionLoss, criterion='L2')),
+    init_cfg=[
+        dict(type='Xavier', layer='Linear', distribution='uniform'),
+        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
+    ])

mmpretrain/configs/_base_/models/mae_vit_base_p16.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmpretrain.models import (MAE, MAEPretrainDecoder, MAEPretrainHead,
+                               MAEViT, PixelReconstructionLoss)
+
+# model settings
+model = dict(
+    type=MAE,
+    backbone=dict(type=MAEViT, arch='b', patch_size=16, mask_ratio=0.75),
+    neck=dict(
+        type=MAEPretrainDecoder,
+        patch_size=16,
+        in_chans=3,
+        embed_dim=768,
+        decoder_embed_dim=512,
+        decoder_depth=8,
+        decoder_num_heads=16,
+        mlp_ratio=4.,
+    ),
+    head=dict(
+        type=MAEPretrainHead,
+        norm_pix=True,
+        patch_size=16,
+        loss=dict(type=PixelReconstructionLoss, criterion='L2')),
+    init_cfg=[
+        dict(type='Xavier', layer='Linear', distribution='uniform'),
+        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
+    ])

mmpretrain/configs/_base_/models/mobilenet_v2_1x.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmpretrain.models import (CrossEntropyLoss, GlobalAveragePooling,
+                               ImageClassifier, LinearClsHead, MobileNetV2)
+
+# model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(type=MobileNetV2, widen_factor=1.0),
+    neck=dict(type=GlobalAveragePooling),
+    head=dict(
+        type=LinearClsHead,
+        num_classes=1000,
+        in_channels=1280,
+        loss=dict(type=CrossEntropyLoss, loss_weight=1.0),
+        topk=(1, 5),
+    ))

mmpretrain/configs/_base_/models/mobilenet_v3_small.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.model.weight_init import NormalInit
+from torch.nn.modules.activation import Hardswish
+
+from mmpretrain.models import (CrossEntropyLoss, GlobalAveragePooling,
+                               ImageClassifier, MobileNetV3,
+                               StackedLinearClsHead)
+
+# model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(type=MobileNetV3, arch='small'),
+    neck=dict(type=GlobalAveragePooling),
+    head=dict(
+        type=StackedLinearClsHead,
+        num_classes=1000,
+        in_channels=576,
+        mid_channels=[1024],
+        dropout_rate=0.2,
+        act_cfg=dict(type=Hardswish),
+        loss=dict(type=CrossEntropyLoss, loss_weight=1.0),
+        init_cfg=dict(
+            type=NormalInit, layer='Linear', mean=0., std=0.01, bias=0.),
+        topk=(1, 5)))

mmpretrain/configs/_base_/models/resnet18.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmpretrain.models import (CrossEntropyLoss, GlobalAveragePooling,
+                               ImageClassifier, LinearClsHead, ResNet)
+
+# model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(
+        type=ResNet,
+        depth=18,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type=GlobalAveragePooling),
+    head=dict(
+        type=LinearClsHead,
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(type=CrossEntropyLoss, loss_weight=1.0),
+        topk=(1, 5),
+    ))

mmpretrain/configs/_base_/models/swin_transformer_base.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmpretrain.models import (CrossEntropyLoss, GlobalAveragePooling,
+                               ImageClassifier, LinearClsHead, SwinTransformer)
+
+# model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(
+        type=SwinTransformer,
+        arch='base',
+        img_size=384,
+        stage_cfgs=dict(block_cfgs=dict(window_size=12))),
+    neck=dict(type=GlobalAveragePooling),
+    head=dict(
+        type=LinearClsHead,
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type=CrossEntropyLoss, loss_weight=1.0),
+        topk=(1, 5)))

mmpretrain/configs/_base_/models/swin_transformer_v2_base.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmpretrain.models import (GlobalAveragePooling, ImageClassifier,
+                               LabelSmoothLoss, LinearClsHead,
+                               SwinTransformerV2)
+
+# model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(
+        type=SwinTransformerV2, arch='base', img_size=384, drop_path_rate=0.2),
+    neck=dict(type=GlobalAveragePooling),
+    head=dict(
+        type=LinearClsHead,
+        num_classes=1000,
+        in_channels=1024,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(type=LabelSmoothLoss, label_smooth_val=0.1, mode='original'),
+        cal_acc=False))

mmpretrain/configs/_base_/models/vit_base_p16.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.model.weight_init import KaimingInit
+
+from mmpretrain.models import (ImageClassifier, LabelSmoothLoss,
+                               VisionTransformer, VisionTransformerClsHead)
+
+# model settings
+model = dict(
+    type=ImageClassifier,
+    backbone=dict(
+        type=VisionTransformer,
+        arch='b',
+        img_size=224,
+        patch_size=16,
+        drop_rate=0.1,
+        init_cfg=[
+            dict(
+                type=KaimingInit,
+                layer='Conv2d',
+                mode='fan_in',
+                nonlinearity='linear')
+        ]),
+    neck=None,
+    head=dict(
+        type=VisionTransformerClsHead,
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type=LabelSmoothLoss, label_smooth_val=0.1, mode='classy_vision'),
+    ))

mmpretrain/configs/_base_/schedules/cifar10_bs128.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.optim import MultiStepLR
+from torch.optim import SGD
+
+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type=SGD, lr=0.1, momentum=0.9, weight_decay=0.0001))
+# learning policy
+param_scheduler = dict(
+    type=MultiStepLR, by_epoch=True, milestones=[100, 150], gamma=0.1)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=128)

mmpretrain/configs/_base_/schedules/cub_bs64.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.optim import CosineAnnealingLR, LinearLR
+from torch.optim import SGD
+
+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(
+        type=SGD, lr=0.01, momentum=0.9, weight_decay=0.0005, nesterov=True))
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type=LinearLR,
+        start_factor=0.01,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type=CosineAnnealingLR,
+        T_max=95,
+        by_epoch=True,
+        begin=5,
+        end=100,
+    )
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=64)

mmpretrain/configs/_base_/schedules/imagenet_bs1024_adamw_swin.py

+# Copyright (c) OpenMMLab. All rights reserved.
+# This is a BETA new format config file, and the usage may change recently.
+from mmengine.optim import CosineAnnealingLR, LinearLR
+from torch.optim import AdamW
+
+# for batch in each gpu is 128, 8 gpu
+# lr = 5e-4 * 128 * 8 / 512 = 0.001
+optim_wrapper = dict(
+    optimizer=dict(
+        type=AdamW,
+        lr=5e-4 * 1024 / 512,
+        weight_decay=0.05,
+        eps=1e-8,
+        betas=(0.9, 0.999)),
+    paramwise_cfg=dict(
+        norm_decay_mult=0.0,
+        bias_decay_mult=0.0,
+        flat_decay_mult=0.0,
+        custom_keys={
+            '.absolute_pos_embed': dict(decay_mult=0.0),
+            '.relative_position_bias_table': dict(decay_mult=0.0)
+        }),
+)
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type=LinearLR,
+        start_factor=1e-3,
+        by_epoch=True,
+        end=20,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(type=CosineAnnealingLR, eta_min=1e-5, by_epoch=True, begin=20)
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=300, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=1024)