Initial commit

.gitignore

@@ -0,0 +1,179 @@
+data
+work_dirs
+
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

configs/_base_/datasets/cifar100_bs16.py

@@ -0,0 +1,45 @@
+# dataset settings
+dataset_type = 'CIFAR100'
+data_preprocessor = dict(
+    num_classes=100,
+    # RGB format normalization parameters
+    mean=[129.304, 124.070, 112.434],
+    std=[68.170, 65.392, 70.418],
+    # loaded images are already RGB format
+    to_rgb=False)
+
+train_pipeline = [
+    dict(type='RandomCrop', crop_size=32, padding=4),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_prefix='data/cifar100',
+        test_mode=False,
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=16,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_prefix='data/cifar100/',
+        test_mode=True,
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='Accuracy', topk=(1, ))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/datasets/cifar10_bs16.py

@@ -0,0 +1,45 @@
+# dataset settings
+dataset_type = 'CIFAR10'
+data_preprocessor = dict(
+    num_classes=10,
+    # RGB format normalization parameters
+    mean=[125.307, 122.961, 113.8575],
+    std=[51.5865, 50.847, 51.255],
+    # loaded images are already RGB format
+    to_rgb=False)
+
+train_pipeline = [
+    dict(type='RandomCrop', crop_size=32, padding=4),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_prefix='data/cifar10',
+        test_mode=False,
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=16,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_prefix='data/cifar10/',
+        test_mode=True,
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='Accuracy', topk=(1, ))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/datasets/cub_bs8_384.py

@@ -0,0 +1,51 @@
+# dataset settings
+dataset_type = 'CUB'
+data_preprocessor = dict(
+    num_classes=200,
+    # 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='Resize', scale=510),
+    dict(type='RandomCrop', crop_size=384),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=510),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/CUB_200_2011',
+        test_mode=False,
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=8,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/CUB_200_2011',
+        test_mode=True,
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='Accuracy', topk=(1, ))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/datasets/cub_bs8_448.py

@@ -0,0 +1,50 @@
+# dataset settings
+dataset_type = 'CUB'
+data_preprocessor = dict(
+    num_classes=200,
+    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='Resize', scale=600),
+    dict(type='RandomCrop', crop_size=448),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=600),
+    dict(type='CenterCrop', crop_size=448),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/CUB_200_2011',
+        test_mode=False,
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=8,
+    num_workers=2,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/CUB_200_2011',
+        test_mode=True,
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='Accuracy', topk=(1, ))
+
+test_dataloader = val_dataloader
+test_evaluator = val_evaluator

configs/_base_/datasets/fungi_bs16_swin_384.py

@@ -0,0 +1,93 @@
+_base_ = ['./pipelines/rand_aug.py']
+
+# dataset settings
+dataset_type = 'Fungi'
+data_preprocessor = dict(
+    num_classes=1604,
+    # 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='LoadImageFromFileFungi'),
+    dict(
+        type='RandomResizedCrop',
+        scale=384,
+        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='LoadImageFromFileFungi'),
+    dict(
+        type='ResizeEdge',
+        scale=438,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    num_workers=8,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/fungi2023/',
+        ann_file='FungiCLEF2023_train_metadata_PRODUCTION.csv',
+        data_prefix='DF20/',
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=8,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/fungi2023/',
+        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
+        data_prefix='DF21/',
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
+
+test_dataloader = dict(
+    batch_size=64,
+    num_workers=8,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/fungi2023/',
+        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
+        data_prefix='DF21/',
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+test_evaluator = val_evaluator

configs/_base_/datasets/fungi_bs16_swin_384_class-balanced.py

@@ -0,0 +1,96 @@
+_base_ = ['./pipelines/rand_aug.py']
+
+# dataset settings
+dataset_type = 'Fungi'
+data_preprocessor = dict(
+    num_classes=1604,
+    # 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='LoadImageFromFileFungi'),
+    dict(
+        type='RandomResizedCrop',
+        scale=384,
+        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='LoadImageFromFileFungi'),
+    dict(
+        type='ResizeEdge',
+        scale=438,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    num_workers=8,
+    dataset=dict(
+        type='ClassBalancedDataset',
+        oversample_thr=1e-2,
+        dataset=dict(
+            type=dataset_type,
+            data_root='data/fungi2023/',
+            ann_file='FungiCLEF2023_train_metadata_PRODUCTION.csv',
+            data_prefix='DF20/',
+            pipeline=train_pipeline)),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=8,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/fungi2023/',
+        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
+        data_prefix='DF21/',
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+val_evaluator = dict(type='SingleLabelMetric', items=['precision', 'recall', 'f1-score'])
+
+test_dataloader = dict(
+    batch_size=64,
+    num_workers=8,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/fungi2023/',
+        ann_file='FungiCLEF2023_val_metadata_PRODUCTION.csv',
+        data_prefix='DF21/',
+        pipeline=test_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=False),
+)
+test_evaluator = val_evaluator

configs/_base_/datasets/imagenet21k_bs128.py

@@ -0,0 +1,53 @@
+# dataset settings
+dataset_type = 'ImageNet21k'
+data_preprocessor = dict(
+    num_classes=21842,
+    # 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),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet21k',
+        ann_file='meta/train.txt',
+        data_prefix='train',
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=128,
+    num_workers=5,
+    dataset=dict(
+        type=dataset_type,
+        data_root='data/imagenet21k',
+        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

configs/_base_/datasets/imagenet_bs128_mbv3.py

@@ -0,0 +1,68 @@
+# 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'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(
+        type='AutoAugment',
+        policies='imagenet',
+        hparams=dict(pad_val=[round(x) for x in bgr_mean])),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.2,
+        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'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    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=128,
+    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

configs/_base_/datasets/imagenet_bs128_poolformer_medium_224.py

@@ -0,0 +1,82 @@
+# 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=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    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=128,
+    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

configs/_base_/datasets/imagenet_bs128_poolformer_small_224.py

@@ -0,0 +1,82 @@
+# 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=248,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    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=128,
+    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

configs/_base_/datasets/imagenet_bs128_revvit_224.py

@@ -0,0 +1,85 @@
+# 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=7,
+        magnitude_std=0.5,
+        hparams=dict(
+            pad_val=[round(x) for x in bgr_mean], interpolation='bicubic')),
+    dict(type='ColorJitter', brightness=0.4, contrast=0.4, saturation=0.4),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',  # should be 'pixel', but currently not supported
+        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=256,
+    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),
+    persistent_workers=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),
+    persistent_workers=True,
+)
+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

configs/_base_/datasets/imagenet_bs128_riformer_medium_384.py

@@ -0,0 +1,82 @@
+# 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=384,
+        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=404,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    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=16,
+    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

configs/_base_/datasets/imagenet_bs128_riformer_small_384.py

@@ -0,0 +1,82 @@
+# 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=384,
+        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=426,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    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=32,
+    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

configs/_base_/datasets/imagenet_bs128_vig_224.py

@@ -0,0 +1,82 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[127.5, 127.5, 127.5],
+    std=[127.5, 127.5, 127.5],
+    # 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=248,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=128,
+    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=128,
+    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

configs/_base_/datasets/imagenet_bs16_eva_196.py

@@ -0,0 +1,62 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255],
+    std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        scale=196,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=196,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=196),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    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=16,
+    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

configs/_base_/datasets/imagenet_bs16_eva_336.py

@@ -0,0 +1,62 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255],
+    std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        scale=336,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=336,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=336),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    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=16,
+    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

configs/_base_/datasets/imagenet_bs16_eva_560.py

@@ -0,0 +1,62 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_preprocessor = dict(
+    num_classes=1000,
+    # RGB format normalization parameters
+    mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255],
+    std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        scale=560,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=560,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=560),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=16,
+    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=16,
+    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

configs/_base_/datasets/imagenet_bs16_pil_bicubic_384.py

@@ -0,0 +1,55 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_preprocessor = dict(
+    # 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=16,
+    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=16,
+    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

configs/_base_/datasets/imagenet_bs256_beitv2.py

@@ -0,0 +1,48 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_root = 'data/imagenet/'
+data_preprocessor = dict(
+    type='TwoNormDataPreprocessor',
+    mean=[123.675, 116.28, 103.53],
+    std=[58.395, 57.12, 57.375],
+    second_mean=[127.5, 127.5, 127.5],
+    second_std=[127.5, 127.5, 127.5],
+    to_rgb=True)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ColorJitter',
+        brightness=0.4,
+        contrast=0.4,
+        saturation=0.4,
+        hue=0.),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(
+        type='RandomResizedCropAndInterpolationWithTwoPic',
+        size=224,
+        second_size=224,
+        interpolation='bicubic',
+        second_interpolation='bicubic',
+        scale=(0.2, 1.0)),
+    dict(
+        type='BEiTMaskGenerator',
+        input_size=(14, 14),
+        num_masking_patches=75,
+        max_num_patches=75,
+        min_num_patches=16),
+    dict(type='PackInputs')
+]
+
+train_dataloader = dict(
+    batch_size=256,
+    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,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs256_davit_224.py

@@ -0,0 +1,82 @@
+# 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=236,
+        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',
+        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

configs/_base_/datasets/imagenet_bs256_levit_224.py

@@ -0,0 +1,82 @@
+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=256,
+    num_workers=4,
+    dataset=dict(
+        type=dataset_type,
+        data_root=r'E:\imagenet',
+        ann_file='meta/val.txt',
+        data_prefix='ILSVRC2012_img_val',
+        pipeline=train_pipeline),
+    sampler=dict(type='DefaultSampler', shuffle=True),
+)
+
+val_dataloader = dict(
+    batch_size=256,
+    num_workers=4,
+    dataset=dict(
+        type=dataset_type,
+        data_root=r'E:\imagenet',
+        ann_file='meta/val.txt',
+        data_prefix='ILSVRC2012_img_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

configs/_base_/datasets/imagenet_bs256_rsb_a12.py

@@ -0,0 +1,74 @@
+# 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=7,
+        magnitude_std=0.5,
+        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=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs')
+]
+
+train_dataloader = dict(
+    batch_size=256,
+    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=256,
+    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

configs/_base_/datasets/imagenet_bs256_rsb_a3.py

@@ -0,0 +1,74 @@
+# 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=6,
+        magnitude_std=0.5,
+        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=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs')
+]
+
+train_dataloader = dict(
+    batch_size=256,
+    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=256,
+    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

configs/_base_/datasets/imagenet_bs256_simmim_192.py

@@ -0,0 +1,34 @@
+# 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=192, crop_ratio_range=(0.67, 1.0)),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='SimMIMMaskGenerator',
+        input_size=192,
+        mask_patch_size=32,
+        model_patch_size=4,
+        mask_ratio=0.6),
+    dict(type='PackInputs')
+]
+
+train_dataloader = dict(
+    batch_size=256,
+    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,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs256_swin_192.py

@@ -0,0 +1,83 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_root = 'data/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=192,
+        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=[104, 116, 124], interpolation='bicubic')),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=[103.53, 116.28, 123.675],
+        fill_std=[57.375, 57.12, 58.395]),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=219,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=192),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=256,
+    num_workers=8,
+    collate_fn=dict(type='default_collate'),
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix='train',
+        pipeline=train_pipeline),
+)
+
+val_dataloader = dict(
+    batch_size=64,
+    num_workers=5,
+    collate_fn=dict(type='default_collate'),
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='meta/val.txt',
+        data_prefix='val',
+        pipeline=test_pipeline),
+)
+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

configs/_base_/datasets/imagenet_bs32.py

@@ -0,0 +1,53 @@
+# 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),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=32,
+    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=32,
+    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

configs/_base_/datasets/imagenet_bs32_byol.py

@@ -0,0 +1,90 @@
+# 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_pipeline1 = [
+    dict(
+        type='RandomResizedCrop',
+        scale=224,
+        interpolation='bicubic',
+        backend='pillow'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.2,
+                hue=0.1)
+        ],
+        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=1.),
+    dict(type='Solarize', thr=128, prob=0.),
+]
+view_pipeline2 = [
+    dict(
+        type='RandomResizedCrop',
+        scale=224,
+        interpolation='bicubic',
+        backend='pillow'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.2,
+                hue=0.1)
+        ],
+        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=0.1),
+    dict(type='Solarize', thr=128, prob=0.2)
+]
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiView',
+        num_views=[1, 1],
+        transforms=[view_pipeline1, view_pipeline2]),
+    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=dataset_type,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs32_mocov2.py

@@ -0,0 +1,59 @@
+# 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)
+
+# The difference between mocov2 and mocov1 is the transforms in the pipeline
+view_pipeline = [
+    dict(
+        type='RandomResizedCrop',
+        scale=224,
+        crop_ratio_range=(0.2, 1.),
+        backend='pillow'),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.4,
+                hue=0.1)
+        ],
+        prob=0.8),
+    dict(
+        type='RandomGrayscale',
+        prob=0.2,
+        keep_channels=True,
+        channel_weights=(0.114, 0.587, 0.2989)),
+    dict(
+        type='GaussianBlur',
+        magnitude_range=(0.1, 2.0),
+        magnitude_std='inf',
+        prob=0.5),
+    dict(type='RandomFlip', prob=0.5),
+]
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='MultiView', num_views=2, transforms=[view_pipeline]),
+    dict(type='PackInputs')
+]
+
+train_dataloader = dict(
+    batch_size=32,
+    num_workers=8,
+    drop_last=True,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    collate_fn=dict(type='default_collate'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs32_pil_bicubic.py

@@ -0,0 +1,62 @@
+# 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',
+        interpolation='bicubic'),
+    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',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=32,
+    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=32,
+    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

configs/_base_/datasets/imagenet_bs32_pil_resize.py

@@ -0,0 +1,53 @@
+# 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=32,
+    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=32,
+    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

configs/_base_/datasets/imagenet_bs32_simclr.py

@@ -0,0 +1,53 @@
+# 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=dataset_type,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs512_mae.py

@@ -0,0 +1,33 @@
+# 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,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs512_mocov3.py

@@ -0,0 +1,91 @@
+# 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_pipeline1 = [
+    dict(
+        type='RandomResizedCrop',
+        scale=224,
+        crop_ratio_range=(0.2, 1.),
+        backend='pillow'),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.2,
+                hue=0.1)
+        ],
+        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=1.),
+    dict(type='Solarize', thr=128, prob=0.),
+    dict(type='RandomFlip', prob=0.5),
+]
+view_pipeline2 = [
+    dict(
+        type='RandomResizedCrop',
+        scale=224,
+        crop_ratio_range=(0.2, 1.),
+        backend='pillow'),
+    dict(
+        type='RandomApply',
+        transforms=[
+            dict(
+                type='ColorJitter',
+                brightness=0.4,
+                contrast=0.4,
+                saturation=0.2,
+                hue=0.1)
+        ],
+        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=0.1),
+    dict(type='Solarize', thr=128, prob=0.2),
+    dict(type='RandomFlip', prob=0.5),
+]
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='MultiView',
+        num_views=[1, 1],
+        transforms=[view_pipeline1, view_pipeline2]),
+    dict(type='PackInputs')
+]
+
+train_dataloader = dict(
+    batch_size=512,
+    num_workers=8,
+    persistent_workers=True,
+    pin_memory=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    collate_fn=dict(type='default_collate'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='meta/train.txt',
+        data_prefix=dict(img_path='train/'),
+        pipeline=train_pipeline))

configs/_base_/datasets/imagenet_bs64.py

@@ -0,0 +1,53 @@
+# 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),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    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',
+        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

configs/_base_/datasets/imagenet_bs64_autoaug.py

@@ -0,0 +1,61 @@
+# 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),
+    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'),
+    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',
+        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

configs/_base_/datasets/imagenet_bs64_clip_224.py

@@ -0,0 +1,72 @@
+# dataset settings
+dataset_type = 'ImageNet'
+img_norm_cfg = dict(
+    mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255],
+    std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255],
+    to_rgb=True)
+image_size = 224
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        size=image_size,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    # dict(
+    #     type='RandAugment',
+    #     policies={{_base_.rand_increasing_policies}},
+    #     num_policies=2,
+    #     total_level=10,
+    #     magnitude_level=9,
+    #     magnitude_std=0.5,
+    #     hparams=dict(
+    #         pad_val=[round(x) for x in img_norm_cfg['mean'][::-1]],
+    #         interpolation='bicubic')),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=img_norm_cfg['mean'][::-1],
+        fill_std=img_norm_cfg['std'][::-1]),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='Resize',
+        size=(image_size, -1),
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=image_size),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    samples_per_gpu=64,
+    workers_per_gpu=8,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+
+evaluation = dict(interval=10, metric='accuracy')

configs/_base_/datasets/imagenet_bs64_clip_384.py

@@ -0,0 +1,72 @@
+# dataset settings
+dataset_type = 'ImageNet'
+img_norm_cfg = dict(
+    mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255],
+    std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255],
+    to_rgb=True)
+image_size = 384
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        size=image_size,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    # dict(
+    #     type='RandAugment',
+    #     policies={{_base_.rand_increasing_policies}},
+    #     num_policies=2,
+    #     total_level=10,
+    #     magnitude_level=9,
+    #     magnitude_std=0.5,
+    #     hparams=dict(
+    #         pad_val=[round(x) for x in img_norm_cfg['mean'][::-1]],
+    #         interpolation='bicubic')),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=img_norm_cfg['mean'][::-1],
+        fill_std=img_norm_cfg['std'][::-1]),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='Resize',
+        size=(image_size, -1),
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=image_size),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    samples_per_gpu=64,
+    workers_per_gpu=8,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+
+evaluation = dict(interval=10, metric='accuracy')

configs/_base_/datasets/imagenet_bs64_clip_448.py

@@ -0,0 +1,73 @@
+# dataset settings
+dataset_type = 'ImageNet'
+img_norm_cfg = dict(
+    mean=[0.48145466 * 255, 0.4578275 * 255, 0.40821073 * 255],
+    std=[0.26862954 * 255, 0.26130258 * 255, 0.27577711 * 255],
+    to_rgb=True)
+image_size = 448
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        size=image_size,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    # dict(
+    #     type='RandAugment',
+    #     policies={{_base_.rand_increasing_policies}},
+    #     num_policies=2,
+    #     total_level=10,
+    #     magnitude_level=9,
+    #     magnitude_std=0.5,
+    #     hparams=dict(
+    #         pad_val=[round(x) for x in img_norm_cfg['mean'][::-1]],
+    #         interpolation='bicubic')),
+    dict(
+        type='RandomErasing',
+        erase_prob=0.25,
+        mode='rand',
+        min_area_ratio=0.02,
+        max_area_ratio=1 / 3,
+        fill_color=img_norm_cfg['mean'][::-1],
+        fill_std=img_norm_cfg['std'][::-1]),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='Resize',
+        size=(image_size, -1),
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=image_size),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+
+data = dict(
+    samples_per_gpu=64,
+    workers_per_gpu=8,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+
+evaluation = dict(interval=10, metric='accuracy')

configs/_base_/datasets/imagenet_bs64_convmixer_224.py

@@ -0,0 +1,82 @@
+# 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=233,
+        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',
+        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

configs/_base_/datasets/imagenet_bs64_deit3_224.py

@@ -0,0 +1,82 @@
+# 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=224,
+        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',
+        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

configs/_base_/datasets/imagenet_bs64_deit3_384.py

@@ -0,0 +1,62 @@
+# 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='ResizeEdge',
+        scale=384,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=384),
+    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

configs/_base_/datasets/imagenet_bs64_edgenext_256.py

@@ -0,0 +1,82 @@
+# 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,
+        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',
+        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

configs/_base_/datasets/imagenet_bs64_mixer_224.py

@@ -0,0 +1,54 @@
+# dataset settings
+dataset_type = 'ImageNet'
+
+# Google research usually use the below normalization setting.
+data_preprocessor = dict(
+    num_classes=1000,
+    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=224),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', 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',
+        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

configs/_base_/datasets/imagenet_bs64_pil_resize.py

@@ -0,0 +1,53 @@
+# 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',
+        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

configs/_base_/datasets/imagenet_bs64_pil_resize_autoaug.py

@@ -0,0 +1,70 @@
+# 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',
+        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

configs/_base_/datasets/imagenet_bs64_swin_224.py

@@ -0,0 +1,82 @@
+# 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',
+        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

configs/_base_/datasets/imagenet_bs64_swin_256.py

@@ -0,0 +1,82 @@
+# 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',
+        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

configs/_base_/datasets/imagenet_bs64_swin_384.py

@@ -0,0 +1,56 @@
+# 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

configs/_base_/datasets/imagenet_bs64_t2t_224.py

@@ -0,0 +1,82 @@
+# 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=248,
+        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',
+        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