init

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+images/wallaby.png filter=lfs diff=lfs merge=lfs -text
+images/zebra.jpg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+mmclassification
+mmdetection
+mmsegmentation
+.idea
+.DS_Store

README.md

@@ -5,7 +5,7 @@ colorFrom: gray
 colorTo: purple
 sdk: streamlit
 sdk_version: 1.17.0
-app_file: app.py
+app_file: main_page.py
 pinned: false
 ---
 

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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='PackClsInputs'),
+]
+
+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/cityscapes_detection.py

@@ -0,0 +1,66 @@
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=[(2048, 800), (2048, 1024)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/instancesonly_filtered_gtFine_train.json',
+            data_prefix=dict(img='leftImg8bit/train/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instancesonly_filtered_gtFine_val.json',
+        data_prefix=dict(img='leftImg8bit/val/'),
+        test_mode=True,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=test_pipeline))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instancesonly_filtered_gtFine_val.json',
+    metric='bbox')
+
+test_evaluator = val_evaluator

configs/_base_/datasets/cityscapes_instance.py

@@ -0,0 +1,96 @@
+# dataset settings
+dataset_type = 'CityscapesDataset'
+data_root = 'data/cityscapes/'
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='RandomResize',
+        scale=[(2048, 800), (2048, 1024)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=(2048, 1024), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=8,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/instancesonly_filtered_gtFine_train.json',
+            data_prefix=dict(img='leftImg8bit/train/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline)))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instancesonly_filtered_gtFine_val.json',
+        data_prefix=dict(img='leftImg8bit/val/'),
+        test_mode=True,
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=test_pipeline))
+
+test_dataloader = val_dataloader
+
+val_evaluator = [
+    dict(
+        type='CocoMetric',
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        metric=['bbox', 'segm']),
+    dict(
+        type='CityScapesMetric',
+        ann_file=data_root +
+        'annotations/instancesonly_filtered_gtFine_val.json',
+        seg_prefix=data_root + '/gtFine/val',
+        outfile_prefix='./work_dirs/cityscapes_metric/instance')
+]
+
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file='annotations/instancesonly_filtered_gtFine_test.json',
+#         data_prefix=dict(img='leftImg8bit/test/'),
+#         test_mode=True,
+#         filter_cfg=dict(filter_empty_gt=True, min_size=32),
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#         type='CityScapesMetric',
+#         format_only=True,
+#         outfile_prefix='./work_dirs/cityscapes_metric/test')

configs/_base_/datasets/coco_detection.py

@@ -0,0 +1,85 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox',
+    format_only=False)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric='bbox',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_detection/test')

configs/_base_/datasets/coco_instance.py

@@ -0,0 +1,85 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'],
+    format_only=False)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric=['bbox', 'segm'],
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_instance/test')

configs/_base_/datasets/coco_instance_semantic.py

@@ -0,0 +1,68 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(
+        type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/', seg='stuffthingmaps/train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric=['bbox', 'segm'],
+    format_only=False)
+test_evaluator = val_evaluator

configs/_base_/datasets/coco_panoptic.py

@@ -0,0 +1,86 @@
+# dataset settings
+dataset_type = 'CocoPanopticDataset'
+data_root = 'data/coco/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadPanopticAnnotations', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='LoadPanopticAnnotations', file_client_args=file_client_args),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/panoptic_train2017.json',
+        data_prefix=dict(
+            img='train2017/', seg='annotations/panoptic_train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/panoptic_val2017.json',
+        data_prefix=dict(img='val2017/', seg='annotations/panoptic_val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoPanopticMetric',
+    ann_file=data_root + 'annotations/panoptic_val2017.json',
+    seg_prefix=data_root + 'annotations/panoptic_val2017/',
+    file_client_args=file_client_args,
+)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=1,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file='annotations/panoptic_image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoPanopticMetric',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/panoptic_image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_panoptic/test')

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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=510),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=600),
+    dict(type='CenterCrop', crop_size=448),
+    dict(type='PackClsInputs'),
+]
+
+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/deepfashion.py

@@ -0,0 +1,83 @@
+# dataset settings
+dataset_type = 'DeepFashionDataset'
+data_root = 'data/DeepFashion/In-shop/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(type='Resize', scale=(750, 1101), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(750, 1101), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='RepeatDataset',
+        times=2,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='Anno/segmentation/DeepFashion_segmentation_train.json',
+            data_prefix=dict(img='Img/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='Anno/segmentation/DeepFashion_segmentation_query.json',
+        data_prefix=dict(img='Img/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='Anno/segmentation/DeepFashion_segmentation_gallery.json',
+        data_prefix=dict(img='Img/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root +
+    'Anno/segmentation/DeepFashion_segmentation_query.json',
+    metric=['bbox', 'segm'],
+    format_only=False)
+test_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root +
+    'Anno/segmentation/DeepFashion_segmentation_gallery.json',
+    metric=['bbox', 'segm'],
+    format_only=False)

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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=248,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=256,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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_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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=196,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=196),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=336,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=336),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=560,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=560),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=384, backend='pillow', interpolation='bicubic'),
+    dict(type='PackClsInputs'),
+]
+
+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_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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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_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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs')
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=236,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs')
+]
+
+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_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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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_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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=256,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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_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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=233,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs')
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=224,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=384,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=384),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=292,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=256),
+    dict(type='PackClsInputs')
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='ResizeEdge', scale=256, edge='short', backend='pillow'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=256,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=256,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(type='Resize', scale=384, backend='pillow', interpolation='bicubic'),
+    dict(type='PackClsInputs'),
+]
+
+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='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=248,
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=224),
+    dict(type='PackClsInputs'),
+]
+
+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_bs8_pil_bicubic_320.py

@@ -0,0 +1,61 @@
+# dataset settings
+dataset_type = 'ImageNet'
+data_preprocessor = dict(
+    # RGB format normalization parameters
+    mean=[122.5, 122.5, 122.5],
+    std=[122.5, 122.5, 122.5],
+    # convert image from BGR to RGB
+    to_rgb=True,
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='RandomResizedCrop',
+        scale=320,
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='RandomFlip', prob=0.5, direction='horizontal'),
+    dict(type='PackClsInputs'),
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile'),
+    dict(
+        type='ResizeEdge',
+        scale=int(320 / 224 * 256),
+        edge='short',
+        backend='pillow',
+        interpolation='bicubic'),
+    dict(type='CenterCrop', crop_size=320),
+    dict(type='PackClsInputs'),
+]
+
+train_dataloader = dict(
+    batch_size=8,
+    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=8,
+    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/lvis_v0.5_instance.py

@@ -0,0 +1,69 @@
+# dataset settings
+dataset_type = 'LVISV05Dataset'
+data_root = 'data/lvis_v0.5/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='RandomChoiceResize',
+        scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
+                (1333, 768), (1333, 800)],
+        keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type='ClassBalancedDataset',
+        oversample_thr=1e-3,
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/lvis_v0.5_train.json',
+            data_prefix=dict(img='train2017/'),
+            filter_cfg=dict(filter_empty_gt=True, min_size=32),
+            pipeline=train_pipeline)))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/lvis_v0.5_val.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='LVISMetric',
+    ann_file=data_root + 'annotations/lvis_v0.5_val.json',
+    metric=['bbox', 'segm'])
+test_evaluator = val_evaluator

configs/_base_/datasets/lvis_v1_instance.py

@@ -0,0 +1,22 @@
+# dataset settings
+_base_ = 'lvis_v0.5_instance.py'
+dataset_type = 'LVISV1Dataset'
+data_root = 'data/lvis_v1/'
+
+train_dataloader = dict(
+    dataset=dict(
+        dataset=dict(
+            type=dataset_type,
+            data_root=data_root,
+            ann_file='annotations/lvis_v1_train.json',
+            data_prefix=dict(img=''))))
+val_dataloader = dict(
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/lvis_v1_val.json',
+        data_prefix=dict(img='')))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(ann_file=data_root + 'annotations/lvis_v1_val.json')
+test_evaluator = val_evaluator

configs/_base_/datasets/objects365v1_detection.py

@@ -0,0 +1,64 @@
+# dataset settings
+dataset_type = 'Objects365V1Dataset'
+data_root = 'data/Objects365/Obj365_v1/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/objects365_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/objects365_val.json',
+        data_prefix=dict(img='val/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/objects365_val.json',
+    metric='bbox',
+    sort_categories=True,
+    format_only=False)
+test_evaluator = val_evaluator

configs/_base_/datasets/objects365v2_detection.py

@@ -0,0 +1,63 @@
+# dataset settings
+dataset_type = 'Objects365V2Dataset'
+data_root = 'data/Objects365/Obj365_v2/'
+
+# file_client_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+file_client_args = dict(backend='disk')
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', file_client_args=file_client_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/zhiyuan_objv2_train.json',
+        data_prefix=dict(img='train/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/zhiyuan_objv2_val.json',
+        data_prefix=dict(img='val/'),
+        test_mode=True,
+        pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/zhiyuan_objv2_val.json',
+    metric='bbox',
+    format_only=False)
+test_evaluator = val_evaluator