add part code

configs/_base_/models/seresnext101_32x4d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SEResNeXt',
+        depth=101,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=4,
+        se_ratio=16,
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/seresnext50_32x4d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SEResNeXt',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=4,
+        se_ratio=16,
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/shufflenet_v1_1x.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ShuffleNetV1', groups=3),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=960,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/shufflenet_v2_1x.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ShuffleNetV2', widen_factor=1.0),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/swin_transformer/base_224.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformer', arch='base', img_size=224, drop_path_rate=0.5),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)

configs/_base_/models/swin_transformer/base_384.py

+# model settings
+# Only for evaluation
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformer',
+        arch='base',
+        img_size=384,
+        stage_cfgs=dict(block_cfgs=dict(window_size=12))),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5)))

configs/_base_/models/swin_transformer/large_224.py

+# model settings
+# Only for evaluation
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='SwinTransformer', arch='large', img_size=224),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5)))

configs/_base_/models/swin_transformer/large_384.py

+# model settings
+# Only for evaluation
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformer',
+        arch='large',
+        img_size=384,
+        stage_cfgs=dict(block_cfgs=dict(window_size=12))),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5)))

configs/_base_/models/swin_transformer/small_224.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformer', arch='small', img_size=224,
+        drop_path_rate=0.3),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)

configs/_base_/models/swin_transformer/tiny_224.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformer', arch='tiny', img_size=224, drop_path_rate=0.2),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)

configs/_base_/models/swin_transformer_v2/base_256.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformerV2',
+        arch='base',
+        img_size=256,
+        drop_path_rate=0.5),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)

configs/_base_/models/swin_transformer_v2/base_384.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformerV2',
+        arch='base',
+        img_size=384,
+        drop_path_rate=0.2),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False))

configs/_base_/models/swin_transformer_v2/large_256.py

+# model settings
+# Only for evaluation
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformerV2',
+        arch='large',
+        img_size=256,
+        drop_path_rate=0.2),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5)))

configs/_base_/models/swin_transformer_v2/large_384.py

+# model settings
+# Only for evaluation
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformerV2',
+        arch='large',
+        img_size=384,
+        drop_path_rate=0.2),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5)))

configs/_base_/models/swin_transformer_v2/small_256.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformerV2',
+        arch='small',
+        img_size=256,
+        drop_path_rate=0.3),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)

configs/_base_/models/swin_transformer_v2/tiny_256.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SwinTransformerV2',
+        arch='tiny',
+        img_size=256,
+        drop_path_rate=0.2),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        init_cfg=None,  # suppress the default init_cfg of LinearClsHead.
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        cal_acc=False),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=0.02, bias=0.),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]),
+)

configs/_base_/models/t2t-vit-t-14.py

+# model settings
+embed_dims = 384
+num_classes = 1000
+
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='T2T_ViT',
+        img_size=224,
+        in_channels=3,
+        embed_dims=embed_dims,
+        t2t_cfg=dict(
+            token_dims=64,
+            use_performer=False,
+        ),
+        num_layers=14,
+        layer_cfgs=dict(
+            num_heads=6,
+            feedforward_channels=3 * embed_dims,  # mlp_ratio = 3
+        ),
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(type='TruncNormal', layer='Linear', std=.02),
+            dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+        ]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=num_classes,
+        in_channels=embed_dims,
+        loss=dict(
+            type='LabelSmoothLoss',
+            label_smooth_val=0.1,
+            mode='original',
+        ),
+        topk=(1, 5),
+        init_cfg=dict(type='TruncNormal', layer='Linear', std=.02)),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/t2t-vit-t-19.py

+# model settings
+embed_dims = 448
+num_classes = 1000
+
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='T2T_ViT',
+        img_size=224,
+        in_channels=3,
+        embed_dims=embed_dims,
+        t2t_cfg=dict(
+            token_dims=64,
+            use_performer=False,
+        ),
+        num_layers=19,
+        layer_cfgs=dict(
+            num_heads=7,
+            feedforward_channels=3 * embed_dims,  # mlp_ratio = 3
+        ),
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(type='TruncNormal', layer='Linear', std=.02),
+            dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+        ]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=num_classes,
+        in_channels=embed_dims,
+        loss=dict(
+            type='LabelSmoothLoss',
+            label_smooth_val=0.1,
+            mode='original',
+        ),
+        topk=(1, 5),
+        init_cfg=dict(type='TruncNormal', layer='Linear', std=.02)),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/t2t-vit-t-24.py

+# model settings
+embed_dims = 512
+num_classes = 1000
+
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='T2T_ViT',
+        img_size=224,
+        in_channels=3,
+        embed_dims=embed_dims,
+        t2t_cfg=dict(
+            token_dims=64,
+            use_performer=False,
+        ),
+        num_layers=24,
+        layer_cfgs=dict(
+            num_heads=8,
+            feedforward_channels=3 * embed_dims,  # mlp_ratio = 3
+        ),
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(type='TruncNormal', layer='Linear', std=.02),
+            dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+        ]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=num_classes,
+        in_channels=embed_dims,
+        loss=dict(
+            type='LabelSmoothLoss',
+            label_smooth_val=0.1,
+            mode='original',
+        ),
+        topk=(1, 5),
+        init_cfg=dict(type='TruncNormal', layer='Linear', std=.02)),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/tinyvit/tinyvit-11m.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='TinyViT',
+        arch='11m',
+        img_size=(224, 224),
+        window_size=[7, 7, 14, 7],
+        out_indices=(3, ),
+        drop_path_rate=0.1,
+        gap_before_final_norm=True,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['LayerNorm'], val=1., bias=0.),
+        ]),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=448,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))