first commit

configs/_base_/models/davit/davit-tiny.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DaViT', arch='t', out_indices=(3, ), drop_path_rate=0.1),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-base-p16-224.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='b',
+        img_size=224,
+        patch_size=16,
+        drop_path_rate=0.2),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-base-p16-384.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='b',
+        img_size=384,
+        patch_size=16,
+        drop_path_rate=0.15),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-huge-p14-224.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='h',
+        img_size=224,
+        patch_size=14,
+        drop_path_rate=0.55),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=1280,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-large-p16-224.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='l',
+        img_size=224,
+        patch_size=16,
+        drop_path_rate=0.45),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-large-p16-384.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='l',
+        img_size=384,
+        patch_size=16,
+        drop_path_rate=0.4),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-medium-p16-224.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='m',
+        img_size=224,
+        patch_size=16,
+        drop_path_rate=0.2),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-small-p16-224.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='s',
+        img_size=224,
+        patch_size=16,
+        drop_path_rate=0.05),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/deit3/deit3-small-p16-384.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DeiT3',
+        arch='s',
+        img_size=384,
+        patch_size=16,
+        drop_path_rate=0.0),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    init_cfg=[
+        dict(type='TruncNormal', layer='Linear', std=.02),
+        dict(type='Constant', layer='LayerNorm', val=1., bias=0.),
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/densenet/densenet121.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='DenseNet', arch='121'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/densenet/densenet161.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='DenseNet', arch='161'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2208,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/densenet/densenet169.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='DenseNet', arch='169'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1664,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/densenet/densenet201.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='DenseNet', arch='201'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1920,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/edgenext/edgenext-base.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='EdgeNeXt',
+        arch='base',
+        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=584,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/edgenext/edgenext-small.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='EdgeNeXt',
+        arch='small',
+        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=304,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/edgenext/edgenext-xsmall.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='EdgeNeXt',
+        arch='xsmall',
+        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=192,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/edgenext/edgenext-xxsmall.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='EdgeNeXt',
+        arch='xxsmall',
+        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=168,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/efficientformer-l1.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='EfficientFormer',
+        arch='l1',
+        drop_path_rate=0,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
+            dict(type='Constant', layer=['LayerScale'], val=1e-5)
+        ]),
+    neck=dict(type='GlobalAveragePooling', dim=1),
+    head=dict(
+        type='EfficientFormerClsHead', in_channels=448, num_classes=1000))

configs/_base_/models/efficientnet_b0.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b0'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1280,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_b1.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b1'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1280,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))