first commit

configs/_base_/models/conformer/small-p32.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='Conformer',
+        arch='small',
+        patch_size=32,
+        drop_path_rate=0.1,
+        init_cfg=None),
+    neck=None,
+    head=dict(
+        type='ConformerHead',
+        num_classes=1000,
+        in_channels=[1024, 384],
+        init_cfg=None,
+        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/conformer/tiny-p16.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='Conformer', arch='tiny', drop_path_rate=0.1, init_cfg=None),
+    neck=None,
+    head=dict(
+        type='ConformerHead',
+        num_classes=1000,
+        in_channels=[256, 384],
+        init_cfg=None,
+        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/convmixer/convmixer-1024-20.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvMixer', arch='1024/20'),
+    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/convmixer/convmixer-1536-20.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvMixer', arch='1536/20'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/convmixer/convmixer-768-32.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvMixer', arch='768/32', act_cfg=dict(type='ReLU')),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

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

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvNeXt', arch='base', drop_path_rate=0.5),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/convnext/convnext-large.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvNeXt', arch='large', drop_path_rate=0.5),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

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

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvNeXt', arch='small', drop_path_rate=0.4),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

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

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvNeXt', arch='tiny', drop_path_rate=0.1),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/convnext/convnext-xlarge.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='ConvNeXt', arch='xlarge', drop_path_rate=0.5),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/convnext_v2/atto.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='atto',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=320,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.2),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+)

configs/_base_/models/convnext_v2/base.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='base',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.1),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/convnext_v2/femto.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='femto',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.1),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+)

configs/_base_/models/convnext_v2/huge.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='huge',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2816,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.1),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/convnext_v2/large.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='large',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.1),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

configs/_base_/models/convnext_v2/nano.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='nano',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=640,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.2),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+)

configs/_base_/models/convnext_v2/pico.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='pico',
+        drop_path_rate=0.1,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.1),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+)

configs/_base_/models/convnext_v2/tiny.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ConvNeXt',
+        arch='tiny',
+        drop_path_rate=0.2,
+        layer_scale_init_value=0.,
+        use_grn=True,
+    ),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(type='LabelSmoothLoss', label_smooth_val=0.2),
+        init_cfg=None,
+    ),
+    init_cfg=dict(
+        type='TruncNormal', layer=['Conv2d', 'Linear'], std=.02, bias=0.),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]),
+)

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

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DaViT', arch='base', out_indices=(3, ), drop_path_rate=0.4),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        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/davit/davit-small.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='DaViT', arch='small', out_indices=(3, ), drop_path_rate=0.2),
+    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)
+    ]))