first commit

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/tiny-vit-large-p16.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VisionTransformer',
+        arch='l',
+        img_size=224,
+        patch_size=16,
+        drop_rate=0.1,
+        init_cfg=[
+            dict(
+                type='Kaiming',
+                layer='Conv2d',
+                mode='fan_in',
+                nonlinearity='linear')
+        ]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=200,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

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),
+    ))

configs/_base_/models/tinyvit/tinyvit-21m.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='TinyViT',
+        arch='21m',
+        img_size=(224, 224),
+        window_size=[7, 7, 14, 7],
+        out_indices=(3, ),
+        drop_path_rate=0.2,
+        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=576,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/tinyvit/tinyvit-5m.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='TinyViT',
+        arch='5m',
+        img_size=(224, 224),
+        window_size=[7, 7, 14, 7],
+        out_indices=(3, ),
+        drop_path_rate=0.0,
+        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=320,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/tnt_s_patch16_224.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='TNT',
+        arch='s',
+        img_size=224,
+        patch_size=16,
+        in_channels=3,
+        ffn_ratio=4,
+        qkv_bias=False,
+        drop_rate=0.,
+        attn_drop_rate=0.,
+        drop_path_rate=0.1,
+        first_stride=4,
+        num_fcs=2,
+        init_cfg=[
+            dict(type='TruncNormal', layer='Linear', std=.02),
+            dict(type='Constant', layer='LayerNorm', val=1., bias=0.)
+        ]),
+    neck=None,
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+        topk=(1, 5),
+        init_cfg=dict(type='TruncNormal', layer='Linear', std=.02)))

configs/_base_/models/twins_pcpvt_base.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='PCPVT',
+        arch='base',
+        in_channels=3,
+        out_indices=(3, ),
+        qkv_bias=True,
+        norm_cfg=dict(type='LN', eps=1e-06),
+        norm_after_stage=[False, False, False, True],
+        drop_rate=0.0,
+        attn_drop_rate=0.,
+        drop_path_rate=0.3),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        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/twins_svt_base.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SVT',
+        arch='base',
+        in_channels=3,
+        out_indices=(3, ),
+        qkv_bias=True,
+        norm_cfg=dict(type='LN'),
+        norm_after_stage=[False, False, False, True],
+        drop_rate=0.0,
+        attn_drop_rate=0.,
+        drop_path_rate=0.3),
+    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'),
+        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/van/van_base.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VAN', arch='base', drop_path_rate=0.1),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        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/van/van_large.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VAN', arch='large', drop_path_rate=0.2),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        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/van/van_small.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VAN', arch='small', drop_path_rate=0.1),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        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/van/van_tiny.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VAN', arch='tiny', drop_path_rate=0.1),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=256,
+        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/vgg11.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VGG', depth=11, num_classes=1000),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/vgg11bn.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VGG', depth=11, norm_cfg=dict(type='BN'), num_classes=1000),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/vgg13.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VGG', depth=13, num_classes=1000),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/vgg13bn.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VGG', depth=13, norm_cfg=dict(type='BN'), num_classes=1000),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/vgg16.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='VGG', depth=16, num_classes=1000),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/vgg16bn.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VGG', depth=16, norm_cfg=dict(type='BN'), num_classes=1000),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))