upload mmpretrain

configs/_base_/models/mobilevit/mobilevit_s.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='MobileViT', arch='small'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=640,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/mobilevit/mobilevit_xs.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='MobileViT', arch='x_small'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/mobilevit/mobilevit_xxs.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='MobileViT', arch='xx_small'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=320,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/mvit/mvitv2-base.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='MViT', arch='base', drop_path_rate=0.3),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        in_channels=768,
+        num_classes=1000,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    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/mvit/mvitv2-large.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='MViT',
+        arch='large',
+        drop_path_rate=0.5,
+        dim_mul_in_attention=False),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        in_channels=1152,
+        num_classes=1000,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    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/mvit/mvitv2-small.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='MViT', arch='small', drop_path_rate=0.1),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        in_channels=768,
+        num_classes=1000,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    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/mvit/mvitv2-tiny.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='MViT', arch='tiny', drop_path_rate=0.1),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        in_channels=768,
+        num_classes=1000,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, mode='original'),
+    ),
+    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/poolformer/poolformer_m36.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='PoolFormer',
+        arch='m36',
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
+        ]),
+    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/poolformer/poolformer_m48.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='PoolFormer',
+        arch='m48',
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
+        ]),
+    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/poolformer/poolformer_s12.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='PoolFormer',
+        arch='s12',
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
+        ]),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/poolformer/poolformer_s24.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='PoolFormer',
+        arch='s24',
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
+        ]),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/poolformer/poolformer_s36.py

+# Model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='PoolFormer',
+        arch='s36',
+        drop_path_rate=0.1,
+        init_cfg=[
+            dict(
+                type='TruncNormal',
+                layer=['Conv2d', 'Linear'],
+                std=.02,
+                bias=0.),
+            dict(type='Constant', layer=['GroupNorm'], val=1., bias=0.),
+        ]),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

configs/_base_/models/regnet/regnetx_1.6gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_1.6gf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=912,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_12gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_12gf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2240,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_3.2gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_3.2gf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1008,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_4.0gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_4.0gf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1360,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_400mf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_400mf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=384,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_6.4gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_6.4gf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1624,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_8.0gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_8.0gf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1920,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/regnet/regnetx_800mf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='RegNet', arch='regnetx_800mf'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=672,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))