first commit

configs/_base_/models/efficientnet_b2.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b2'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1408,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_b3.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b3'),
+    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/efficientnet_b4.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b4'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1792,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_b5.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b5'),
+    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/efficientnet_b6.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b6'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2304,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_b7.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b7'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2560,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_b8.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='b8'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2816,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_em.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    # `em` means EfficientNet-EdgeTPU-M arch
+    backbone=dict(type='EfficientNet', arch='em', act_cfg=dict(type='ReLU')),
+    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_es.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    # `es` means EfficientNet-EdgeTPU-S arch
+    backbone=dict(type='EfficientNet', arch='es', act_cfg=dict(type='ReLU')),
+    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_l2.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNet', arch='l2'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=5504,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_v2/efficientnetv2_b0.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', 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_v2/efficientnetv2_b1.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', 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),
+    ))

configs/_base_/models/efficientnet_v2/efficientnetv2_b2.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', arch='b2'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1408,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/efficientnet_v2/efficientnetv2_b3.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', arch='b3'),
+    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/efficientnet_v2/efficientnetv2_l.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', arch='l'),
+    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_v2/efficientnetv2_m.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', arch='m'),
+    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_v2/efficientnetv2_s.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', arch='s'),
+    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_v2/efficientnetv2_xl.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='EfficientNetV2', arch='xl'),
+    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/eva/eva-g.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='BEiTViT',
+        arch='eva-g',
+        img_size=224,
+        patch_size=14,
+        layer_scale_init_value=0.0,
+        out_type='avg_featmap',
+        use_abs_pos_emb=True,
+        use_rel_pos_bias=False,
+        use_shared_rel_pos_bias=False,
+    ),
+    neck=None,
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1408,
+        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/eva/eva-l.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='BEiTViT',
+        arch='l',
+        img_size=224,
+        patch_size=14,
+        layer_scale_init_value=0.0,
+        out_type='avg_featmap',
+        use_abs_pos_emb=True,
+        use_rel_pos_bias=False,
+        use_shared_rel_pos_bias=False,
+        layer_cfgs=dict(bias=True),
+    ),
+    neck=None,
+    head=dict(
+        type='LinearClsHead',
+        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)
+    ]))