add part code

configs/_base_/models/hivit/tiny_224.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='HiViT',
+        arch='tiny',
+        img_size=224,
+        ape=True,
+        rpe=True,
+        drop_path_rate=0.05),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=384,
+        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/hornet/hornet-base-gf.py

+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='base-gf', drop_path_rate=0.5),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

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

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='base', drop_path_rate=0.5),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/hornet/hornet-large-gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='large-gf', drop_path_rate=0.2),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/hornet/hornet-large-gf384.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='large-gf384', drop_path_rate=0.4),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ])

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

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='large', drop_path_rate=0.2),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=1536,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/hornet/hornet-small-gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='small-gf', drop_path_rate=0.4),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

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

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='small', drop_path_rate=0.4),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=768,
+        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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/hornet/hornet-tiny-gf.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='tiny-gf', drop_path_rate=0.2),
+    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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

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

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HorNet', arch='tiny', drop_path_rate=0.2),
+    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.),
+        dict(type='Constant', layer=['LayerScale'], val=1e-6)
+    ],
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0)
+    ]))

configs/_base_/models/hrnet/hrnet-w18.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w18'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(18, 36, 72, 144)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/hrnet/hrnet-w30.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w30'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(30, 60, 120, 240)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/hrnet/hrnet-w32.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w32'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(32, 64, 128, 256)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/hrnet/hrnet-w40.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w40'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(40, 80, 160, 320)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/hrnet/hrnet-w44.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w44'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(44, 88, 176, 352)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/hrnet/hrnet-w48.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w48'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(48, 96, 192, 384)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/hrnet/hrnet-w64.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='HRNet', arch='w64'),
+    neck=[
+        dict(type='HRFuseScales', in_channels=(64, 128, 256, 512)),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='LinearClsHead',
+        in_channels=2048,
+        num_classes=1000,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

configs/_base_/models/inception_v3.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(type='InceptionV3', num_classes=1000, aux_logits=False),
+    neck=None,
+    head=dict(
+        type='ClsHead',
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5)),
+)

configs/_base_/models/itpn_hivit-base-p16.py

+# model settings
+model = dict(
+    type='iTPN',
+    backbone=dict(
+        type='iTPNHiViT',
+        arch='base',
+        reconstruction_type='pixel',
+        mask_ratio=0.75),
+    neck=dict(
+        type='iTPNPretrainDecoder',
+        num_patches=196,
+        patch_size=16,
+        in_chans=3,
+        embed_dim=512,
+        decoder_embed_dim=512,
+        decoder_depth=6,
+        decoder_num_heads=16,
+        mlp_ratio=4.,
+        reconstruction_type='pixel',
+        #  transformer pyramid
+        fpn_dim=256,
+        fpn_depth=2,
+        num_outs=3,
+    ),
+    head=dict(
+        type='MAEPretrainHead',
+        norm_pix=True,
+        patch_size=16,
+        loss=dict(type='PixelReconstructionLoss', criterion='L2')),
+    init_cfg=[
+        dict(type='Xavier', layer='Linear', distribution='uniform'),
+        dict(type='Constant', layer='LayerNorm', val=1.0, bias=0.0)
+    ])

configs/_base_/models/levit-256-p16.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='LeViT',
+        arch='256',
+        img_size=224,
+        patch_size=16,
+        drop_path_rate=0,
+        attn_ratio=2,
+        mlp_ratio=2,
+        out_indices=(2, )),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LeViTClsHead',
+        num_classes=1000,
+        in_channels=512,
+        distillation=True,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, loss_weight=1.0),
+        topk=(1, 5),
+    ),
+    train_cfg=dict(augments=[
+        dict(type='Mixup', alpha=0.8),
+        dict(type='CutMix', alpha=1.0),
+    ]))