添加mmclassification-0.24.1代码，删除mmclassification-speed-benchmark

openmmlab_test/mmclassification-0.24.1/configs/_base_/models/vit-base-p16.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VisionTransformer',
+        arch='b',
+        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=1000,
+        in_channels=768,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1,
+            mode='classy_vision'),
+    ))

openmmlab_test/mmclassification-0.24.1/configs/_base_/models/vit-base-p32.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VisionTransformer',
+        arch='b',
+        img_size=224,
+        patch_size=32,
+        drop_rate=0.1,
+        init_cfg=[
+            dict(
+                type='Kaiming',
+                layer='Conv2d',
+                mode='fan_in',
+                nonlinearity='linear')
+        ]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=768,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

openmmlab_test/mmclassification-0.24.1/configs/_base_/models/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=1000,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

openmmlab_test/mmclassification-0.24.1/configs/_base_/models/vit-large-p32.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='VisionTransformer',
+        arch='l',
+        img_size=224,
+        patch_size=32,
+        drop_rate=0.1,
+        init_cfg=[
+            dict(
+                type='Kaiming',
+                layer='Conv2d',
+                mode='fan_in',
+                nonlinearity='linear')
+        ]),
+    neck=None,
+    head=dict(
+        type='VisionTransformerClsHead',
+        num_classes=1000,
+        in_channels=1024,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

openmmlab_test/mmclassification-0.24.1/configs/_base_/models/wide-resnet50.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        stem_channels=64,
+        base_channels=128,
+        expansion=2,
+        style='pytorch'),
+    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),
+    ))

openmmlab_test/mmclassification-0.24.1/configs/_base_/schedules/cub_bs64.py

+# optimizer
+optimizer = dict(
+    type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0005, nesterov=True)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    min_lr=0,
+    warmup='linear',
+    warmup_iters=5,
+    warmup_ratio=0.01,
+    warmup_by_epoch=True)
+runner = dict(type='EpochBasedRunner', max_epochs=100)

openmmlab_test/mmclassification-0.24.1/configs/_base_/schedules/imagenet_bs1024_adamw_conformer.py

+paramwise_cfg = dict(
+    norm_decay_mult=0.0,
+    bias_decay_mult=0.0,
+    custom_keys={
+        '.cls_token': dict(decay_mult=0.0),
+    })
+
+# for batch in each gpu is 128, 8 gpu
+# lr = 5e-4 * 128 * 8 / 512 = 0.001
+optimizer = dict(
+    type='AdamW',
+    lr=5e-4 * 128 * 8 / 512,
+    weight_decay=0.05,
+    eps=1e-8,
+    betas=(0.9, 0.999),
+    paramwise_cfg=paramwise_cfg)
+optimizer_config = dict(grad_clip=None)
+
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    by_epoch=False,
+    min_lr_ratio=1e-2,
+    warmup='linear',
+    warmup_ratio=1e-3,
+    warmup_iters=5 * 1252,
+    warmup_by_epoch=False)
+
+runner = dict(type='EpochBasedRunner', max_epochs=300)

openmmlab_test/mmclassification-0.24.1/configs/_base_/schedules/imagenet_bs1024_adamw_swin.py

+paramwise_cfg = dict(
+    norm_decay_mult=0.0,
+    bias_decay_mult=0.0,
+    custom_keys={
+        '.absolute_pos_embed': dict(decay_mult=0.0),
+        '.relative_position_bias_table': dict(decay_mult=0.0)
+    })
+
+# for batch in each gpu is 128, 8 gpu
+# lr = 5e-4 * 128 * 8 / 512 = 0.001
+optimizer = dict(
+    type='AdamW',
+    lr=5e-4 * 1024 / 512,
+    weight_decay=0.05,
+    eps=1e-8,
+    betas=(0.9, 0.999),
+    paramwise_cfg=paramwise_cfg)
+optimizer_config = dict(grad_clip=dict(max_norm=5.0))
+
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    by_epoch=False,
+    min_lr_ratio=1e-2,
+    warmup='linear',
+    warmup_ratio=1e-3,
+    warmup_iters=20,
+    warmup_by_epoch=True)
+
+runner = dict(type='EpochBasedRunner', max_epochs=300)

openmmlab_test/mmclassification-0.24.1/configs/_base_/schedules/imagenet_bs1024_coslr.py

+# optimizer
+optimizer = dict(type='SGD', lr=0.8, momentum=0.9, weight_decay=5e-5)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    min_lr=0,
+    warmup='linear',
+    warmup_iters=5,
+    warmup_ratio=0.1,
+    warmup_by_epoch=True)
+runner = dict(type='EpochBasedRunner', max_epochs=100)

openmmlab_test/mmclassification-0.24.1/configs/_base_/schedules/imagenet_bs2048_rsb.py

+# optimizer
+optimizer = dict(type='Lamb', lr=0.005, weight_decay=0.02)
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+    policy='CosineAnnealing',
+    min_lr=1.0e-6,
+    warmup='linear',
+    # For ImageNet-1k, 626 iters per epoch, warmup 5 epochs.
+    warmup_iters=5 * 626,
+    warmup_ratio=0.0001)
+runner = dict(type='EpochBasedRunner', max_epochs=100)