添加openmmlab测试用例

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet18_cifar.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet_CIFAR',
+        depth=18,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=10,
+        in_channels=512,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet34.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet',
+        depth=34,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=512,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        topk=(1, 5),
+    ))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet34_cifar.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet_CIFAR',
+        depth=34,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=10,
+        in_channels=512,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet50.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        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-speed-benchmark/configs/_base_/models/resnet50_cifar.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet_CIFAR',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=10,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+    ))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet50_cifar_cutmix.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet_CIFAR',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='MultiLabelLinearClsHead',
+        num_classes=10,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0, use_soft=True)),
+    train_cfg=dict(
+        augments=dict(type='BatchCutMix', alpha=1.0, num_classes=10,
+                      prob=1.0)))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet50_cifar_mixup.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet_CIFAR',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='MultiLabelLinearClsHead',
+        num_classes=10,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0, use_soft=True)),
+    train_cfg=dict(
+        augments=dict(type='BatchMixup', alpha=1., num_classes=10, prob=1.)))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet50_cutmix.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='MultiLabelLinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0, use_soft=True)),
+    train_cfg=dict(
+        augments=dict(
+            type='BatchCutMix', alpha=1.0, num_classes=1000, prob=1.0)))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet50_label_smooth.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(
+            type='LabelSmoothLoss', label_smooth_val=0.1, loss_weight=1.0),
+        topk=(1, 5),
+    ))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnet50_mixup.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        style='pytorch'),
+    neck=dict(type='GlobalAveragePooling'),
+    head=dict(
+        type='MultiLabelLinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0, use_soft=True)),
+    train_cfg=dict(
+        augments=dict(type='BatchMixup', alpha=0.2, num_classes=1000,
+                      prob=1.)))

openmmlab_test/mmclassification-speed-benchmark/configs/_base_/models/resnetv1d101.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNetV1d',
+        depth=101,
+        num_stages=4,
+        out_indices=(3, ),
+        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-speed-benchmark/configs/_base_/models/resnetv1d152.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNetV1d',
+        depth=152,
+        num_stages=4,
+        out_indices=(3, ),
+        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-speed-benchmark/configs/_base_/models/resnetv1d50.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNetV1d',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        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-speed-benchmark/configs/_base_/models/resnext101_32x4d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=4,
+        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-speed-benchmark/configs/_base_/models/resnext101_32x8d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=8,
+        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-speed-benchmark/configs/_base_/models/resnext152_32x4d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNeXt',
+        depth=152,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=4,
+        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-speed-benchmark/configs/_base_/models/resnext50_32x4d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='ResNeXt',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=4,
+        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-speed-benchmark/configs/_base_/models/seresnet101.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SEResNet',
+        depth=101,
+        num_stages=4,
+        out_indices=(3, ),
+        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-speed-benchmark/configs/_base_/models/seresnet50.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SEResNet',
+        depth=50,
+        num_stages=4,
+        out_indices=(3, ),
+        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-speed-benchmark/configs/_base_/models/seresnext101_32x4d.py

+# model settings
+model = dict(
+    type='ImageClassifier',
+    backbone=dict(
+        type='SEResNeXt',
+        depth=101,
+        num_stages=4,
+        out_indices=(3, ),
+        groups=32,
+        width_per_group=4,
+        se_ratio=16,
+        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),
+    ))