添加openmmlab测试用例

openmmlab_test/mmclassification-speed-benchmark/configs/resnext/resnext101_32x4d_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnext101_32x4d.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnext/resnext101_32x8d_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnext101_32x8d.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnext/resnext152_32x4d_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnext152_32x4d.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnext/resnext50_32x4d_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnext50_32x4d.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/seresnet/README.md

+# Squeeze-and-Excitation Networks
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+```latex
+@inproceedings{hu2018squeeze,
+  title={Squeeze-and-excitation networks},
+  author={Hu, Jie and Shen, Li and Sun, Gang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={7132--7141},
+  year={2018}
+}
+```
+
+## Results and models
+
+### ImageNet
+
+|         Model         | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
+|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
+| SE-ResNet-50          | 28.09     | 4.13     | 77.74 | 93.84 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/seresnet50/seresnet50_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet50_batch256_imagenet_20200804-ae206104.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet50_batch256_imagenet_20200708-657b3c36.log.json) |
+| SE-ResNet-101         | 49.33     | 7.86     | 78.26 | 94.07 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/seresnet101/seresnet101_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet101_batch256_imagenet_20200804-ba5b51d4.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet101_batch256_imagenet_20200708-038a4d04.log.json) |

openmmlab_test/mmclassification-speed-benchmark/configs/seresnet/metafile.yml

+Collections:
+  - Name: SEResNet
+    Metadata:
+      Training Data: ImageNet
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Epochs: 140
+      Batch Size: 256
+      Architecture:
+        - ResNet
+    Paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper.html
+    README: configs/seresnet/README.md
+
+Models:
+- Config: configs/seresnet50/seresnet50_b32x8_imagenet.py
+  In Collection: SEResNet
+  Metadata:
+    FLOPs: 4130000000
+    Parameters: 28090000
+  Name: seresnet50_b32x8_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 77.74
+      Top 5 Accuracy: 93.84
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet50_batch256_imagenet_20200804-ae206104.pth
+- Config: configs/seresnet101/seresnet101_b32x8_imagenet.py
+  In Collection: SEResNet
+  Metadata:
+    FLOPs: 7860000000
+    Parameters: 49330000
+  Name: seresnet101_b32x8_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 78.26
+      Top 5 Accuracy: 94.07
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet101_batch256_imagenet_20200804-ba5b51d4.pth

openmmlab_test/mmclassification-speed-benchmark/configs/seresnet/seresnet101_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/seresnet101.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/seresnet/seresnet50_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/seresnet50.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256_140e.py',
+    '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/seresnext/README.md

+# Squeeze-and-Excitation Networks
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+```latex
+@inproceedings{hu2018squeeze,
+  title={Squeeze-and-excitation networks},
+  author={Hu, Jie and Shen, Li and Sun, Gang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={7132--7141},
+  year={2018}
+}
+```

openmmlab_test/mmclassification-speed-benchmark/configs/seresnext/seresnext101_32x4d_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/seresnext101_32x4d.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/seresnext/seresnext50_32x4d_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/seresnext50_32x4d.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/shufflenet_v1/README.md

+# ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+```latex
+@inproceedings{zhang2018shufflenet,
+  title={Shufflenet: An extremely efficient convolutional neural network for mobile devices},
+  author={Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={6848--6856},
+  year={2018}
+}
+```
+
+## Results and models
+
+### ImageNet
+
+|         Model         | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
+|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
+| ShuffleNetV1 1.0x (group=3)   | 1.87      | 0.146    | 68.13 | 87.81 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/shufflenet_v1/shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/shufflenet_v1/shufflenet_v1_batch1024_imagenet_20200804-5d6cec73.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/shufflenet_v1/shufflenet_v1_batch1024_imagenet_20200804-5d6cec73.log.json) |

openmmlab_test/mmclassification-speed-benchmark/configs/shufflenet_v1/metafile.yml

+Collections:
+  - Name: Shufflenet V1
+    Metadata:
+      Training Data: ImageNet
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+        - No BN decay
+      Training Resources: 8x 1080 GPUs
+      Epochs: 300
+      Batch Size: 1024
+      Architecture:
+        - Shufflenet V1
+    Paper: https://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_ShuffleNet_An_Extremely_CVPR_2018_paper.html
+    README: configs/shufflenet_v1/README.md
+
+Models:
+- Config: configs/shufflenet_v1/shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py
+  In Collection: Shufflenet V1
+  Metadata:
+    FLOPs: 146000000
+    Parameters: 1870000
+  Name: shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 68.13
+      Top 5 Accuracy: 87.81
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/shufflenet_v1/shufflenet_v1_batch1024_imagenet_20200804-5d6cec73.pth

openmmlab_test/mmclassification-speed-benchmark/configs/shufflenet_v1/shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py

+_base_ = [
+    '../_base_/models/shufflenet_v1_1x.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize.py',
+    '../_base_/schedules/imagenet_bs1024_linearlr_bn_nowd.py',
+    '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/shufflenet_v2/README.md

+# Shufflenet v2: Practical guidelines for efficient cnn architecture design
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+```latex
+@inproceedings{ma2018shufflenet,
+  title={Shufflenet v2: Practical guidelines for efficient cnn architecture design},
+  author={Ma, Ningning and Zhang, Xiangyu and Zheng, Hai-Tao and Sun, Jian},
+  booktitle={Proceedings of the European conference on computer vision (ECCV)},
+  pages={116--131},
+  year={2018}
+}
+```
+
+## Results and models
+
+### ImageNet
+
+|         Model         | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
+|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
+| ShuffleNetV2 1.0x     | 2.28      | 0.149    | 69.55 | 88.92 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/shufflenet_v2/shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/shufflenet_v2/shufflenet_v2_batch1024_imagenet_20200812-5bf4721e.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/shufflenet_v2/shufflenet_v2_batch1024_imagenet_20200804-8860eec9.log.json) |

openmmlab_test/mmclassification-speed-benchmark/configs/shufflenet_v2/metafile.yml

+Collections:
+  - Name: Shufflenet V2
+    Metadata:
+      Training Data: ImageNet
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+        - No BN decay
+      Training Resources: 8x 1080 GPUs
+      Epochs: 300
+      Batch Size: 1024
+      Architecture:
+        - Shufflenet V2
+    Paper: https://openaccess.thecvf.com/content_ECCV_2018/papers/Ningning_Light-weight_CNN_Architecture_ECCV_2018_paper.pdf
+    README: configs/shufflenet_v2/README.md
+
+Models:
+- Config: configs/shufflenet_v2/shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py
+  In Collection: Shufflenet V2
+  Metadata:
+    FLOPs: 149000000
+    Parameters: 2280000
+  Name: shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 69.55
+      Top 5 Accuracy: 88.92
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/shufflenet_v2/shufflenet_v2_batch1024_imagenet_20200812-5bf4721e.pth

openmmlab_test/mmclassification-speed-benchmark/configs/shufflenet_v2/shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py

+_base_ = [
+    '../_base_/models/shufflenet_v2_1x.py',
+    '../_base_/datasets/imagenet_bs64_pil_resize.py',
+    '../_base_/schedules/imagenet_bs1024_linearlr_bn_nowd.py',
+    '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/speed_test/AlexNet.py

+_base_ = [
+    '../_base_/models/mobilenet_v2_1x.py', './datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256_epochstep.py',
+    '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/speed_test/datasets/imagenet_bs32.py

+# dataset settings
+dataset_type = 'DummyImageNet'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=128,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='accuracy')

openmmlab_test/mmclassification-speed-benchmark/configs/speed_test/datasets/imagenet_bs64.py

+# dataset settings
+dataset_type = 'DummyImageNet'
+img_norm_cfg = dict(
+    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+train_pipeline = [
+    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='ToTensor', keys=['gt_label']),
+    dict(type='Collect', keys=['img', 'gt_label'])
+]
+test_pipeline = [
+    dict(type='Normalize', **img_norm_cfg),
+    dict(type='ImageToTensor', keys=['img']),
+    dict(type='Collect', keys=['img'])
+]
+data = dict(
+    samples_per_gpu=128,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/train',
+        pipeline=train_pipeline),
+    val=dict(
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline),
+    test=dict(
+        # replace `data/val` with `data/test` for standard test
+        type=dataset_type,
+        data_prefix='data/imagenet/val',
+        ann_file='data/imagenet/meta/val.txt',
+        pipeline=test_pipeline))
+evaluation = dict(interval=1, metric='accuracy')