添加openmmlab测试用例

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet18_b16x8_cifar10.py

+_base_ = [
+    '../_base_/models/resnet18_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet18_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnet18.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet34_b16x8_cifar10.py

+_base_ = [
+    '../_base_/models/resnet34_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet34_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnet34.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b16x8_cifar10.py

+_base_ = [
+    '../_base_/models/resnet50_cifar.py', '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b16x8_cifar100.py

+_base_ = [
+    '../_base_/models/resnet50_cifar.py',
+    '../_base_/datasets/cifar100_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]
+
+model = dict(head=dict(num_classes=100))
+
+optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0005)
+lr_config = dict(policy='step', step=[60, 120, 160], gamma=0.2)

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b16x8_cifar10_mixup.py

+_base_ = [
+    '../_base_/models/resnet50_cifar_mixup.py',
+    '../_base_/datasets/cifar10_bs16.py',
+    '../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b32x8_coslr_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256_coslr.py',
+    '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b32x8_cutmix_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50_cutmix.py',
+    '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b32x8_label_smooth_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50_label_smooth.py',
+    '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b32x8_mixup_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50_mixup.py',
+    '../_base_/datasets/imagenet_bs32.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b64x32_warmup_coslr_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py',
+    '../_base_/schedules/imagenet_bs2048_coslr.py',
+    '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b64x32_warmup_imagenet.py

+_base_ = [
+    '../_base_/models/resnet50.py', '../_base_/datasets/imagenet_bs64.py',
+    '../_base_/schedules/imagenet_bs2048.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet50_b64x32_warmup_label_smooth_imagenet.py

+_base_ = ['./resnet50_batch2048_warmup.py']
+model = dict(
+    head=dict(
+        type='LinearClsHead',
+        num_classes=1000,
+        in_channels=2048,
+        loss=dict(
+            type='LabelSmoothLoss',
+            loss_weight=1.0,
+            label_smooth_val=0.1,
+            num_classes=1000),
+    ))

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnetv1d101_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnetv1d101.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnetv1d152_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnetv1d152.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnetv1d50_b32x8_imagenet.py

+_base_ = [
+    '../_base_/models/resnetv1d50.py',
+    '../_base_/datasets/imagenet_bs32_pil_resize.py',
+    '../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
+]

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

+# Aggregated Residual Transformations for Deep Neural Networks
+
+## Introduction
+
+<!-- [ALGORITHM] -->
+
+```latex
+@inproceedings{xie2017aggregated,
+  title={Aggregated residual transformations for deep neural networks},
+  author={Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and Tu, Zhuowen and He, Kaiming},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={1492--1500},
+  year={2017}
+}
+```
+
+## Results and models
+
+### ImageNet
+
+|         Model         | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
+|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
+| ResNeXt-32x4d-50      | 25.03     | 4.27     | 77.90 | 93.66 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext50_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_b32x8_imagenet_20210429-56066e27.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_b32x8_imagenet_20210429-56066e27.log.json) |
+| ResNeXt-32x4d-101     | 44.18     | 8.03     | 78.71  | 94.12 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext101_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.log.json) |
+| ResNeXt-32x8d-101     | 88.79     | 16.5     | 79.23 | 94.58 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext101_32x8d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_b32x8_imagenet_20210506-23a247d5.log.json) |
+| ResNeXt-32x4d-152     | 59.95     | 11.8     | 78.93 | 94.41 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnext/resnext152_32x4d_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.log.json) |

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

+Collections:
+  - Name: ResNeXt
+    Metadata:
+      Training Data: ImageNet
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+      Training Resources: 8x V100 GPUs
+      Epochs: 100
+      Batch Size: 256
+      Architecture:
+        - ResNeXt
+    Paper: https://openaccess.thecvf.com/content_cvpr_2017/html/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.html
+    README: configs/resnext/README.md
+
+Models:
+- Config: configs/resnext/resnext50_32x4d_b32x8_imagenet.py
+  In Collection: ResNeXt
+  Metadata:
+    FLOPs: 4270000000
+    Parameters: 25030000
+  Name: resnext50_32x4d_b32x8_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 77.92
+      Top 5 Accuracy: 93.74
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_batch256_imagenet_20200708-c07adbb7.pth
+- Config: configs/resnext/resnext101_32x4d_b32x8_imagenet.py
+  In Collection: ResNeXt
+  Metadata:
+    FLOPs: 8030000000
+    Parameters: 44180000
+  Name: resnext101_32x4d_b32x8_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 78.7
+      Top 5 Accuracy: 94.34
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_batch256_imagenet_20200708-87f2d1c9.pth
+- Config: configs/resnext/resnext101_32x8d_b32x8_imagenet.py
+  In Collection: ResNeXt
+  Metadata:
+    FLOPs: 16500000000
+    Parameters: 88790000
+  Name: resnext101_32x8d_b32x8_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 79.22
+      Top 5 Accuracy: 94.52
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x8d_batch256_imagenet_20200708-1ec34aa7.pth
+- Config: configs/resnext/resnext152_32x4d_b32x8_imagenet.py
+  In Collection: ResNeXt
+  Metadata:
+    FLOPs: 11800000000
+    Parameters: 59950000
+  Name: resnext152_32x4d_b32x8_imagenet
+  Results:
+  - Dataset: ImageNet
+    Metrics:
+      Top 1 Accuracy: 79.06
+      Top 5 Accuracy: 94.47
+    Task: Image Classification
+  Weights: https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_batch256_imagenet_20200708-aab5034c.pth