mmaction2配置与测试

源码地址：https://github.com/open-mmlab/mmaction2

一、安装环境：

Ubuntu16.04+anaconda： Python3.7  pytorch1.5.0 cuda10.1

mmaction2 V0.13.0：https://github.com/open-mmlab/mmaction2/releases/tag/v0.13.0

mmcv-full==1.3.0

二、安装步骤

1. 创建虚拟环境：conda create -n py37 python=3.7
2. 激活环境
3. 安装torch==1.5.0（本文使用的是离线安装包）
4. 安装mmcv-ful（根据cuda和torch版本）： pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.5.0/index.html
5. 克隆mmaction2的仓库：git clone https://github.com/open-mmlab/mmaction2.git
6. 编译并安装：
   1. cd mmaction2
   2. pip install -r requirements/build.txt
   3. python setup.py develop
   4. 
   5. 进入Python后，导入mmcv和mmaction查看是否成功。

三、功能测试

1. cd demo
2. 查看demo.ipynb文件，本文将其转为py文件，方便测试。

3. from mmaction.apis import init_recognizer, inference_recognizer
   
   config_file = '../configs/recognition/tsn/tsn_r50_video_inference_1x1x3_100e_kinetics400_rgb.py'
   # download the checkpoint from model zoo and put it in `checkpoints/`
   checkpoint_file = '../checkpoints/tsn_r50_256p_1x1x8_100e_kinetics400_rgb.pth'
   model = init_recognizer(config_file, checkpoint_file, device='cpu')
   
   
   # test a single video and show the result:
   video = 'demo.mp4'
   label = 'label_map_k400.txt'
   results = inference_recognizer(model, video, label)
   
   # show the results
   for result in results:
       print(f'{result[0]}: ', result[1])

4. 根据加载的网络，下载模型（重命名了）：tsn_r50_256p_1x1x8_100e_kinetics400_rgb.pth（地址：https://github.com/open-mmlab/mmaction2/blob/master/configs/recognition/tsn/README.md）
5. 运行测试文件：python demo_test.py 
6. 得到识别结果
7. 
8. 待续