openpose的demo_offline测试问题

在进行运行ST-GCN Demo时遇到问题：
demo_offline调试：

python main.py demo_offline --video E:/Ruan/torch/st-gcn-master/st-gcn-master/resource/media/clean_and_jerk.mp4 --openpose E:/Ruan/openpose-master/openpose-master/build/python/openpose/Release

报如下错误：

(pytorch) E:\Ruan\torch\st-gcn-master\st-gcn-master>python main.py demo_offline --video E:/Ruan/torch/st-gcn-master/st-gcn-master/resource/media/clean_and_jerk.mp4 --openpose E:/Ruan/openpose-master/openpose-master/build/python/openpose/Release
Can not find Openpose Python API.
Traceback (most recent call last):
  File "main.py", line 33, in <module>
    p.start()
  File "E:\Ruan\torch\st-gcn-master\st-gcn-master\processor\demo_offline.py", line 31, in start
    video, data_numpy = self.pose_estimation()
TypeError: 'NoneType' object is not iterable

按照网上教程修改demo_offline文件后，报错依旧存在
本人修改如下：

def  pose_estimation(self):
        # load openpose python api
        if self.arg.openpose is not None:
            sys.path.append('{}/build/python/openpose/Release'.format(self.arg.openpose))
            os.environ['PATH']  = os.environ['PATH'] + ';' + 'E:/Ruan/openpose-master/openpose-master/build/x64/Release/;' + 'E:/Ruan/openpose-master/openpose-master/build/bin;'
            # sys.path.append('{}/python'.format(self.arg.openpose))
            # sys.path.append('{}/build/python'.format(self.arg.openpose))
        try:
            # from openpose import pyopenpose as op
            import pyopenpose as op
        except:
            print('Can not find Openpose Python API.')
            return

基于new bing的回答参考：
从错误信息来看，不能找到 Openpose Python API 。

您可以确认一下下面这些问题是否存在：

1. 确认 openpose 的路径是否正确。

2. 请检查你是否已经成功编译安装了 Openpose Python API。你可以在执行 python main.py demo_offline 命令前单独运行一个 Py 文件，测试你是否能够成功地导入 pyopenpose 模块。

• 这篇博客: ST-GCN源码运行完整版（含OpenPose编译安装）及常见问题中的 （2）demo_offline测试 部分也许能够解决你的问题, 你可以仔细阅读以下内容或跳转源博客中阅读:
  

• python main.py demo_offline --video E:/st-gcn/st-gcn-master/st-gcn-master/resource/media/clean_and_jerk.mp4 --openpose E:/st-gcn/openpose-master/openpose-master
  

  报错如下：
  错误1：
  video, data_numpy = self.pose_estimation() TypeError: ‘NoneType’ object is not iterable
  
  解决办法：
  更改demo_offline里的文件内容如下：

  将pose_estimation()函数更改如下
      def pose_estimation(self):
          # load openpose python api
          if self.arg.openpose is not None:
              sys.path.append('{}/build/python/openpose/Release'.format(self.arg.openpose))
              os.environ['PATH']  = os.environ['PATH'] + ';' + 'E:/st-gcn/openpose-master/openpose-master/build/x64/Release/;' + 'E:/st-gcn/openpose-master/openpose-master/build/bin;'
              # sys.path.append('{}/python'.format(self.arg.openpose))
              # sys.path.append('{}/build/python'.format(self.arg.openpose))
          try:
              # from openpose import pyopenpose as op
              import pyopenpose as op
          except:
              print('Can not find Openpose Python API.')
              return
  

  错误2：
  opWrapper.emplaceAndPop([datum])
  TypeError: emplaceAndPop(): incompatible function arguments. The following argument types are supported:
  1. (self: pyopenpose.WrapperPython, arg0: std::vector<std::shared_ptrop::Datum,std::allocator<std::shared_ptrop::Datum > >) -> bool

  Invoked with: <pyopenpose.WrapperPython object at 0x00000263AFEEA8F0>, [<pyopenpose.Datum object at 0x00000263AFF05F10>]
  
  解决办法：
  更改demo_offline里的文件内容如下：

  将opWrapper.emplaceAndPop([datum])更改如下：
  opWrapper.emplaceAndPop(op.VectorDatum([datum]))
  

  错误3：
  Check failed: error == cudaSuccess (2 vs. 0) out of memory
  
  解决办法：
  更改网络分辨率
  更改demo_offline里的文件内容如下：

  将params = dict(model_folder='./models', model_pose='COCO')更改如下：
  params = dict(model_folder='./models', model_pose='COCO', net_resolution='320x176')
  

  结果如下：
  

根据你的错误信息：

Traceback (most recent call last):
  File "main.py", line 33, in <module>
    p.start()
  File "E:\Ruan\torch\st-gcn-master\st-gcn-master\processor\demo_offline.py", line 31, in start
    video, data_numpy = self.pose_estimation()
TypeError: 'NoneType' object is not iterable

可以知道， self.pose_estimation()这个方法的返回是None；根据你贴出来的代码，发现这个方法在执行

import pyopenpose as op

的时候失败，所以抛出了exception。你先确认下你是不是安装了pyopenpose, 并确保这个包是可以被import的。