Issue while running a sample video

Hi I was trying to run videopose.py using python 3.7 in virtual env using ubuntu 18.04. The command i used was as follows

python3.7 videopose.py --video ./outputs/kunkun_cut.mp4 which results in the following error

Traceback (most recent call last):
  File "videopose.py", line 174, in <module>
    inference_video('outputs/dance.mp4', 'alpha_pose')
  File "videopose.py", line 163, in inference_video
    main(args)
  File "videopose.py", line 67, in main
    split_video(args.viz_video)
  File "/sandbox/video-to-pose3D/common/utils.py", line 154, in split_video
    saved_path = os.path.dirname(save_path)
UnboundLocalError: local variable 'save_path' referenced before assignment

I am using hrnet as 2D detector .

[zh-plus]

As is said in my README

1. If you’re using PyCharm, mark ./joints_detectors/Alphapose, ./joints_detectors/hrnet and ./pose_trackers as source root.
2. If your’re trying to run in command line, add these paths mentioned above to the sys.path at the head of ./videopose.py

The bug is caused by the fact that these paths are not in your sys.path. I’ve updated my code to add them into sys.path manually. You can pull the project and try again.

[zh-plus]

May caused by the index of cuda devices:

os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"  # see issue #152
os.environ["CUDA_VISIBLE_DEVICES"] = "1"

I’m using multi-GPU machine in my environment. Try to change the value of os.environ["CUDA_VISIBLE_DEVICES"] = "1" into “0” in ./videopose.py