CMU-Perceptual-Computing-Lab / caffe_rtpose

Realtime C++ code for multi-person pose estimation
Other
356 stars 207 forks source link

No Output for either image or Video test #7

Closed sguin1 closed 7 years ago

sguin1 commented 7 years ago

We compiled and executed the rtpose.bin (w/o making any changes) and for some reason, its not generating any output for either image or video file.

There is no error either. I have pasted the command and output below

Any idea why it is not generating json file?

Thanks

./build/examples/rtpose/rtpose.bin --image_dir /home/xxx/images/dnn/ --write_json output init done opengl support available E0109 19:00:27.296622 118173 rtpose.cpp:1538] rtcpm successfully finished. E0109 19:00:27.296898 118173 rtpose.cpp:1541] Total time: 4.61036 seconds. xxx@yyy:~/project/dnn/caffe_rtpose$ ls output/

sjobeek commented 7 years ago

I've experienced this same issue on an Ubuntu 16.04 machine using OpenCV 3.1 (GTX 1060).

Any ideas for approaches to debug the issue?

ZheC commented 7 years ago

This problem is mainly caused by openCV version difference as reported in https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose/issues/2 and https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose/issues/5. We made a commit in https://github.com/CMU-Perceptual-Computing-Lab/caffe_rtpose/commit/e1388f76e4f43c54e53b17907d1d8d119277893a Did you use the updated version? One way to debug the issue is to turn off the display and write out the result, e.g., ./build/examples/rtpose/rtpose.bin --video test.mp4 --no_display --write_frames output/ Please let us know if you meet the same problem

sjobeek commented 7 years ago

I ended up getting it working with opencv 2.4, but I may try again with 3.1 in the future.

Thanks for the suggestions.

gineshidalgo99 commented 7 years ago

Solution on #21.