Closed ybjeong530 closed 3 years ago
@ybjeong530 Would you mind share me your input video or images. I can help debug on my side.
@penincillin Hi. I'v changed the format to mp4 and reduce the resolution and then it worked. Thanks :)
@ybjeong530 Great news ! Then I am gonna close this issue. Please feel free to reopen it or create a new one in case you encounter with other problems.
Hi @penincillin. I have a similar problem. Reducing the resolution does help but I actually need the video to have a high resolution, otherwise, certain subtle movements might be missed.
Would you be willing to debug this if I share the video?
Just took a look and this turned out to be trivial. The max height of OpenGL rendering is set by default as 1080
. Modify this line to set a new max height accordingly.
Just took a look and this turned out to be trivial. The max height of OpenGL rendering is set by default as
1080
. Modify this line to set a new max height accordingly.
yup this solved it thanks!
Hi. I encountered the following ValueError while I was running the demo.demo_bodymocap.
~/Motion Capture/frankmocap-master$ python -m demo.demo_bodymocap --input_path ./sample_data/soccer.mov --out_dir ./mocap_output Loading Body Pose Estimator use_smplx False WARNING: You are using a SMPL model, with only 10 shape coefficients.
Wraning: Cannot resize the gl window Traceback (most recent call last): File "/home/vrcrew/anaconda3/envs/venv_frankmocap/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/vrcrew/anaconda3/envs/venv_frankmocap/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/vrcrew/Motion Capture/frankmocap-master/demo/demo_bodymocap.py", line 178, in
main()
File "/home/vrcrew/Motion Capture/frankmocap-master/demo/demo_bodymocap.py", line 174, in main
run_body_mocap(args, body_bbox_detector, body_mocap, visualizer)
File "/home/vrcrew/Motion Capture/frankmocap-master/demo/demo_bodymocap.py", line 123, in run_body_mocap
body_bbox_list = body_bbox_list)
File "/home/vrcrew/Motion Capture/frankmocap-master/renderer/visualizer.py", line 115, in visualize
res_img = np.concatenate((res_img, rend_img), axis=1)
File "<__array_function__ internals>", line 6, in concatenate
ValueError: all the input array dimensions for the concatenation axis must match exactly, but along dimension 0, the array at index 0 has size 2160 and the array at index 1 has size 1080
And I am not sure how I can resolve this issue. Do you have any idea how to solve this problem?
Best,