chunyuwang / h36m-toolbox Goto Github PK

Hello before using this github, I need account but they are not allowing me for a few months.
So if any one can share account, it will be really helpful. Thanks.

Joseph.

hello, i wonder how the mask is genereted? is it got by some auto-label method?

Hi, you have supplied a great toolbox for processing h36m dataset.
I was wondering when using 3d coordinates of joints, why not use Poses_D3_positions, it seems this is the 3D coordinates in the world coordinates system and Poses_D3_positions_mono_universal seems to be "3D positions using the same limb lengths for all subjects "?

One of the video files for subject 11 has been fixed by the Human3.6M dataset maintainers (S11/Videos/Directions.54138969.mp4). So the md5 value should be changed from 13a24f30eb4e7cc505cbf80410c90ffe to
25c25250be8f75d7991dcbf74bb9d339

I do experiments in my own data but the R in pkl is different from my R. So how to generateed the inner parameters in camera data.pkl?

when running this code, there exists error FileNotFoundError: [WinError 2], and I don't know how to tackle it.
The detail message are as follows.
Traceback (most recent call last): File "video_to_images.py", line 40, in <module> call([ File "C:\Users\AppData\Local\Programs\Python\Python38\lib\subprocess.py", line 340, in call with Popen(*popenargs, **kwargs) as p: File "C:\Users\AppData\Local\Programs\Python\Python38\lib\subprocess.py", line 854, in __init__ self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Users\AppData\Local\Programs\Python\Python38\lib\subprocess.py", line 1307, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
Thank you very much!