Dongyang Jin
Dongyang Jin
me too
Thank you for your answering. But the reason for this error is depth_x and depth_y is inf. And center_x and center_y is int.
Thank you for your answer. I try your method to remove inf, but this method will make a new error that in this picture: 
This is bug now, but I really don't know why this error occurs.  
thanks! ---Original--- From: ***@***.***> Date: Fri, May 27, 2022 22:54 PM To: ***@***.***>; Cc: "Jin ***@***.******@***.***>; Subject: Re: [KonstantinosAng/PyKinect2-Mapper-Functions] when using color_point_2_depth_point, sometime an error will occur (Issue #10) ok,...
Thanks a lot. I'll study it again.
> It seems I missed processing the skeleton pose, which is why it throws an error requiring two channels. Regarding silhouettes, as paddle-seg is recommended, do we have a recommended...
Deepgaitv2 uses 3D convolution to extract temporal features, which is more helpful in extracting temporal features in order than in random order.
You can check the compatibility between torch and cuda versions. Maybe it is helpful.