Ignoring Invisible keypoints at inference time.

[myatthukyaw-edu]

I am running demo.py and making inference on testing videos. But the invisible keypoints locations are not that accurate. So, I want to ignore that keypoints and get only visible keypoints. I found IN_VIS_THRE parameter in config .yaml files. I changed that value and test it. But it didn't work.

[minmin518]

I have the same problem, have you solved it? thank you very much