When I was running the training of crowdpose dataset, there were 'nan' and 'NaN or Inf found in input tensor' problems. I checked the data. This problem is caused by the disappearance or explosion of the gradient. After I adjusted the learning rate, this problem still can not be solved. Please help me.

HRNet / DEKR

This is an official implementation of our CVPR 2021 paper "Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression" (https://arxiv.org/abs/2104.02300)

MIT License

438 stars 76 forks source link

When I was running the training of crowdpose dataset, there were 'nan' and 'NaN or Inf found in input tensor' problems. I checked the data. This problem is caused by the disappearance or explosion of the gradient. After I adjusted the learning rate, this problem still can not be solved. Please help me. #28

Open LiPan123456789 opened 2 years ago

LiPan123456789 commented 2 years ago

Although it has this problem, it is still running normally. Is it right to continue running like this?

Gengzigang commented 2 years ago

Hi, I am sorry that I have not met this problem. You can reproduce our results in the paper using the cloned code without any change.