Regarding model selection during training

microsoft / MeshTransformer

Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"

https://arxiv.org/abs/2012.09760

MIT License

614 stars 95 forks source link

Closed tqtrunghnvn closed 3 years ago

tqtrunghnvn commented 3 years ago

Hi,

Delving into your code, I see that you were using PAmPJPE for selecting the better model.

Is there any intuition for that?

Thank you!

kevinlin311tw commented 3 years ago

PAmPJPE measures the errors of the reconstructed structure without regard to the scale and rigid pose. I mainly look at this metric.