search

jhb86253817 / PIPNet

Efficient facial landmark detector
MIT License
405 stars 81 forks source link

Training with data where some points are missing from GT #46

Open zovathio opened 1 year ago

zovathio commented 1 year ago

Hello, thank you for your work. Is it possible to train the model with additional custom data, where not all the points have Ground Truth positions? For example, I want to train for 68 landmarks, but several images from my custom data are only annotated with 40 points and the remaining 28 points are not annotated.

jhb86253817 commented 1 year ago

Hi, it is possible, but you need to modify the code and add corresponding masks to loss calculation when certain landmark GTs are not available. And this requires some coding efforts.