search

MarcoForte / FBA_Matting

Official repository for the paper F, B, Alpha Matting
MIT License
464 stars 95 forks source link

Radam not converging #46

Open ilyaskhanbey opened 3 years ago

ilyaskhanbey commented 3 years ago

Hello, thnak you for your great work I am trying to make the training code. So i started by making alpha loss, composition loss and regression loss, and i used radam optimizer RAdam(group_weight(net, 1e-5, 1e-5, 0.0001)) as you mentionned. To test the convegenve and evrithing is right in my code i took only 2 images with hair from adobe dataset and start training with these 2 images. But it's seems the loss is not converging, however when using the classical adam optimizer i got convergence in few iterations. the group_weight function seems dealing with parameters of the resnet encoder, i think i should use a pretrained resnet. could you share the pretrained resnet you used and if possible the code to load it in matting module. thanks in advance

EricLe-dev commented 2 years ago

@ilyaskhanbey I think I have encountered the same issue. Even after successfully loading the pretrained resnet. Have you solved the issue?