Closed babyformula closed 4 years ago
After another review, I started to understand the trimap code part. But there still some code maybe typos or something:
Thanks
1, the pred_alpha is the output of network and whose value is 0~1. 2, +1. can avoid dividing by 0.
After read the code and implemented the training, I had some doubts about the alpha_loss calculation. According to the paper, the formulation'd relate to GT alpha and the Pred alpha, why was the trimap involved? And during the training, the alpha_loss was always staying at about 0.2, never got converged. Glad to talk with you.