vkl123

> I read the training code. Method **supervised_training_iter** takes image, trimap and gt_matte. > > To generate trimap I wrote next code: > > ``` > def makeEdgeMask(mask, width): >...

Thank you for your response.  I used CUDA 10. 0 and pytorch1.7. Are there any problems?  ---Original--- From: "flybiubiu"

Hello, in my own training set, I encountered the same problem as you, when the number of iterations reached 1000, NaN situation appeared.Could you please tell me how you solved...