tsing90

thanks for your reply, I'm looking forward to that implementation which I think is quite important for video quality.

what's the resolution of your input? usually the model tends to converge after 50 epochs

recently I had a similar issue (but I used batchnorm2d due to 1gpu), the possible reason may be due to small size of batch size. reference: https://discuss.pytorch.org/t/performance-highly-degraded-when-eval-is-activated-in-the-test-phase/3323

@lizhengwei1992 thanks for your reply, is there any special effect by deducting the mean value which makes the value falls into the range of [-0.5, 0.5]? btw, I think there...

looking forward to it

@protossw512 I know you may not be able to share your trained model as you explained authorization problem, but would you please share Joker's pretrained model? the link of his...

try to modify this line and see whether your problem can be solved: https://github.com/lizhengwei1992/Semantic_Human_Matting/blob/master/model/network.py#L39 bg, unsure, fg = torch.split(trimap_softmax, 1, dim=1)

just write their (images&masks) paths into that file . BTW, I have just released similar code, please refer to [my repo](https://github.com/tsing90/pytorch_semantic_human_matting.git)

@alialamiidrissi thanks for your solution, worked!