zhengbowei

hello, AKASH2907. Have you tested the author's CelebA model? I test the CelebA model using code "python test.py --checkpoints ./checkpoints/celeba --input ./examples/celeba /images --mask ./examples/celeba /masks --output ./checkpoints/results" and it...

Hello, have you noticed the code of gated convolution? In author's paper, there is no bias in its formula (i.e. sigmoid (Gatingy,x)), so the probability value of the missing area...

Hi,everybody! I want to test the pretrained model, but I do not know how to prepare "zip_root": "../datazip" and the setting of "-l", thank you for your answer!

Hi,everybody! I want to test the pretrained model, but I do not know how to prepare "zip_root": "../datazip" and the setting of "-l", thank you for your answer!

I am going to write a paper, which uses the code you implement. Can I put your website in the paper? thank you for your contribution. ---Original--- From: "Otenim"

hello, I use your code to train more than 1 million ImageNet images, but the effect is very poor, the inpainting effect is blurred, I would like to ask what...

hello, I training my project using Place2 datasets and the last option --arc is seted as places2. but on Training Phase 2 , the code reports error:"RuntimeError: size mismatch, m1:...

I deleted the latter two parameters and changed them to “def _pointwise_loss(self, lambd, lambd_optimized, input, target, discounting_mask, size_average=True, reduce=True): if target.requires_grad: d = lambd(input, target) d = d * discounting_mask...

when i run.py,this is problem,i dont know why, TypeError: l1_loss() takes from 2 to 3 positional arguments but 4 were given