context-encoder
context-encoder copied to clipboard
pathak22
[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
Hi，I'm trying some algorithms of image restoration. Can you provide a data set of Paris StreetView dataset?Thanks,My e-mail address is [email protected] Best， Chen
Any idea on how to implement this paper in pytorch would be of a great help.! And what do these line of the code do? How do I implement these...
@pathak22 How to remove the blocking artifact in the patch loction after reconstruction of image? What value to be set in this part of code? image_ctx[{{},{1},{1 + opt.fineSize/4 + opt.overlapPred,...
TypeError: RangeIndex(...) must be called with integers, map was passed for stop
In the file (train.lua and data.lua), why set torch.setnumthreads(1)? I am a little confused about the setting. Can I set multithreads, such as torch.setnumthreads(torch.getnumthreads())? Thanks for your time.
hi 1 I have a question about the loadSize, why should we use 129 not just 128? 2 why should we use overlapPred? 3 I have a image which fineSize...
Hi, From page 5: To customize GANs for this task, one could condition on the given context information; i.e., the mask Mˆ ⊙ x. However, conditional GANs don’t train easily...
Hi, First of all, great and interesting work. Congratulations! I have recently started my Ph.D. and your paper was one of the few interesting and helpful baselines for me to...
Hi, I find that if the opt.conditionAdv is true , then the input of the Adversarial discriminator net is 128x128, but if set it false, the input is changed to...
@pathak22 , hi. I tried the train_random.lua. and the result is as follow:  but I think it is only pseudorandom. for a given training, the random position is also...