Photo-Realistic-Super-Resoluton
Photo-Realistic-Super-Resoluton copied to clipboard
leehomyc
Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
The following is my mistake： t_folder=dataset/ model_folder=model/ th run_sr.lua { ntrain : inf beta1 : 0.9 name : "super_resolution" dataset : "folder" niter : 250 lr : 0.001 model_folder :...
Dear sir: This paper is interesting. Thanks for your implementation! I have some learning need now,can u share your trained model.if can ,I must be give you much thanks!
do you have tricks when you train the model.what is the problem? @leehomyc thanks
Hi~it's me again and this time I have met another problem =) The first time I run "t_folder=/xx/xx model_file=/xx/xx result_path=/xx/xx th run_test.lua" and it worked perfectly, which is nice, but...
Dear Sir, I train the code which you submited with ImageNet on epoch 3, but didn't have good performance. Would you please give some model to compare? Thank you very...
Dear Sir, Thanks so much to your work, we are trying some new idea based your work. We have seen that you have submitted Feb 10 a new picture result...
Hi~when I run ur code : "t_folder=xxx model_folder=xxx th run_sr.lua", and I got an error like this: hannraoi@hannraoi-B85M-DS3H:~/Photo-Realistic-Super-Resoluton-master$ t_folder=../MY_TRAIN_5/ model_folder=../MY_SRGAN_MODEL/ th run_sr.lua { model_folder : "../MY_SRGAN_MODEL/" lr : 0.001 batchSize...
train_folder=/Users/anthonyyuan/Desktop/src/ccc/Photo-Realistic-Super-Resoluton-master/train_folder model_folder=/Users/anthonyyuan/Desktop/src/ccc/Photo-Realistic-Super-Resoluton-master/your_save_folder th run_sr.lua { ntrain : inf beta1 : 0.9 name : "super_resolution" dataset : "folder" niter : 250 lr : 0.001 model_folder : "/Users/anthonyyuan/Desktop/src/ccc/Photo-Realistic-Super-Resoluton-master/your_save_folder" batchSize : 32 scale...
Thanks for this works. But I have questions. This work produced images are gray. How to change this work to produced SR color images? where source code I should modify?...