search

cameronfabbri / Underwater-Color-Correction

Using GANs to correct color distortion in underwater images.
291 stars 86 forks source link

issues about CycleGAN #3

Open IPNUISTlegal opened 6 years ago

IPNUISTlegal commented 6 years ago

i can't find that how long is it spent on CycleGAN training to generate distorted images in your paper. Does GTX 1080 have the ability to train CycleGAN?cause i found CycleGAN has nine residule_blocks! I am not sure about what CycleGAN input is? distortion images and clear images？Where do these distortion images come from? I just started learning GAN, thank you very much for replying！

Xiaodong-Bran commented 6 years ago

@IPNUISTlegal Hi, how is your learning going? I just read the paper. I think the authors wrote that they collected the images from ImageNet and visually classified the images into distorted images vs. non-distorted images.

IPNUISTlegal commented 6 years ago

@Xiaodong-Bran a little difficult，i am noob in python and deeplearning. to my best knowledge， distorted images and non-distorted images were trainded by CycleGAN.