search

liyunsheng13 / BDL

MIT License
222 stars 30 forks source link

Train and eval size of Cycle-GAN #11

Closed sshaoshuai closed 5 years ago

sshaoshuai commented 5 years ago

Hi, Thanks for sharing the codes! I have a small question about the training of Cycle-GAN. For the training of Cycle-GAN, the input images are resized to 256x256 for the training. But the original size of image is 1024x564 (such as GTA), so after training of Cycle-GAN, how could you generate the transfered image of GTA in the original size (1024x564) ? If you directly feed the original GTA image to the model trained with 256x256, does it harm the transfered performance? Thanks very much and looking forward to your reply!

liyunsheng13 commented 5 years ago

What I did to train Cycle-GAN is to resize the image to 1024X or X1024 and then crop a patch with size 452*452. You can choose other size based on the GPU you use.

sshaoshuai commented 5 years ago

Ok, Thank you! I will try it.