syfbme

> > It's a data loader problem. > > When training domainA, there are 2 or 3 types of input: real_old_rgb, real_old_l, clean. In one batch, the number of old...

Maybe you should remove L1 loss: For L1 loss, model tends to generate colors which is the median number of your training space. By the way, what datasets do you...

Hi @MengXinChengXuYuan What's your --k_size value?

> I'm also looking forward to the training log > In my experiment, using the defaut model setting and my own dataset > When training model A, G_featD is very...

Hi @MengXinChengXuYuan What do you mean by "there are always other problems". There is no chessboard effects but other issue? If so, what is that?

The source code will resize image's height and weight to 16 multiple. So you can resize your image too using code like: `oh = int(round(oh / 16) * 16) ow...

According to the source code, remove "--X4" in "CUDA_VISIBLE_DEVICES=4,5,6,7 python3 train.py --X4 --input-dir SOURCE_PATH" will meet your expectation