运行CUT时遇到的问题|contrastive-unpaired-translation

1.灰度图像

在使用自己的灰度模式图像训练时,应该把input_nc和output_nc改为1,运行时报错:

RuntimeError: Given groups=1, weight of size [64, 1, 7, 7], expected input[2, 3, 518, 518] to have 1 channels, but got 3 channels instead
(cut1) python train.py --dataroot ./datasets/oct --name oct_CUT --CUT_mode CUT

解决办法:

 

找到unaligned_dataset.py 的 line 67,将transform = get_transform(modified_opt)改为transform = get_transform(modified_opt,grayscale=(self.opt.input_nc == 1))