I found there is an error when training

[Ixiaohuihuihui]

Hi, when I run this project, I found that sou_img = util.tensor2img(visuals['LQ'][2]) save_img = np.concatenate([sou_img, rlt_img, ill_img, gt_img, rlt_img3, rlt_img2], axis=0)

should be sou_img = util.tensor2img(visuals['LQ'])
save_img = np.concatenate([sou_img, rlt_img, ill_img, gt_img, rlt_img3, rlt_img2], axis=0)

Otherwise, their shapes will not match. The sou_img is [600, 400], not [600, 400, 3]. The error report is File "<array_function internals>", line 6, in concatenate ValueError: all the input arrays must have same number of dimensions, but the array at index 0 has 2 dimension(s) and the array at index 1 has 3 dimension.

[xiaogang00]

Thanks for your kind advice and we have fixed this.

[Ixiaohuihuihui]

And I have another question: how to test real images which did not contain gt images?

[xiaogang00]

Hello:
If there are no gt images, you should re-write the dataloader script which requires no gt images.