Please check the Pascal VOC train_aug.

[Bala93]

I have changed this line "https://github.com/CVI-SZU/CLIMS/blob/master/segmentation/deeplabv2/libs/datasets/voc.py#L150' to the following to start the training

file_list = [id_.rstrip().split(" ")[0].split('/')[-1].split('.')[0] for id_ in file_list]

[Sierkinhane]

Hi, you can use the train_aug.txt at here. It looks like

2007_000032
2007_000039
2007_000063
2007_000068
2007_000121
2007_000170
2007_000241
2007_000243
2007_000250
2007_000256

[Bala93]

Ok, I think with this format, it should work. I downloaded from other source, where it had both img and mask.