Training Cityscapes - Changes in label_utils.py about deeplab-v2--resnet-101--tensorflow

[zhengyang-wang]

According to your link,

Please adapt the train IDs as appropriate for your approach.
Note that you might want to ignore labels with ID 255 during training.
Further note that the current train IDs are only a suggestion. You can use whatever you like.
Make sure to provide your results using the original IDs and not the training IDs.
Note that many IDs are ignored in evaluation and thus you never need to predict these!

Only 19 classes are used in evaluation. For self-evaluation, you need to ignore 255 and -1, which can easily be achieved by using the weights arguments. If you want to upload your results, you need to map "trainId" back to original "id".