Eromera/erfnet_pytorch

Image Normalization in Pre-processing for Cityscapes

Closed this issue · 2 comments

Hi,

I was trying to train the network on the Cityscapes dataset, and while going through the main training script, I could not find any Image Normalization code in the pre-processing part (here).

Does that mean we don't train the network on normalized image or am I missing something?

Thanks in advance!

Hi, yes you are right in the main code there is no normalization but in my own code i sometimes use it, you can add it in MyCoTransform function. Cheers

Thank you!