Issam H. Laradji

perfect, it is the `trainId` here: ``` https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/helpers/labels.py ```

Hi, thanks for your interest. 1. these are the class ids (obtained from https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/helpers/labels.py) , where class 13 corresponds to car. ``` labels = [ # name id trainId category...

Hi @ayush9198gupta sorry for the late reply, can you attach the custom images? I can test it and see where it is going wrong. Thanks

I think I found the bug. Changing line 132 in https://github.com/ncullen93/torchsample/blob/master/torchsample/transforms/affine_transforms.py from `return outputs if idx > 1 else outputs[0]` to `return outputs if idx >= 1 else outputs[0]` fixes...

I am getting the same issue. @huangzh13 is there an easy way to solve this?

where did you find `train_coarse_extra.py` ? @shahabty

Thanks a lot @gjy3035 that's very helpful! Would it be okay if you provide the hyperparameters you used with Cycada/SSIM? For example, - the lambda in the reconstruction loss; -...

Thanks a lot Junyu! I have sent you an email regarding this! my email is [email protected]

Thanks Junyu for your time!

Thanks for your reply! The implementation is the same as yours except that I used the `discriminator` as the classifier on top of "bert-base-cased" and removed the generator part, see...