does not run about espgan HOT 5 CLOSED

Hi, thanks for your question.

There are not bugs. First, you could use zip instead of itertools.izip (maybe you are asking this, it depends on your python version); Second, please make sure your dataset size can be divided exactly by the batch size .

Hope the above is helpful for you.

from espgan.

No, you misunderstood the usage of zip. The zip() function will only iterate over the smallest list passed. If given lists of different lengths, the resulting combination will only be as long as the smallest list passed.

from espgan.

Maybe you should check your data loader. You could check the data preparation in https://github.com/LynnHo/CycleGAN-Tensorflow-2/tree/v1. Or you could write your own data loader.

from espgan.

By the way, maybe you could check the length of "itertools.izip(a_loader, b_loader)". Also, the length of a_loader and b_loader.

I remember the training data size is 12,936, so the length of "itertools.izip(a_loader, b_loader)" should be 12936. In this case, the maximum of i is 12,935.

You could check your dataset loader code step by step. Good luck!

from espgan.

First, I have released this code for about 11 months. You are the first one to find a "bug". I think you could check your code step by step. We didn't meet your issue, how can we find a "bug". I don't think the bug is a friendly word for someone who releases her/his codes (but the issue is welcome).
Moreover, I mean you need to check your data path preparation. You need to make sure you put images into the right path. Again, check the path structure in https://github.com/LynnHo/CycleGAN-Tensorflow-2/tree/v1.
Last, I have given you some possible ways to find out the issue.

from espgan.