Yang

> I might need to rerun that experiment as it's hard to find it in my messy local files. I don't have much resource currently but I will do it...

Hi, there, I've written a short python file to process the youtube-vos folders into zips. You may refer to this for processing the Davis dataset. ```python import os import zipfile...

> > Hi, there, > > I've written a short python file to process the youtube-vos folders into zips. You may refer to this for processing the Davis dataset. >...

Hi there, Have you figured out the reason and trained the model successfully?

> I also found this problem. I'm try to solve it . Have you solved this problem? Thanks.

> and your reconstruct loss is rising, I believe you generate results better, I want to ask, reconstruct loss decreasing is the phenomenon of right? Hi, I am studying this...

> discriminators don't share the weights. Then, the filter in the optimizer of the discriminator is used for debugging, right? Thank you.

Hi, @hdjsjyl The lower the FID, the better the result. So your result seems good. I also trained this network for 50 epochs, and I get the FID score of...

> For anyone who needs a temporary solution, reverting back to commit `e28bdee` will allow pre-trained model to work. Thank you very much.

> @Aspen233 what is mod here? It's not defined anywhere so it will throw an error. I think you meant module. Yes, you are right. The "False" of the strict...