Can only train one epoch, then training won't start anymore.

lucidrains / lightweight-gan

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

MIT License

1.62k stars 220 forks source link

Can only train one epoch, then training won't start anymore. #100

Open debagos opened 2 years ago

debagos commented 2 years ago

Hello :smiley:

I have two models (different datasets; different options) and with both I have the same problem: As soon as the model enters epoch 1, I can't continue training anymore. When I want to continue the training lightweight_gan exits without an error immediately, without even processing even one iteration.

When I delete/move the model_1.pt file I can start training again, but eh-

I use the latest version provided by pip. Help is appreciated!