Open EoinKenny opened 1 year ago
Hello @EoinKenny , it could be the case when the model is trained on multiple GPUs. I trained the model on single GPU, so I didn't encounter any error. Please refine the code if you see it. Also, feel free to create a pull request!
Thanks for this repo!
It seems like the code doesn't save the models correctly when using multiple GPUs right? Like if I train on multiple GPUs but load on a single CPU, it won't work I think.
You have this
But I think you need self.G.module.state_dict() ?