Closed ahmed-fau closed 6 years ago
True. Saving the state of the optimizer will not be difficult. Are you willing to do a pull-request with this? If not, I'll be happy to implement this myself :)
Unfortunately I am still not proficient with Github utilities and edit the scripts locally :( Sorry for that and thanks for your support.
Sorry for the late work. Saving the optimizer states as well as model states are now implemented.
Hi @deNsuh ,
It seems that resuming the training process is incomplete as the optimizers for both generator and discriminator networks are not being saved.
Best Regards