I am testing a cGAN in keras / tensorflow, and after 1000 epochs I saved the model.
After a bit of time I restored
- the generator model + weights
- the discriminator model + weights
- the GAN weights (the model is recreated)
This is the resulting val_accuracy:
It is possible to see clearly that there is an immense drop in val_loss after restoring the model.
Could someone explain me why/what could have caused this situation ?