While plotting both dicriminator and generator loss in GANs , what inference or conclusions can we make out of both the losses?
Since it is a fluctating plot , how to decide when should we stop our training or what is optimal no of iterations ?
Loss Curve in GANs
hey @gautam75,
The loss plots shows the learning nature of our model , whether it be generator part or discriminator.
So , more the fluctuations , lesser the model is understanding and learning.
Hence , you need to get a smooth slop to get better results.
Now , coming to how to get that.
Try changing model architecture or work on parameters like learning rate ( lowering it ), optimizer etc.
I hope this helps.
Thank You 
.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.