When i am training my dc-gan , my generator loss instead of decreasing or remaining constant, it continuously keeps on increasing , thereby i guess i am not able to get as clear images i should get?
Code link:https://colab.research.google.com/drive/1D0S254RUkfaqQwiEFebyon_5jzCH4cRi?usp=sharing
Increase in generator loss
Hey @saksham_thukral, in Generative adversarial networks , the discriminator and the generator play a kind of minimax game. Sometimes, the loss increases while sometimes the loss decreases. I have checked your code, it is absolutely correct and the images that are formed are also without much noise and the interpretation of digits is also possible. So if you want you can change the hyperparameters of the code to see some different results, else the output looks nice 
Hope this helps.
Happy Coding 
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.