What are the parameters involved to calculate the gradient during backpropagation?

[srishti-git1110 (Srishti Gureja)]

@Jeet

How does retain_graph=True matter here?

Refer this

@Jeet

What impact will it make if I remove the same because I could already get the gradients of all the parameters from the discriminator and the generator just by calling lossG.backward() after calling lossD.backward()?

No need to use retain_graph=True if that runs error free for you.
However, I’m anticipating it’ll not. retain_graph=True shall be required here as when you call lossG.backward() without it, you are basically trying to backward through the graph a second time after the saved tensors have already been freed which will produce an error.