'A computational graph with a common node in PyTorch is it wasting memory?

This image shows my computational graph(Something like a DCGAN). And I first call backward on the last intermediate node of G1 with retain_graph=true. And then call backward on the last intermediate node of G2 with retain_graph=false.

My question is graph G1 still in memory?

I want to train my network in N epochs. How many G1 graphs are still in memory?

pytorch backpropagation

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution	Source

'A computational graph with a common node in PyTorch is it wasting memory?

Sources

Related Questions