How to detach the generator in exercise 1 basic GANS

Course Q&A Generative Adversarial Networks (GANS) Build Basic Generative Adversarial Networks
1

This is regarding Coursera | Online Courses & Credentials From Top Educators. Join for Free | Coursera

It says “remember to detach the generator.” What does that mean? I don’t see a function call for “detach.”

2

You have to read the pytorch documentation. The detach() method is part of the definition of the Tensor class.

It was also discussed in the “Intro to PyTorch” assignment in Week 1 of GANs C1.

Here’s a thread which discusses why we do the detach in some cases and not in others.