How to detach the generator in exercise 1 basic GANS

paulinpaloalto · March 5, 2024, 4:12am

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.

Topic		Replies	Views
GAN Course 1 Week 1 Assignment 1 Exercise Training Build Basic Generative Adversarial Networks week-1	4	673	November 19, 2022
Reason for detach not being called in generator loss function Build Basic Generative Adversarial Networks week-1	3	571	June 12, 2023
Detach() used in Assignment 4 Build Basic Generative Adversarial Networks week-4	5	598	November 13, 2022
Error Message Concerning Building the Training Code Build Basic Generative Adversarial Networks week-1	4	530	January 6, 2023
Why don't we detach the discriminator? Build Basic Generative Adversarial Networks week-2 , week-3	1	663	October 6, 2022