Hi, I get a RuntimeError when the test_disc_reasonable() method calls disc_loss.backward(). The error trace is: RuntimeError Traceback (most recent call last) in 71 break 72 —> 73 test_disc_reasonable() 74 test_disc_loss() 75 print(“Success!”) in…

Interesting! My guess is that it must be something to do with how you are using “detach()” to avoid computing gradients on the generator. Did you perhaps apply detach also on the real images being fed to the discriminator? I tried a couple of experiments with that and could not reproduce the error t…

Hi, I have the same problem. I have no idea why it happens. noise = get_noise(n_samples=num_images, z_dim=z_dim, device=device) fake = gen(noise) fake_preds = disc(fake) fake_loss = criterion(fake_preds.detach(), torch.zeros_like(fake_preds)) real_preds= disc(real) real_loss = criterion(real_preds.…

One thing to try is not to detach the real predictions. The point is we only want to detach the fake predictions, because we don’t want to waste the cpu cycles to compute gradients on the generator. But we need the gradients for the discriminator, right? That’s because the point here is to train the…

Thank you for the advice, when I do not detach the real predictions, the specific error does not presents itself.

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

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

aray November 17, 2021, 7:52am 6

Here’s a thread on why we sometimes want to detach outputs.

Topic		Replies	Views
C1W1 test_gen_loss error : RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn Build Basic Generative Adversarial Networks week-module-1	2	1143	February 15, 2024
Assertion Error in get_disc_loss Build Basic Generative Adversarial Networks week-module-1	6	618	December 29, 2022
Week 1 Assignment: RuntimeError Build Basic Generative Adversarial Networks week-module-1	7	891	February 15, 2022
C1W1 UNQ_C6 Assertion Error without any information Build Basic Generative Adversarial Networks week-module-1	4	606	November 11, 2022
Attribute Error in test_disc_reasonable() Build Basic Generative Adversarial Networks week-module-1	3	580	March 6, 2023

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

Related topics