I am having an issue in the function ‘get_gen_loss’ regarding the tensor dimensions. The issue is while I am using the same ‘disc’ function here (as the one I am using in the ‘get_disc_loss’, and it works properly there), the function here is resulting in [10, 64] tensors instead of [10,1]. Here is…

'get_gen_loss' issue with tensor dimension

paulinpaloalto June 4, 2023, 10:04pm 4

That’s great news! Here’s a thread from a while back that explains the detach issue in a bit more detail.

Topic		Replies	Views
GAN Course 1 Week 1 Assignment 1 Exercise Training Build Basic Generative Adversarial Networks week-1	4	661	November 19, 2022
Assertion Error for Get_Gen_Loss Build Basic Generative Adversarial Networks week-1	2	683	September 30, 2021
C1 w1 - unq_c6: Build Basic Generative Adversarial Networks week-1	3	474	June 29, 2023
Assertion Error in get_disc_loss Build Basic Generative Adversarial Networks week-1	6	608	December 29, 2022
C1W1_Your_First_GAN - UNQ_C6 - test_disc_reasonable(),test_disc_loss() Build Basic Generative Adversarial Networks week-1	5	555	August 12, 2023