Hi!, I encountered the problem with model-not-learning with torch.cat((torch.tensor(x, dtype=torch.float32), torch.tensor(y, dtype=torch.float32)), 1) in combine_vectors method // Although it passes all the unit tests But it works well with “torch.cat((x.float(), y.float()), dim = 1)” Can someb…

[C1W4A_Build_a_Conditional_GAN # UNQ_C2] Model didn't learn with the wrong float casting in combine_vectors

paulinpaloalto December 22, 2023, 4:21pm 5

Yes, this is a known case in which the grader seems to use an older version of PyTorch. Here’s another thread about it.

Topic		Replies	Views
Trouble with two questions of Build a Conditional GAN Build Basic Generative Adversarial Networks week-4	2	566	April 1, 2022
C1W4 Build a Conditional GAN: def combine_vectors(x, y): Build Basic Generative Adversarial Networks week-4	1	805	November 21, 2022
C1W4A_Build_a_Conditional_GAN Assignment Grader Problem Build Basic Generative Adversarial Networks week-4	5	642	March 12, 2024
C1W4: Cell #7. Can't compile the student's code. Error: RuntimeError("Expected object of scalar type Long but got scalar type Float for sequence element 1 in sequence argument at position #1 'tensors'",) Build Basic Generative Adversarial Networks week-4	5	942	October 3, 2023
Programming Assignment: Conditional GAN "Try Again · 0/5 points earned" Build Basic Generative Adversarial Networks week-4	8	32	November 1, 2024