C4W1 - Ex3 - Incorrect third dimension of decoder output

Course Q&A Natural Language Processing NLP with Attention Models
1

Hi!

How can I troubleshoot the 3rd dimension of the logit tensor? Its shape is (64, 15, 256) when it should be (64, 15, 12000), but I’m not able to find my mistake in the code earlier. Has anybody has the same issue?

Thanks!

2

Finally a Dense layer. This one should have the same number of units as the size of the vocabulary since you expect it to compute the logits for every possible word in the vocabulary.

From the instructions

1 Like