I surely have no idea how to implement a mask in mask_exclude_positives especially for the second mask, seems I forgot to how to do so from other labs/courses.

These are the instructions given for you: To create the mask, you need to check if the cell is diagonal by computing tf.eye(batch_size) ==1, or if the non-diagonal cell is greater than the diagonal with (negative_zero_on_duplicate > tf.expand_dims(positive, 1) In other words, you just need a Pyt…

C3W3 Exercise 2 on creating masks

Course Q&A Natural Language Processing NLP with Sequence Models

arvyzukai February 12, 2024, 5:48am 2

Hi @Lujain_Andijani

Take a look at these calculations, it might suggest you what’s going on.

Cheers

Topic		Replies	Views
C3W3_Assignment - Duplicate Questions NLP with Sequence Models week-module-3 , assignment	4	62	April 19, 2025
Mask_exclude_positives NLP with Sequence Models week-module-4	3	758	September 12, 2022
TripletLossFn C3_W4 NLP with Sequence Models week-module-4	1	621	September 1, 2022
W3 unq_c3 issue NLP with Sequence Models week-module-4	1	546	September 20, 2022
NLP C3 W3 E4: Mask NLP with Sequence Models week-module-3	4	616	April 4, 2023

C3W3 Exercise 2 on creating masks

Related topics