# NLP with Sequence Models

**URL:** https://community.deeplearning.ai/c/course-q-a/natural-language-processing/nlp-course-3/195.md

[Latest](https://community.deeplearning.ai/latest.md) · [Categories](https://community.deeplearning.ai/categories.md) · [Tags](https://community.deeplearning.ai/tags.md)

---

## [About the NLP with Sequence Models category](https://community.deeplearning.ai/t/about-the-nlp-with-sequence-models-category/26692)

<div class="topic-metadata">

**Author:** [@Community-Team](https://community.deeplearning.ai/u/Community-Team)\
**Replies:** 0

</div>

Welcome to course 3 of Natural Langauge Processing Specialization. In this course, you will use dense and recurrent neural networks, LSTMs, GRUs, and Siamese networks in TensorFlow and Trax to perform advanced sentimen…

---

## [C3W3\_Assignment Grader: An unexpected error occurred](https://community.deeplearning.ai/t/c3w3-assignment-grader-an-unexpected-error-occurred/895119)

<div class="topic-metadata">

**Author:** [@rajjuvin](https://community.deeplearning.ai/u/rajjuvin)\
**Replies:** 15\
**Last updated:** [September 16, 2026, 6:55am UTC](https://community.deeplearning.ai/t/c3w3-assignment-grader-an-unexpected-error-occurred/895119 "2026-09-16T06:55:42Z")

</div>

Hi, I’m encountering an error when submitting the C3W3\_assignment for NLP Course 3: (NLP with Sequence Models) : Week 3: Siamese Networks. Assignment name: Question Duplicates. All the tests passed. In spite of this, w…

---

## [Definition of the closest diagonal](https://community.deeplearning.ai/t/definition-of-the-closest-diagonal/894256)

<div class="topic-metadata">

**Author:** [@Andy\_0416](https://community.deeplearning.ai/u/Andy_0416)\
**Replies:** 2\
**Last updated:** [August 1, 2026, 2:52pm UTC](https://community.deeplearning.ai/t/definition-of-the-closest-diagonal/894256 "2026-08-01T14:52:26Z")

</div>

The definition of the closest diagonal is “the highest number in the off-diagonals.” (C3, W3, Computing the Cost II, reading). What if the closest diagonal value is greater than the diagonal value?

---

## [C3W1\_Practice\_Assignment: Prepare Data Error](https://community.deeplearning.ai/t/c3w1-practice-assignment-prepare-data-error/891188)

<div class="topic-metadata">

**Author:** [@Poornima\_Dongre](https://community.deeplearning.ai/u/Poornima_Dongre)\
**Replies:** 3\
**Last updated:** [April 4, 2026, 4:25pm UTC](https://community.deeplearning.ai/t/c3w1-practice-assignment-prepare-data-error/891188 "2026-04-04T16:25:02Z")

</div>

Hi Team, I am getting error in the ‘prepare the data’ section of the C3W1\_Practice\_Assignment: Sentiment with Deep Neural Networks. All my previous tests are passes. Please help with the error.

---

## [Download slides of lecture W2](https://community.deeplearning.ai/t/download-slides-of-lecture-w2/285177)

<div class="topic-metadata">

**Author:** [@moustafa\_fathy](https://community.deeplearning.ai/u/moustafa_fathy)\
**Replies:** 2\
**Last updated:** [January 25, 2026, 1:32pm UTC](https://community.deeplearning.ai/t/download-slides-of-lecture-w2/285177 "2026-01-25T13:32:15Z")

</div>

How to download slides ?

---

## [Grader error: grading feedback not found](https://community.deeplearning.ai/t/grader-error-grading-feedback-not-found/98877)

<div class="topic-metadata">

**Author:** [@Dirk\_Bahle](https://community.deeplearning.ai/u/Dirk_Bahle)\
**Replies:** 9\
**Last updated:** [December 29, 2025, 7:42pm UTC](https://community.deeplearning.ai/t/grader-error-grading-feedback-not-found/98877 "2025-12-29T19:42:14Z")

</div>

I cannot get my week 4 assignment for Question Duplicates processed because I keep getting the above error. I have ensured there no global variable definitions and the notebook is otherwise processing fine but is not pro…

---

## [Some courses are missing from dl-ai-learning platform](https://community.deeplearning.ai/t/some-courses-are-missing-from-dl-ai-learning-platform/884285)

<div class="topic-metadata">

**Author:** [@ratatoe](https://community.deeplearning.ai/u/ratatoe)\
**Replies:** 1\
**Last updated:** [December 1, 2025, 6:32pm UTC](https://community.deeplearning.ai/t/some-courses-are-missing-from-dl-ai-learning-platform/884285 "2025-12-01T18:32:58Z")

</div>

I noticed that several well-known DeepLearning.AI offerings—such as the NLP Specialization, GAN Specialization, and the TensorFlow Specialization series—do not appear on the new integrated deeplearning.ai learning platfo…

---

## [C3W1 Assignment - perplexity](https://community.deeplearning.ai/t/c3w1-assignment-perplexity/883806)

<div class="topic-metadata">

**Author:** [@dsong99](https://community.deeplearning.ai/u/dsong99)\
**Replies:** 4\
**Last updated:** [November 23, 2025, 3:30am UTC](https://community.deeplearning.ai/t/c3w1-assignment-perplexity/883806 "2025-11-23T03:30:05Z")

</div>

I am having trouble in C3W1 Assignment - perplexity calculation. I passed unit test first 8 examples, but fail 9-th example. I see the preds dimension is 4 while tartget is 3: preds.shape (2, 1, 7, 3) target.shape (2, 7…

---

## [C3W1 perplexity calculation](https://community.deeplearning.ai/t/c3w1-perplexity-calculation/587989)

<div class="topic-metadata">

**Author:** [@Dennis\_Sinitsky](https://community.deeplearning.ai/u/Dennis_Sinitsky)\
**Replies:** 4\
**Last updated:** [November 22, 2025, 6:36pm UTC](https://community.deeplearning.ai/t/c3w1-perplexity-calculation/587989 "2025-11-22T18:36:38Z")

</div>

I am passing first 8 examples in testing, but fail 9-th example. This is printout of some dimensions and variables, followed by error message. In particular, I am failing when preds shape is 4-dimentional tensor while 1-…

---

## [C3W3 Assignment: TripletLoss - Getting exactly half/quarter of expected values](https://community.deeplearning.ai/t/c3w3-assignment-tripletloss-getting-exactly-half-quarter-of-expected-values/883519)

<div class="topic-metadata">

**Author:** [@ziad\_agamy](https://community.deeplearning.ai/u/ziad_agamy)\
**Replies:** 1\
**Last updated:** [November 17, 2025, 3:42pm UTC](https://community.deeplearning.ai/t/c3w3-assignment-tripletloss-getting-exactly-half-quarter-of-expected-values/883519 "2025-11-17T15:42:09Z")

</div>

Hi everyone, I’m stuck on the TripletLoss implementation for C3W3 (Siamese Networks) My implementation follows the assignment exactly: \*\*codes removed as it is part of the grade function codes and which assess your su…

---

## [Understanding Sentinels in C4W3\_Assignment](https://community.deeplearning.ai/t/understanding-sentinels-in-c4w3-assignment/883088)

<div class="topic-metadata">

**Author:** [@chartechaccountant](https://community.deeplearning.ai/u/chartechaccountant)\
**Replies:** 3\
**Last updated:** [November 11, 2025, 9:00pm UTC](https://community.deeplearning.ai/t/understanding-sentinels-in-c4w3-assignment/883088 "2025-11-11T21:00:39Z")

</div>

/notebooks/C4W3\_Assignment.ipynb From what I understand, sentinels are used in the decoder of the T5 as targets. They are like placeholders. Lets assume vocab size is 32,000. Lets assume I=2, Love =3, learning=4, and …

---

## [C3W1 - Confused with Embedding and Mean Layers](https://community.deeplearning.ai/t/c3w1-confused-with-embedding-and-mean-layers/882986)

<div class="topic-metadata">

**Author:** [@dsong99](https://community.deeplearning.ai/u/dsong99)\
**Replies:** 3\
**Last updated:** [November 10, 2025, 4:39am UTC](https://community.deeplearning.ai/t/c3w1-confused-with-embedding-and-mean-layers/882986 "2025-11-10T04:39:19Z")

</div>

I am confused with NLP C3W1 introduction, I don’t understand how embedding for each word has multiple dimensions and needs to take a mean on them (Per discussion on https://community.deeplearning.ai/t/trax-mean-layer/230…

---

## [C3W1\_Practice\_Assignment - Exercise 8 - graded\_very\_positive\_tweet](https://community.deeplearning.ai/t/c3w1-practice-assignment-exercise-8-graded-very-positive-tweet/518954)

<div class="topic-metadata">

**Author:** [@lukmanaj](https://community.deeplearning.ai/u/lukmanaj)\
**Replies:** 3\
**Last updated:** [October 31, 2025, 3:25pm UTC](https://community.deeplearning.ai/t/c3w1-practice-assignment-exercise-8-graded-very-positive-tweet/518954 "2025-10-31T15:25:38Z")

</div>

It is quite exciting to try out using tensorflow after using trax previously. Regarding this particular exercise, I am finding it difficult to get a tweet that has the required positive score. Instructions: For your …

---

## [Deleted the programming assignment workbook by mistake](https://community.deeplearning.ai/t/deleted-the-programming-assignment-workbook-by-mistake/881862)

<div class="topic-metadata">

**Author:** [@chartechaccountant](https://community.deeplearning.ai/u/chartechaccountant)\
**Replies:** 4\
**Last updated:** [October 21, 2025, 3:48pm UTC](https://community.deeplearning.ai/t/deleted-the-programming-assignment-workbook-by-mistake/881862 "2025-10-21T15:48:06Z")

</div>

When creating a post, please add: Week # must be added in the tags option of the post. Link to the classroom item you are referring to: Description (include relevant info but please do not post solution code or your en…

---

## [NLP C3\_W2: Section 4.3 Wrong values comparison](https://community.deeplearning.ai/t/nlp-c3-w2-section-4-3-wrong-values-comparison/881609)

<div class="topic-metadata">

**Author:** [@khteh](https://community.deeplearning.ai/u/khteh)\
**Replies:** 1\
**Last updated:** [October 17, 2025, 12:54pm UTC](https://community.deeplearning.ai/t/nlp-c3-w2-section-4-3-wrong-values-comparison/881609 "2025-10-17T12:54:03Z")

</div>

It should be np.allclose(pred\_x, pred\_x\_padded\[:,:3,:\])

---

## [\`log\_softmax\` in Dense layer + \`from\_logits=True\` in cross-entropy loss](https://community.deeplearning.ai/t/log-softmax-in-dense-layer-from-logits-true-in-cross-entropy-loss/881558)

<div class="topic-metadata">

**Author:** [@khteh](https://community.deeplearning.ai/u/khteh)\
**Replies:** 2\
**Last updated:** [October 16, 2025, 4:05pm UTC](https://community.deeplearning.ai/t/log-softmax-in-dense-layer-from-logits-true-in-cross-entropy-loss/881558 "2025-10-16T16:05:52Z")

</div>

I see NLP course uses for quite a number of times the combination of log\_softmax in the Dense layer with from\_logits=True in the cross-entropy loss function in order to have a stable computation of the softmax. How does …

---

## [NLP C3\_W3: classify() hits shape error by the grader](https://community.deeplearning.ai/t/nlp-c3-w3-classify-hits-shape-error-by-the-grader/881461)

<div class="topic-metadata">

**Author:** [@khteh](https://community.deeplearning.ai/u/khteh)\
**Replies:** 7\
**Last updated:** [October 16, 2025, 12:29pm UTC](https://community.deeplearning.ai/t/nlp-c3-w3-classify-hits-shape-error-by-the-grader/881461 "2025-10-16T12:29:55Z")

</div>

The classify() function in the assignment notebook of this course has the following snippet of code: \_, n\_feat = ?? What’s that and how to make use of it? I comment it out and it passes w3\_unittest.test\_classify(classi…

---

## [NLP C3\_W2: model.fit crashes](https://community.deeplearning.ai/t/nlp-c3-w2-model-fit-crashes/881399)

<div class="topic-metadata">

**Author:** [@khteh](https://community.deeplearning.ai/u/khteh)\
**Replies:** 4\
**Last updated:** [October 15, 2025, 3:28am UTC](https://community.deeplearning.ai/t/nlp-c3-w2-model-fit-crashes/881399 "2025-10-15T03:28:11Z")

</div>

model.fit(train\_dataset.batch(BATCH\_SIZE), validation\_data = val\_dataset.batch(BATCH\_SIZE), shuffle=True, epochs = 2) crashes. restarting the kernel doesn’t help.

---

## [NLP C3W1 Assignment about log perplexity](https://community.deeplearning.ai/t/nlp-c3w1-assignment-about-log-perplexity/870190)

<div class="topic-metadata">

**Author:** [@mejiroalbon](https://community.deeplearning.ai/u/mejiroalbon)\
**Replies:** 1\
**Last updated:** [August 10, 2025, 4:32am UTC](https://community.deeplearning.ai/t/nlp-c3w1-assignment-about-log-perplexity/870190 "2025-08-10T04:32:52Z")

</div>

Function failed in example 1. Review the axis variable you are passing. It must be set to the last axis, but must be generalizable. What is the index that represents the last axis in general? The testing code block gave…

---

## [Welcome to Natural Language Processing with Sequence Models](https://community.deeplearning.ai/t/welcome-to-natural-language-processing-with-sequence-models/859499)

<div class="topic-metadata">

**Author:** [@suusuu938](https://community.deeplearning.ai/u/suusuu938)\
**Replies:** 5\
**Last updated:** [July 25, 2025, 8:34am UTC](https://community.deeplearning.ai/t/welcome-to-natural-language-processing-with-sequence-models/859499 "2025-07-25T08:34:38Z")

</div>

Cannot import available module in assignment

---

## [How to upload my certificates to credly](https://community.deeplearning.ai/t/how-to-upload-my-certificates-to-credly/845356)

<div class="topic-metadata">

**Author:** [@mahder](https://community.deeplearning.ai/u/mahder)\
**Replies:** 1\
**Last updated:** [July 7, 2025, 5:18am UTC](https://community.deeplearning.ai/t/how-to-upload-my-certificates-to-credly/845356 "2025-07-07T05:18:20Z")

</div>

how to upload my certificates to credly

---

## [C3W1-Assignment Submission error](https://community.deeplearning.ai/t/c3w1-assignment-submission-error/840433)

<div class="topic-metadata">

**Author:** [@Satyabrat\_2005](https://community.deeplearning.ai/u/Satyabrat_2005)\
**Replies:** 10\
**Last updated:** [July 6, 2025, 12:03am UTC](https://community.deeplearning.ai/t/c3w1-assignment-submission-error/840433 "2025-07-06T00:03:03Z")

</div>

\#C3W1- Assignment. There was a problem on submission of assignment “There was a problem compiling the code from your notebook. Details: No module named ‘w1\_unittest’”

---

## [NLP pour la traduction du francais dans les langues africaine](https://community.deeplearning.ai/t/nlp-pour-la-traduction-du-francais-dans-les-langues-africaine/837298)

<div class="topic-metadata">

**Author:** [@mario\_niki](https://community.deeplearning.ai/u/mario_niki)\
**Replies:** 4\
**Last updated:** [June 21, 2025, 5:38pm UTC](https://community.deeplearning.ai/t/nlp-pour-la-traduction-du-francais-dans-les-langues-africaine/837298 "2025-06-21T17:38:32Z")

</div>

je suis un jeune burkinabé expert en IA et je veux concevoir un modèle capable de traduire le francais et l’anglais en la langue mooré je suis du Burkina faso quelqu’un peut me donner des piste ?

---

## [Grader Error: "name 'text\_vectorization' is not defined" in Week 3 Programming Assignment](https://community.deeplearning.ai/t/grader-error-name-text-vectorization-is-not-defined-in-week-3-programming-assignment/817156)

<div class="topic-metadata">

**Author:** [@stiansd17](https://community.deeplearning.ai/u/stiansd17)\
**Replies:** 6\
**Last updated:** [June 15, 2025, 10:27am UTC](https://community.deeplearning.ai/t/grader-error-name-text-vectorization-is-not-defined-in-week-3-programming-assignment/817156 "2025-06-15T10:27:16Z")

</div>

Hi, I’m encountering a persistent error when submitting the Week 3 programming assignment (Question Duplicates) in the NLP Sequence Models course. The grader returns the following error message: There was an error grad…

---

## [NLP course Sequence Models Week 3 final programming assignment doubt](https://community.deeplearning.ai/t/nlp-course-sequence-models-week-3-final-programming-assignment-doubt/629224)

<div class="topic-metadata">

**Author:** [@Rashmi11](https://community.deeplearning.ai/u/Rashmi11)\
**Replies:** 9\
**Last updated:** [June 15, 2025, 10:05am UTC](https://community.deeplearning.ai/t/nlp-course-sequence-models-week-3-final-programming-assignment-doubt/629224 "2025-06-15T10:05:51Z")

</div>

Topic: Hard Negative Mining (Exercise 2) Images removed by moderator as the post creator posted codes from grader cell and did not follow code of conduct Loss value I am getting is 2.4 but the expected value is 0.7 …

---

## [NLP with Sequence Models W3 in the Final Coding Assignment](https://community.deeplearning.ai/t/nlp-with-sequence-models-w3-in-the-final-coding-assignment/833640)

<div class="topic-metadata">

**Author:** [@Sambhav0000](https://community.deeplearning.ai/u/Sambhav0000)\
**Replies:** 1\
**Last updated:** [June 15, 2025, 10:22am UTC](https://community.deeplearning.ai/t/nlp-with-sequence-models-w3-in-the-final-coding-assignment/833640 "2025-06-15T10:22:06Z")

</div>

Topic: In the second excercise of w3 final coding assignment , i am getting loss 2.2 but the excepted value is 0.7 , and therefore my test casses are failing , please help me fix it

---

## [Error in trying to fit the model](https://community.deeplearning.ai/t/error-in-trying-to-fit-the-model/832917)

<div class="topic-metadata">

**Author:** [@ronsperber](https://community.deeplearning.ai/u/ronsperber)\
**Replies:** 1\
**Last updated:** [June 13, 2025, 6:58pm UTC](https://community.deeplearning.ai/t/error-in-trying-to-fit-the-model/832917 "2025-06-13T18:58:22Z")

</div>

When I try to fit the model I get a long error, but it seems like the relevant info is the last “UNIMPLEMENTED: Cast string to float is not supported” If I comment out the model.fit, but leave model.compile, t…

---

## [Can someone explain why an RNN is depicted like this (Cost Function)?](https://community.deeplearning.ai/t/can-someone-explain-why-an-rnn-is-depicted-like-this-cost-function/821149)

<div class="topic-metadata">

**Author:** [@saidubbaka](https://community.deeplearning.ai/u/saidubbaka)\
**Replies:** 1\
**Last updated:** [May 25, 2025, 7:09am UTC](https://community.deeplearning.ai/t/can-someone-explain-why-an-rnn-is-depicted-like-this-cost-function/821149 "2025-05-25T07:09:54Z")

</div>

Can someone explain why an RNN is depicted like this in the Cost Function for RNNs lecture? I thought at each timestep only one input is send to the RNN-cell that it’s mapped to (in many to many RNNs). This picture remin…

---

## [NLP\_C3W1\_Practice Assignment - issue with build\_vocabulary](https://community.deeplearning.ai/t/nlp-c3w1-practice-assignment-issue-with-build-vocabulary/818243)

<div class="topic-metadata">

**Author:** [@lisestdenis](https://community.deeplearning.ai/u/lisestdenis)\
**Replies:** 4\
**Last updated:** [May 22, 2025, 1:27am UTC](https://community.deeplearning.ai/t/nlp-c3w1-practice-assignment-issue-with-build-vocabulary/818243 "2025-05-22T01:27:38Z")

</div>

I am appear to be doing something wrong with the build\_vocabulary. My unit test passed but the grader is giving me the following error: Failed test case: vocab does not contain all words. Expected: 9535, but got: 95…

---

## [Certificate Not Available After Course Completion – "Sequence Models](https://community.deeplearning.ai/t/certificate-not-available-after-course-completion-sequence-models/816554)

<div class="topic-metadata">

**Author:** [@Sam39](https://community.deeplearning.ai/u/Sam39)\
**Replies:** 2\
**Last updated:** [May 16, 2025, 10:20pm UTC](https://community.deeplearning.ai/t/certificate-not-available-after-course-completion-sequence-models/816554 "2025-05-16T22:20:53Z")

</div>

Dear Coursera Support Team, I hope this message finds you well. I have recently completed the course “Sequence Models” by DeepLearning.AI, and the platform confirms that I have completed all weeks, videos, assignments,…

[Next page](https://community.deeplearning.ai/c/course-q-a/natural-language-processing/nlp-course-3/195.md?page=1)
