Chevron Left
Back to Generating New Recipes using GPT-2

Learner Reviews & Feedback for Generating New Recipes using GPT-2 by Coursera Project Network

4.0
stars
45 ratings

About the Course

In this 2 hour long project, you will learn how to preprocess a text dataset comprising recipes, and split it into a training and validation set. You will learn how to use the HuggingFace library to fine-tune a deep, generative model, and specifically how to train such a model on Google Colab. Finally, you will learn how to use GPT-2 effectively to create realistic and unique recipes from lists of ingredients based on the aforementioned dataset. This project aims to teach you how to fine-tune a large-scale model, and the sheer magnitude of resources it takes for these models to learn. You will also learn about knowledge distillation and its efficacy in use cases such as this one. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....

Top reviews

RM

Apr 20, 2022

Really fun project with knowledgeable instructor. Highly recommended. :)

RR

Aug 24, 2020

Excellent hands-on experience on how to do use big Models like GPT-2

Filter by:

1 - 12 of 12 Reviews for Generating New Recipes using GPT-2

By Gencho Z

•

Sep 11, 2022

IMO, this project is totally useless. Only real code was data preprocessing, and this was pretty bad: implementing in 10-15 lines of python, what can be done in a single line in pandas (if you're going to use a library, might as well *use it*!)

By Alejandro N

•

Dec 29, 2021

Incomplete resources, a lot of people unable to finish the project because the lecturer does not include all the files needed to execute them! Very dissapointed with this project!

By Mayur S

•

Sep 24, 2020

One of my primary motivation to opt for this course was to understand how to fine-tune GPT2. Bit disappointed.

By Mohammad J

•

Mar 8, 2022

The resulting trained system tends to hallucinate a lot. For example the recipie includes ingridents that are not in the list, and some sometimes odd things are mixed like cream and lemon.

inaccurancies and hallucinate are not addressed in this course. But if you just want to understand the pipework and how to use google colab its not bad.

By Rossana M

•

Apr 20, 2022

Really fun project with knowledgeable instructor. Highly recommended. :)

By Raj R

•

Aug 25, 2020

Excellent hands-on experience on how to do use big Models like GPT-2

By Or K K

•

Jun 5, 2023

good

By Samar M

•

Aug 30, 2020

Thank you for your efforts but resources of this course not available once the course have completed!!

By CL S P

•

Jun 27, 2023

I had a lot of trouble with the virtual machine, but the instructor was really terrific.

By Jorge G

•

Feb 25, 2021

I do not recommend taking this type of course, take one and pass it, however after a few days I have tried to review the material, and my surprise is that it asks me to pay again to be able to review the material. Of course coursera gives me a small discount for having already paid it previously. It is very easy to download the videos and difficult to get hold of the material, but with ingenuity it is possible. Then I recommend uploading them to YouTube and keeping them private for when they want to consult (they avoid legal problems and can share with friends), then they can request a refund.

By Claudio A

•

Feb 18, 2023

The content was outdated and the instructor had a lot of syntax errors during the recordings.

By Priyank J

•

Apr 22, 2023

More focus on completion then explanation. Bit fast for learners. No reference code or reading material.