FAQ: Generating Text with Deep Learning - Setup for Testing

This community-built FAQ covers the “Setup for Testing” exercise from the lesson “Generating Text with Deep Learning”.

Paths and Courses
This exercise can be found in the following Codecademy content:

Natural Language Processing

FAQs on the exercise Setup for Testing

There are currently no frequently asked questions associated with this exercise – that’s where you come in! You can contribute to this section by offering your own questions, answers, or clarifications on this exercise. Ask or answer a question by clicking reply (reply) below.

If you’ve had an “aha” moment about the concepts, formatting, syntax, or anything else with this exercise, consider sharing those insights! Teaching others and answering their questions is one of the best ways to learn and stay sharp.

Join the Discussion. Help a fellow learner on their journey.

Ask or answer a question about this exercise by clicking reply (reply) below!
You can also find further discussion and get answers to your questions over in Language Help.

Agree with a comment or answer? Like (like) to up-vote the contribution!

Need broader help or resources? Head to Language Help and Tips and Resources. If you are wanting feedback or inspiration for a project, check out Projects.

Looking for motivation to keep learning? Join our wider discussions in Community

Learn more about how to use this guide.

Found a bug? Report it online, or post in Bug Reporting

Have a question about your account or billing? Reach out to our customer support team!

None of the above? Find out where to ask other questions here!

Hi there, on part 5 onwards on this exercise I keep getting the following error:

E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: UNKNOWN ERROR (303)

I tried this on 2 different devices - one running Windows and one MacOS, the issue is there on both. I have Tensorflow installed, as well as the Cuda Toolkit. I ran out of ideas how to fix this and it’s really frustrating since I am almost at the end of the course.

I must say that I really like the way CC is teaching, but this course is somehow a mess. I think they should try to include much more visualisation. I’m really unsatisfied with my outcomes of the course. It was more like following instructions without having any clue what you are doing. I would prefer to go in really small steps (even if it takes twice the time) but get a good and knowledge-foundated set of new skills.

5 Likes

I’m still struggling to understand why would we need to redefine another model and not use the previous one?

I get that the previous model uses teacher forcing to speed up convergence & training, and this one doesn’t apply teacher forcing because we don’t know the “ground truth” of the text data is. But isn’t that the point of training the previous model? Please elaborate if anyone understands :slight_smile:

2 Likes