Git Product home page Git Product logo

Comments (6)

ctallec avatar ctallec commented on July 19, 2024

Have you generated the dataset using the first command ? If not, first generate the dataset, then launch the second command. Otherwise, can you check that your datasets/carracing folder is not empty (beware, there's an s at the end of dataset, if you generated in dataset/carracing, this might be the cause of your issue) ?

from world-models.

Fairasname avatar Fairasname commented on July 19, 2024

I generated the dataset with the same command structure, but used 500 rollouts and 64 threads. And yes, I meant datasets with "s". So the path to my *.npz is "world-models/datasets/carracing/thread_x/rollout_y.npz", where x goes from 0 to 63, and y goes from 0 to 7.

Should I run the first command with 1000 rollouts?

Thanks!

from world-models.

ctallec avatar ctallec commented on July 19, 2024

Ok, this is probably the problem, you need to generate at least 601 rollouts ... That's a bit hardcoded, but basically we are using the first 600 rollout files to train and the rest to test. If you generate at least 800 rollouts (to have a decent test set) you should be fine.

from world-models.

Fairasname avatar Fairasname commented on July 19, 2024

Alright, I will try to get >601 and report back!

from world-models.

ctallec avatar ctallec commented on July 19, 2024

Small correction, we use the 600 lasts as test set, and the rest as train set.

from world-models.

Fairasname avatar Fairasname commented on July 19, 2024

The VAE is finally training, thanks!

from world-models.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.