Git Product home page Git Product logo

Comments (2)

TimDettmers avatar TimDettmers commented on August 20, 2024

Thank you for your bug report!

It seems that the data on your disk is smaller than the data for a mini-batch, can that be? If you rerun the full data preprocessing pipeline, do you still have the error? What also might help is to change the seed that you pass into the StreamBatcher:

    train_batcher = StreamBatcher(Config.dataset, 'train', Config.batch_size, randomize=True, keys=input_keys, seed=88888888)

Furthermore, it would be helpful if you can replicate this bug with an existing dataset and configuration so that I can replicate it. With this I should be able to fix the bug quickly.

from conve.

TimDettmers avatar TimDettmers commented on August 20, 2024

There were some issues with the batch size in the evaluation procedure. The training and test batch size can now also be different. See 5feb358 for details.

I do not think this addresses the issue, but without further information, I am not able to replicate the error above.

from conve.

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.