Code Monkey home page Code Monkey logo

transformer-xl's People

Contributors

davidsvy avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

transformer-xl's Issues

Adapting Gated Transformer-XL implementation for non-NLP application?

First off, thank you so much for making your implementation open source. It's a huge help!

I'd like to use the Gated Transformer-XL implementation for a time series RL project of mine and would like to better understand what parts of the code are necessary to benefit from GTrXL. Specifically, I see the mem_list values, but didn't see that mentioned in this explanation of GTrXL. I'm still fairly new to ML, so I'm having a hard time understanding if it'd be okay to remove the mem_list part of the code. Or is it a core part of GTrXL?

I encounter error said OSError: Unable to open file (file signature not found)

Hello,

Thank you for sharing nice code. I finished training model using 'python train_music.py' command. I can check several checkpoint file was generated under 'checkpoints_music' folder.

Then, I tried to load one of them to generate music using 'python generate_music.py 1 /media/kimbring2/Steam/transformer-xl/checkpoints_music/optimizer1.npy' and met error of title.

I am not sure what is a problem. How can I solve that problem?

It is also good idea you share one of checkpoint of your side.

Thank you

ValueError: You are trying to load a weight file containing 12 layers into a model with 17 layers.

Hello, thank you so much for sharing your work in this space. This has been very helpful for me to grok the transformer-xl architecture beyond a simple toy app. I am trying to generate music using the steps provided in the readme however when attempting to run the generate_music.py file I'm getting the above error. I've tried searching throughout the repo to align these layers but I haven't been able to fix it. Any help in resolving this error is greatly appreciated.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.