Git Product home page Git Product logo

tfjs-mnist-workshop's Introduction

tfjs-mnist-workshop

This is an e2e TensorFlow workshop from model training using Keras API all the way to visualization using TensorFlow.js

User will need to complete exercises (.ipynb files) under py/ folder. Reference implementation could be found from /py/solutions folder.

User guide

  • Prepare environment
    • For Windows users, download and install ANaconda with either Python 2 or Python 3
    • For Linux/Mac users, you should already have Python installed
  • Install dependencies
    • pip install -r requirements.txt
    • If you're facing connectivity issues, please use pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
  • Visualize the initial model in browser
    • For Python 2 users, python -m SimpleHTTPServer
    • For Python 3 users, python -m http.server
    • Open localhost:8080 in your browser
    • Most of the predictions are wrong (red) because the model is doing random guess
  • Coding
    • Use jupyter notebook to complete an exercise and generate a model
  • Convert the mdoel to TF JS format
    • For windows users, convert.bat PATH_TO_THE_H5_FILE
    • For Linux/Mac users, convert.sh PATH_TO_THE_H5_FILE
  • Visualize the model in browser
    • For Python 2 users, python -m SimpleHTTPServer
    • For Python 3 users, python -m http.server
    • Open localhost:8080 in your browser
    • Most of the predictions should be correct (green) now

tfjs-mnist-workshop's People

Contributors

wangtz avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

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.