Giter Club home page Giter Club logo

visualml's Introduction


Visual Machine Learning

Visual Machine Learning contains a set of Machine Learning and Deep Learning interactive visualisation demos for developing intuition. These demos are developed using TensorFlow.js and can be executed directly in your browser. This project is an extension of ML examples from tfjs-examples. We implement new demos, as well as, add additional features into the ones that already existed in TFJS.

Some examples may require web-gl enabled browsers and viewers may experience latency during executing the demos based on the device.

Overview of Demos

Example name Demo link Input data type Task type Model type Training Inference
ANN ๐Ÿ”— Iris Dataset View NN architecture, View Confusion Matrix Multilayer perceptron Browser Browser
Autoencoder ๐Ÿ”— MNIST dataset Visualising Latent Space Autoencoder Browser Browser
Logistic Regression ๐Ÿ”— Various 2D data Visualising Decision Boundary Logistic Regression Browser Browser
MNIST-CNN ๐Ÿ”— MNIST Visualising Activations CNN Browser Browser
PCA ๐Ÿ”— Various Visualising Principal Components & projected dimensions PCA Browser Browser
SVM ๐Ÿ”— 2D Dataset Visualising Support Vectors and Kernels SMO Browser Browser
Neural Style Transfer ๐Ÿ”— Image Data Visualising Style Transfer using MobileNet Style Transfer Browser Browser
Vanishing Gradients ๐Ÿ”— Iris Dataset Developing Intuition how Relu Fixes Vanishing Gradients Neural Networks Browser Browser

Dependencies

All the examples require the following dependencies to be installed.

How to build?

cd into the directory

If you are using yarn:

cd MNIST-CNN
yarn
yarn watch

If you are using npm:

cd MNIST-CNN
npm install
npm run watch

Details

The convention is that each example contains two scripts:

  • yarn watch or npm run watch: This starts and generates a local development HTML server tracking filesystem for changes, supporting hot-reloading.

  • yarn build or npm run build: generates a dist/ folder which contains the build artifacts and can be used for deployment.

Contributing

If you want to contribute a demo, please reach out to us on Github issues before sending us a pull request as we are trying to keep this set of examples small and highly curated.

Acknowledgements

visualml's People

Contributors

akshitmittal1 avatar anirudhdagar avatar ankitdsi2010 avatar dependabot[bot] avatar dhruv220445 avatar gargdoppler avatar gupta1912 avatar ishan-kumar2 avatar r7rohan avatar sahilg06 avatar saswatpp avatar subham103 avatar vipul2001 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  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  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  avatar  avatar  avatar  avatar  avatar  avatar  avatar

visualml's Issues

Build a Standalone main static website

Deploy a static gh-pages website from the VisualML repo, allowing users to view the list of demos with a short summary of each demo. Each demo will still maintain its own personal website. The idea is to direct users from a single webpage showcasing all the demos in brief.

Addition of Polynomial Regression and its deployment on the website

Task-Implementation of polynomial regression using tf.js and deploying it on the website

Steps to be followed-

  • Start off by making the relevant index.js file

  • The file should have the following functions:

  • mean

  • std-dev

  • normalizedvectors

  • toNormalizedTensor

  • Modelfit

  • RenderPredictions

  • fitandrender

  • generate(X-Y)data

  • draw the data using plotly.js

  • Next task is to make the relevant index.html file to display the algorithm

Resources to follow

TASK- Make the cards on index page uniform and responsive

Steps to be followed-

  • The code for the cards can be found here
  • The css code is inline. You can create the css classes in style.css file
  • Change the css of the boxes such that size of all the cards on the site is uniform
  • Make the webpage fully responsive, for eg. the boxes aren't responsive. Apart from this, there are other issues on the page like:
    For a 13'' screen, the site appears as:
    image
    But for a 15'' screen, the site appears as:
    image

TASK- Designing of a fully responsive footer

Design a fully responsive footer to be added at the bottom of all the pages of the VisualML site (including the home page and the demo pages).
The footer shall:

  • display the DSG logo
  • contain links to all the social media accounts of DSG under a Contact Us heading
  • display DSG's address

Add the HTML code for the footer below this line for the home page. Add the CSS for it in this file. Similarly, add the footer to all the demo pages.

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.