Visualizing How Neural Networks Classify 2D Data

About the project

The project intends to visualize how inputs are transformed linearly and non-linearly by a deep neural network. Users can interactively change the number of layers and neurons of the neural nets and their parameters.

This project is created with Create React App and TensorFlow.js and is now available at https://baichuanzhou.github.io/Intuitive-Classification/.

Deployment

First use git clone https://github.com/baichuanzhou/Intuitive-Classification
Then, cd to your directory and run:

npm install

Installs the necessary dependency for the App.

Then you can start the App in development mode:

npm start

Runs the app in the development mode.
Open http://localhost:3000 to view it in your browser.

The page will reload when you make changes.
You may also see any lint errors in the console.

npm run build

Builds the app for production to the build folder.
It correctly bundles React in production mode and optimizes the build for the best performance.

The build is minified and the filenames include the hashes.
Your app is ready to be deployed!
Then run:

serve -s

The app will run live at your local host http://localhost:3000