3D Convolution Neural Network Visualizer

A React TypeScript application using Three.js to visualize convolutional neural network operations in 3D space. This project creates an interactive stacked projection view of CNN layers showing the flow of data through the network. Its aim is to help build an intuition of how convolutional parameters affect the receptive field of the recursive receptive field

Note

I have no prior experience with React (or TypeScript) and a large portion of the initial work was done with Claude. Any PRs/issues for sections which are done in a non-idiomatic or inefficient way are welcome

Getting Started

Prerequisites

• Node.js (v18 or later)
• npm or yarn

Installation

1. Clone the repository

git clone <repository-url>
cd convolution-visualizer

2. Install dependencies

npm install

3. Start the development server

npm run dev

4. Open your browser and navigate to http://localhost:5173/

Development

Available Scripts

• npm run dev - Start development server
• npm run build - Build for production
• npm run preview - Preview production build
• npm run lint - Run ESLint

License

This project is licensed under the MIT License.