Quick start

Deep Java Library (DJL) is designed to be easy to get started with and simple to use. The easiest way to learn DJL is to read the beginner tutorial or our examples.

You can also view our 1.5 hour long (in 8 x ~10 minute segments) DJL 101 tutorial video series:

Prerequisites

You need a Java Development Kit (JDK) installed on your system. We recommend using JDK 8, but any later version also works. For more information, see Setup.
You need git installed on your system to clone the DJL repository.

Try DJL

We developed several interactive toolkits for you to experience DJL. You can start from here to run inference online and download starter template with DJL.

See DJL Future Labs

Beginner tutorial

To get started, we recommend that you follow our short beginner tutorial. It takes you through some of the basics of deep learning to create a model, train your model, and run inference using your trained model.

Run examples

DJL also provides examples for both training and performing inference with deep learning models. You can find the examples and their source code in the examples directory.

All of our examples are executed by a simple command. For detailed command line instructions, see each example’s Readme.md file.

Train your first model
Single-shot Object Detection inference example
More examples
Jupyter examples

Other resources

JavaDoc API Reference
Contributor Documentation
FAQ

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!