Deep Java Library (DJL) is designed to be the lowest barrier of entry for Deep Learning. The easiest way to learn DJL is to read the beginner tutorial or our examples.
- You need to have JDK installed on your system. We recommend using JDK 8, but any later version will also work. For more information, see Setup.
- You need to have git installed on your system to clone the DJL repository.
We try our best to maintain a stable master branch. However, if you run into issues, please try to use the latest stable release.
The best way to get started is to follow our short beginner tutorial. It takes you through some of the basics of deep learning for creating a model, training your model, and running inference using your trained model.
DJL also provides examples for both training and performing inference with deep learning models. The examples and their source code can be found in the examples directory.
All of our examples can be executed by a simple command. Please refer to each example’s README for detailed command line instructions: