Deep Java Library (DJL) is designed to be the lowest barrier of entry for Deep Learning. The easiest way to learn DJL is to follow our examples and jupyter notebooks.
- 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.
DJL 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:
Our Jupyter notebooks are another great way to learn how to use DJL. Each notebook provides a guide with detailed steps and explanations. You can find them in the jupyter directory. Make sure you follow the Setup guide to configure the jupyter environment for Java.