Skip to content

DJL - TensorFlow engine implementation

Overview

This module contains the Deep Java Library (DJL) EngineProvider for TensorFlow.

We don't recommend that developers use classes in this module directly. Use of these classes will couple your code with TensorFlow and make switching between frameworks difficult.

Currently training is not supported.

Documentation

The latest javadocs can be found on here.

You can also build the latest javadocs locally using the following command:

# for Linux/macOS:
./gradlew javadoc

# for Windows:
..\..\gradlew javadoc

The javadocs output is built in the build/doc/javadoc folder.

Installation

You can pull the TensorFlow engine from the central Maven repository by including the following dependency:

  • ai.djl.tensorflow:tensorflow-engine:0.31.0
<dependency>
    <groupId>ai.djl.tensorflow</groupId>
    <artifactId>tensorflow-engine</artifactId>
    <version>0.31.0</version>
    <scope>runtime</scope>
</dependency>

By default, DJL will download the TensorFlow native libraries into cache folder the first time you run DJL. It will automatically determine the appropriate jars for your system based on the platform and GPU support.

You can choose a native library based on your platform if you don't have network access at runtime.

macOS

For macOS, you can use the following library:

  • ai.djl.tensorflow:tensorflow-native-cpu:2.16.1:osx-aarch64
<dependency>
    <groupId>ai.djl.tensorflow</groupId>
    <artifactId>tensorflow-native-cpu</artifactId>
    <classifier>osx-aarch64</classifier>
    <version>2.16.1</version>
    <scope>runtime</scope>
</dependency>

Linux

For the Linux platform, you can choose between CPU, GPU. If you have NVIDIA CUDA installed on your GPU machine, you can use one of the following library:

Linux GPU

  • ai.djl.tensorflow:tensorflow-native-cu121:2.16.1:linux-x86_64 - CUDA 12.1-cudnn8
<dependency>
    <groupId>ai.djl.tensorflow</groupId>
    <artifactId>tensorflow-native-cu121</artifactId>
    <classifier>linux-x86_64</classifier>
    <version>2.16.1</version>
    <scope>runtime</scope>
</dependency>

Linux CPU

  • ai.djl.tensorflow:tensorflow-native-cpu:2.16.1:linux-x86_64
<dependency>
    <groupId>ai.djl.tensorflow</groupId>
    <artifactId>tensorflow-native-cpu</artifactId>
    <classifier>linux-x86_64</classifier>
    <scope>runtime</scope>
    <version>2.16.1</version>
</dependency>

Windows

For the Windows platform, you can choose between CPU and GPU.

Windows GPU

  • ai.djl.tensorflow:tensorflow-native-cu121:2.16.1:win-x86_64 - CUDA 12.1-cudnn8
<dependency>
    <groupId>ai.djl.tensorflow</groupId>
    <artifactId>tensorflow-native-cu121</artifactId>
    <classifier>win-x86_64</classifier>
    <version>2.16.1</version>
    <scope>runtime</scope>
</dependency>

Windows CPU

  • ai.djl.tensorflow:tensorflow-native-cpu:2.16.1:win-x86_64
<dependency>
    <groupId>ai.djl.tensorflow</groupId>
    <artifactId>tensorflow-native-cpu</artifactId>
    <classifier>win-x86_64</classifier>
    <scope>runtime</scope>
    <version>2.16.1</version>
</dependency>