OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Deeplearning4J

Deeplearning4J is an open-source suite of Java Virtual Machine libraries for building, training and running deep-learning models, with tools for data preparation, numerical computing and selected model imports.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Deeplearning4J — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Deeplearning4J when deep-learning work needs to live in a JVM application and you want libraries for data preparation, network construction, training or numerical operations. Check the specific component's import documentation before planning around a model format.

Who it is for

  • Java developers building neural-network applications.
  • Teams using JVM languages such as Scala, Kotlin or Clojure.
  • Developers integrating model training, data pipelines or model execution into JVM server applications.

Documented uses

  • Prepare machine-learning data from supported file and media formats.
  • Build and tune neural networks, including custom layers.
  • Train models in JVM applications, including distributed training with Apache Spark.
  • Use supported imported models from other frameworks in Java-based applications.
  • Run neural-network computations with Java and C++ numerical libraries.
Before you choose

Requirements & limits

The repository is public and identifies the project as open source under the Apache-2.0 license.

  • Integration is through a build tool; the README provides Maven dependency examples.
  • The ecosystem separates responsibilities across DL4J, ND4J/LibND4J, SameDiff and DataVec.
  • Model-import support varies by library and format: the component notes specify Keras H5 support in DL4J and frozen TensorFlow .pb support in SameDiff.
  • The README lists Windows, Linux and macOS support and describes CPU and CUDA GPU options, with some hardware and platform exceptions.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add Deeplearning4J CPU dependencies to a Maven project

Set up a Maven project to use Deeplearning4J with the CPU backend.

Before you start

  • A Maven project with a pom.xml file.
  • A build tool; the project says Deeplearning4J usage is supported with a build tool because it has numerous dependencies.

Steps

  1. Add the org.eclipse.deeplearning4j:deeplearning4j-core dependency at version 1.0.0-M2.1 to pom.xml.

  2. Add the org.eclipse.deeplearning4j:nd4j-native-platform dependency at version 1.0.0-M2.1 to pom.xml.

  3. Use the configured dependencies in the Maven project for the CPU backend.

Expected outcome

The Maven project is configured with the documented Deeplearning4J dependencies for CPU-backend use.

Guide limitations

  • This recipe covers dependency setup, not building or running a model.
  • The README recommends official pre-compiled releases; source builds have separate CPU and GPU instructions.
  • The documented tests use the platform-tests module and require JDK 11.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
deeplearning4j/deeplearning4j · Official homepage title · retained in its source language
How we review sourcesSuggest a correction