Deep Java Library

Open source library to build and deploy deep learning in Java
Get Started GitHub
Join the DJL newsletter


device_hub

Engine Agnostic

Write once and run anywhere. Develop your model using DJL and run it on an engine of your choice

group

Built for Java developers

Intuitive APIs use native Java concepts and abstract away complexity involved with Deep learning

cloud_upload

Ease of deployment

Bring in your own model, or use a state of the art model from our library to deploy in minutes

From our customers

  • “The Netflix observability team's future plans with DJL include trying out its training API, scaling usage of transfer learning inference, and exploring its bindings for PyTorch and MXNet to harness the power and availability of transfer learning.”
    Stanislav Kirdey, Engineer at Netflix observability team
  • “Using DJL allowed us to run large batch inference on Spark for Pytorch models. DJL helped reduce inference time from over six hours to under two hours.”
    -- Xiaoyan Zhang, Data Scientist at TalkingData
  • “DJL enables us to run models built with different ML frameworks side by side in the same JVM without infrastructure changes. ”
    -- Hermann Burgmeier, Engineer at Amazon Advertising team
  • “Our science team prefers using Python. Our engineering team prefers using Java/Scala. With DJL, data science team can build models in different Python APIs such as Tensorflow, Pytorch, and MXNet, and engineering team can run inference on these models using DJL. We found that our batch inference time was reduced by 85% from using DJL.”
    -- Vaibhav Goel, Engineer at Amazon Behavior Analytics team