Skip to content

DJL - PyTorch model zoo

The PyTorch model zoo contains symbolic (JIT Traced) models that can be used for inference. All the models in this model zoo contain pre-trained parameters for their specific datasets.

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 PyTorch engine from the central Maven repository by including the following dependency in you pom.xml file:

<dependency>
    <groupId>ai.djl.pytorch</groupId>
    <artifactId>pytorch-model-zoo</artifactId>
    <version>0.30.0</version>
</dependency>

Pre-trained models

The PyTorch model zoo contains Computer Vision (CV) models. All the models are grouped by task under these two categories as follows:

  • CV
  • Image Classification
  • Object Detection
  • Style Transfer
  • Image Generation

How to find a pre-trained model in model zoo

Please see DJL Model Zoo