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>0.31.0</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