DJL - PaddlePaddle model zoo¶
The PaddlePaddle model zoo contains symbolic models that can be used for inference. All the models in this model zoo contain pre-trained parameters for their specific datasets.
The latest javadocs can be found on the djl.ai website.
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.
You can pull the ai.djl.paddlepaddle:paddlepaddle-model-zoo from the central Maven repository by including the following dependency:
<dependency> <groupId>ai.djl.paddlepaddle</groupId> <artifactId>paddlepaddle-model-zoo</artifactId> <version>0.10.0-SNAPSHOT</version> </dependency>
The PaddlePaddle model zoo contains Computer Vision (CV) models.
- Face Detection: Detect faces in the image
- Mask Classification: Detect mask
- Word Recognition: Find word blocks in the image
- Word Orientation Classification: Find if rotate image is needed
- Word Recognition: Recognize text from image
How to find a pre-trained model in model zoo¶
Please see DJL Model Zoo