Zero-Shot Inference Service

Generative AI vision transformers such as CLIP and OWL-ViT have made it possible to build zero shot inference models capable of open vocabulary object detection. This means the model is not bounded by a set of pre-defined classes to detect. The objects to detect are configured at runtime by the user.

The Zero Shot Inference AI service, enables quick deployment of Generative AI with Jetson Platform Services for open vocabulary detection on live video stream input. This service uses NanoOwl, an optimized version of OWL-ViT.

The Zero Shot Inference service exposes REST API endpoints to control stream input and objects to detect.

For more information on using this microservice, refer to https://docs.nvidia.com/jetson/jps/inference-services/zero_shot_detection.html

License

By downloading or using the software and materials, you agree to the License Agreement for Jetson Platform Services