Apply Owl-ViT to Images Project

Integration of the Owl-ViT model for class-agnostic object detection

Overview • How to Run

Overview

Application allows you to label projects images using Owl-ViT detection model.

Application key points:

• Select project or dataset to label
• Serve this model by Serve OWL-ViT app and choose model session in selector

• Set up model input data as text-prompt or reference-image
• Preview detection results
• Apply model to project images and save new annotations to new project or add to existed

🔥🔥🔥 Check out our youtube tutorial and the complete guide in our blog:

How to Run

1. Start the application from Ecosystem or context menu of an Images Project

2. Choose your input project / dataset

3. Select your served model and click Select model button

4. Reference Image:
     Pick reference image from your project by clicking navigating buttons and place the reference object in the bounding box
   
   Text Prompt:
     Type the description of the object you want to detect in the corresponding field

Adjust the confidence and NMS thresholds and click Set model input button

5. View predictions preview by clicking according button

6. Select the way you want to save the project and click Run model