https://github.com/capjamesg/sam-clip

Use Grounding DINO, Segment Anything, and CLIP to label objects in images.
https://github.com/capjamesg/sam-clip

clip computer-vision segment-anything zero-shot-object-detection

Last synced: 10 months ago
JSON representation

Use Grounding DINO, Segment Anything, and CLIP to label objects in images.

• Host: GitHub
• URL: https://github.com/capjamesg/sam-clip
• Owner: capjamesg
• License: mit
• Created: 2023-11-17T09:42:39.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-12-27T21:45:40.000Z (over 2 years ago)
• Last Synced: 2025-05-04T23:52:17.383Z (about 1 year ago)
• Topics: clip, computer-vision, segment-anything, zero-shot-object-detection
• Language: Python
• Homepage:
• Size: 7.81 KB
• Stars: 31
• Watchers: 3
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# sam-clip

Use Grounding DINO, Segment Anything, and CLIP to label objects in images.

Below is an image with segmentation masks of all `McDonalds` logos in an image.

This demo was created by sending the prompt `logo` to Grounding DINO and SAM, then classifying each prediction using CLIP with two prompts: `McDonalds` and `Burger King`.



## License

This project is licensed under an [MIT license](LICENSE).