https://github.com/capjamesg/sam-gpt4v
Use Grounding DINO, Segment Anything, and GPT-4V to label images with segmentation masks for use in training smaller, fine-tuned models.
https://github.com/capjamesg/sam-gpt4v
Last synced: over 1 year ago
JSON representation
Use Grounding DINO, Segment Anything, and GPT-4V to label images with segmentation masks for use in training smaller, fine-tuned models.
- Host: GitHub
- URL: https://github.com/capjamesg/sam-gpt4v
- Owner: capjamesg
- License: mit
- Created: 2023-11-07T23:06:49.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-11-23T14:32:20.000Z (over 2 years ago)
- Last Synced: 2025-04-30T11:14:18.414Z (over 1 year ago)
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 66
- Watchers: 2
- Forks: 5
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# SAM-GPT-4V
Use [Grounding DINO](https://blog.roboflow.com/grounding-dino-zero-shot-object-detection/), [Segment Anything](https://blog.roboflow.com/how-to-use-segment-anything-model-sam/), and [GPT-4V](https://blog.roboflow.com/gpt-4-vision/) to label images with segmentation masks for use in training smaller, fine-tuned models.
Here is an example of SAM-GPT-4V used to label the manufacturer of a car:
## License
This project is licensed under an [MIT license](LICENSE).