Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
-
Updated
Aug 7, 2024 - Python
Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
Use Florence 2 to auto-label data for use in training fine-tuned object detection models.
GroundedSAM Base Model plugin for Autodistill
YOLOv8 Target Model plugin for Autodistill
GPT-4V(ision) module for use with Autodistill.
EdgeSAM model for use with Autodistill.
Grounding DINO module for use with Autodistill.
SAM-CLIP module for use with Autodistill.
Use PaliGemma to auto-label data for use in training fine-tuned vision models.
GPT-4o (with Vision) module for use with Autodistill.
DINOv2 module for use with Autodistill.
CLIP module for use with Autodistill.
Explore the cutting edge of computer vision with this comprehensive repository, showcasing a spectrum from classical machine learning to state-of-the-art transformer models.
Segment Anything HQ (SAM HQ) module for use with Autodistill.
LLaVA base model for use with Autodistill.
SegGPT module for use with Autodistill
OWLv2 base model for use with Autodistill.
A template for use in creating Autodistill Base Model packages.
Add a description, image, and links to the autodistill topic page so that developers can more easily learn about it.
To associate your repository with the autodistill topic, visit your repo's landing page and select "manage topics."