Image Segmentation Script
by Meta AI · open-source · Last verified 2026-03-17
Runs Segment Anything Model (SAM 2) or Mask2Former on image batches, producing per-pixel segmentation masks with class labels and confidence scores. Includes utilities for mask overlay visualization and RLE-encoded mask export compatible with COCO annotation format.
https://github.com/facebookresearch/segment-anything-2 ↗B
B—Above Average
Adoption: B+Quality: AFreshness: ACitations: BEngagement: F
Specifications
- License
- Apache-2.0
- Pricing
- open-source
- Capabilities
- instance-segmentation, semantic-segmentation, mask-export, coco-format
- Integrations
- pytorch, huggingface, pycocotools
- Use Cases
- autonomous-driving-datasets, medical-image-analysis, satellite-image-processing
- API Available
- No
- Language
- python
- Dependencies
- torch, torchvision, segment-anything-2, pycocotools, pillow, matplotlib
- Environment
- Python 3.10+, CUDA 11.8+
- Est. Runtime
- 5-20 minutes
- Tags
- segmentation, sam, mask, instance-segmentation, vision
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
62Adoption
72
Quality
85
Freshness
88
Citations
65
Engagement
0