Somnusochi / VLM-AutoYOLO
AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation with NVIDIA LocateAnything-3B, manual refinement, one-click YOLO training, video keyframe extraction, and model validation. Supports image and video.
Why this job: matched by what the repo talks about: video, image, pipeline, end
What it does
- VLM auto-labeling. Open-vocabulary object detection with LocateAnything-3B
- SAM2 / SAM3 segmentation. Bbox → pixel-precise mask with SAM 2.1 or SAM3 text-driven detection+segmentation in one pass, BBox/Mask toggle on canvas
- Video annotation. Intelligent keyframe extraction (scene / motion / interval), SSIM dedup
- Manual refinement. Canvas draw mode, NMS filtering, hide/show individual boxes
- Multi-format export/import. YOLO, YOLO-Seg, COCO JSON, Pascal VOC XML, CreateML JSON — export all saved detections or selected records as ZIP, import datasets via chunked upload (max 10GB, resume support)
Get started
git clone https://github.com/Somnusochi/VLM-AutoYOLO.git
cd VLM-AutoYOLO
python3 cli.py all huggingface-cli download nvidia/LocateAnything-3B --local-dir backend/model
python -c "from sam2.build_sam import build_sam2_hf; build_sam2_hf('facebook/sam2.1-hiera-base-plus', device='cpu')" - Maintenance
- Active
- Last commit 51 days ago
- Stars
- 278
- +3 this week
- Licence
- AGPL-3.0
- Share-alike, even hosted
- Downloads for
- None listed
- No release files
- Latest version
- v1.5.16
- Released 2 months ago
- Built with
- Python
- 53% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 71% closed
- 2 still open
- Pull requests
- 2 merged
- 1 waiting
- Releases
- 37
- 30+ in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| insight-platform / Savant | 869 | 2 months ago | Apache-2.0 | No downloads |
| VIAME / VIAME | 345 | 34 days ago | Custom | No downloads |
More: languages, topics and project record
Languages
- Python 53%
- TypeScript 45%
- CSS 1%
- Dockerfile <1%
Topics
- auto-labeling
- computer-vision
- data-annotation
- deep-learning
- fastapi
- locate-anything
- machine-learning
- nvidia
- object-detection
- pytorch
- react
- video-annotation
Project record
- JobVideo
- StatusListed
- Commits353
- Forks41
- Watching0
- Stars in 28 days+17
- CreatedJun 2, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026