facebookresearch / facebookresearch/detectron2
YOLO-based series of detectors and DERT need be update
Open
enhancement
- Dominant language
- Python
- Stars
- 34.7k
- Forks
- 7.9k
- PR merge metrics
- No merged PRs in 30d
Description
The YOLO-based series of detectors and DERT have long been the SOTA and widely used. We are still based on the FRCNN-2015 framework, which is too old. When will the detection base model be updated to add the YOLO series models and DERT?
Contributor guide
Research direction
The issue names no files, tests, or entry points. Start by surveying Detectron2's existing detector and model documentation, then clarify the requested YOLO-based and DERT integrations and acceptance criteria with maintainers; done would mean the agreed models are supported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100