mmdetection
https://github.com/open-mmlab/mmdetection
Python
OpenMMLab Detection Toolbox and Benchmark
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported7 Subscribers
Add a CodeTriage badge to mmdetection
Help out
- Issues
- Problems I found while training deformable-detr：ms_deform_attn_impl_forward: implementation for device cuda:0 not found.
- 为什么mmdetection的faster rcnn的实现使用L1损失函数而不是Smooth L1?
- How to get validation loss/mAP during VarifocalNet training?
- ValueError: matrix contains invalid numeric entries
- KeyError: 'Models' when mmengine get config metainfos
- To share my code "use tensorrt async can speed up mask-rcnn inference in video processing"
- AttributeError: class `EpochBasedTrainLoop` in mmengine/runner/loops.py: class `MultiImageMixDataset` in mmdet/datasets/dataset_wrappers.py: class `CocoDataset` in mmdet/datasets/coco.py: 'str' object has no attribute 'items'
- Slow instance segmentation inference speed on RTMDet
- Different memory requirement for different datasets (3x times more memory)?
- ValueError: class `EpochBasedTrainLoop` in mmengine/runner/loops.py: class `CocoDataset` in mmdet/datasets/coco.py: need at least one array to concatenate
- Docs
- Python not yet supported