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 supported6 Subscribers
Add a CodeTriage badge to mmdetection
Help out
- Issues
- [Feature] Enhanced geospatial support
- [Bug]
- [Bug] On A100 80GB PCIe gives Cuda Illegal memory access if samples_per_gpu>x such that VRAM>30GB
- [Bug] YOLOX "loss_bbox" may sometimes equal to zero in training.
- [Feature] [3.x] May I ask the reason why the color palette value based on the model?
- [New Models] Domain Adaptive Object Detection
- average inference time per frame/per video increases for htc object detection and segmenation model
- AssertionError: loss log variables are different across GPUs! I used cascade Rcnn to train object365,and I have processed the dataset. However,the loss always turn to NAN and it can not run the first epoch successfully.
- [Feature] Support YOLOX-PAI 3.x
- Refactor detr 3.x conditional detr and group detr
- Docs
- Python not yet supported