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
- mmdetection-3.0 rtmdet with ExpMomentumEMA,resume
- The conv propagation in VitDet
- Use backbone network implemented in MMPretrain, raise KeyError(f'Cannot find {norm_layer} in registry under
- Freeze the swin backbone
- GFL is unable to train
- Large Image utilities need a local implementation of shift_bbox
- Confusion about Text Prompting
- Training image loading problems
- 单类别检测,密集小目标检测,原图像素2048*2048,物体像素,物体像素 25*25左右,单张图片有大概2500个单类别物体,训练发现map=0,有时候0.001,,例如使用retinanet_r50_fpn_2x_coco.py。应该如何修改,单张显卡训练,我怀疑1物体密集而且小,2数量多,针对数量多的问题,是不是mmdetection代码有设置上限最多检测多少个
- Training benchmark results
- Docs
- Python not yet supported