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
- AssertionError: The length of palette should not be less than `num_classes`.
- why gpu-util is low ?
- [BUG]Replace the seesaw loss function into a two-stage object detection model results in an error.
- I have added a drop block module to Solo v2 head, which can run normally during training. However, when inferring the model, the model will report an error
- In mmdetection3.0, memory keep increasing fast in the training process of DETR-like object detectors, while in mmdetection2.52.2 the memory increases slowly.
- The test time of mask2former head
- Training dataset of single-channel infrared images
- Support LoadAnnotations during validation
- mmdetection issues and alternatives
- The same backbone successfully trained in a two-stage model,but when training in a one-stage model,mAP remained at 0.00
- Docs
- Python not yet supported