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
- No model can learn anything from my dataset. (But I already trained models outside of MMDetection successfully)
- RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one.
- RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
- KeyError: 'SiLU is already registered in model at torch.nn.modules.activation'
- Multi-GPU training hangs sometimes when fine tuning the RTMDet instance segmentation model
- Customized Loss Function
- Train with multiple(4) GPUs
- [Training is in progress] [Feature] Support RT-DETR
- ConcatDataset does not seem to support customize dataset settings "metainfo" yet
- Obtain object coordinates based on mask rcnn results and depth maps
- Docs
- Python not yet supported