mmsegmentation
https://github.com/open-mmlab/mmsegmentation
Python
OpenMMLab Semantic Segmentation 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 supported1 Subscribers
Add a CodeTriage badge to mmsegmentation
Help out
- Issues
- Keep training and validation pipeline separated
- Keep train/valand eval configs separated
- result per class returns nan
- wandb config logging
- decode.acc_seg drops to 0.0 quickly and leads to 0s evaluation scores on custom dataset
- KeyError: 'EncoderDecoder: \'`cfg` or `default_args` must contain the key "type", but got {\\\'num_classes\\\': 171}\\nNone\''
- Add HRViT
- Support CAM based method for model interpretability
- mmseg中计算accuracy时使用threshold参数时报错
- voc test 报错问题
- Docs
- Python not yet supported