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
- Multi-gpu training
- Solution about not finding *_labelTrainIds in val2017 in the training COCO-Stuff dataset and errors in the official code.
- docker runtime error in mutil GPU train
- It seems that self.conv layer cause the cuda memory overflow:RuntimeError: CUDA error: an illegal memory access was encountered
- 实例的模型下载失败
- Distributed multiple GPU training occpuies more memory on GPU0 when load pretrained model
- TypeError: class `IterBasedTrainLoop` in mmengine/runner/loops.py: class `RepeatDataset` in mmengine/dataset/dataset_wrapper.py: __init__() got an unexpected keyword argument 'pipeline'
- how to add colorbar to featuremap?
- how to arrange the feature map when the backend is changed to local
- test_timm_backbone - AssertionError: No equivalent norm layer for syncbatchnorm
- Docs
- Python not yet supported