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
- 'SegLocalVisualizer is not in the mmengine::visualizer registry
- Colab GPU RAM (16 GB) overflow while inferencing using Segformer B4 pretrained model with Cityscape dataset
- How to start single-machine multi-card training
- RuntimeError: Inference tensors cannot be saved for backward. To work around you can make a clone to get a normal tensor and use it in autograd
- mmcv present keyError:‘loss’, when rewrite the code
- GPU Memory Usage Peaks at the Beginning and Is Stable later.
- Is the validation loss computed in the mmsegmentation 1.2.2? If so, how can i plot it?
- clip2mmseg.py not support ViT-B/32 pre-training weight
- Error during save and load models using api init_model
- default "ignore_index=-100" or "ignore_index=255"
- Docs
- Python not yet supported