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
- ValueError: need at least one array to concatenate when training with custom .tif dataset
- 当我对mmseg.models.backbones.unet进行debug时，出现错误
- Produce wrong label in the loveda dataset
- KeyError: 'PALETTE'
- How to modify config file for single channel images trainning!
- How do I convert labelme annotated datasets into cityscapes?
- Unable to freeze decoder weights completely
- [CodeCamp2023-527] Add pixel contrast cross entropy loss
- get_flops.py can not be used by Mask2Former and MaskFormer
- Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed. This is not an error, but may impair performance
- Docs
- Python not yet supported