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
- Explanation of data_preprocessor size and its conection to padding
- The problem of semantic segmentation for multimodal data
- When training with the 1.0 network, I have a validation set of 143 images, but regardless of testing or validation, only the 50th and 100th images are being evaluated.
- Same config but iou of some class get 0 | 什么都没改但是训练过程中有的类别的iou突然变成0了
- Problems with training (related to OHEM?)
- If one inference requires approximately the entire GPU's memory, then the second inference cannot proceed
- I have configured test_ Pipeline, but it seems like he's not working
- SETR Backbone Question - num_layers and num_heads don't match those of pre-trained ViT
- [Fix] Fix the problem that ham_head cannot be executed on NPU.
- Can't reproduce the result in the doc using model deeplabv3 on ade20k.
- Docs
- Python not yet supported