facebookresearch / facebookresearch/detectron2
train Panoptic Segmentation model on custom dataset
Open
enhancement
- Dominant language
- Python
- Stars
- 34.7k
- Forks
- 7.9k
- PR merge metrics
- No merged PRs in 30d
Description
## ❓ How to train Panoptic Segmentation on a custom dataset ?
Hello everyone,
My question is two-fold :
1. What is the expected Detectron2 format for Panoptic Segmentation ? In the PS paper, they are talking about a pixel-wise annotation (either stuff class or instance ID) but it seems that D2 requires bounding boxes as well.
2. Is it possible to train PS on a custom dataset with only pixel-wise annotations ?
Thanks,
Cyril
Contributor guide
Assessment
This issue has not been assessed yet.