facebookresearch / facebookresearch/detectron2
QAT training support?
Open
enhancement
- Dominant language
- Python
- Stars
- 34.7k
- Forks
- 7.9k
- PR merge metrics
- No merged PRs in 30d
Description
Since some model such MaskRCNN gains a lot speed up and very tiny precesion drop in int8 model, is there any plan to support automatically QAT training support in d2?
Contributor guide
Assessment
This issue has not been assessed yet.