deepinsight / deepinsight/insightface
Why you want backbone's gradient to multiply world_size (partial fc, pytorch version)
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I've noticed you enforce backbone's gradient to multiply a scaler world_size , can you explain the insight behind this motivation ?
https://github.com/deepinsight/insightface/blob/79aacd2bb3323fa50a125b828bb1656166604487/recognition/partial_fc/pytorch/partial_fc.py#L190
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.