deepinsight / deepinsight/insightface
Need of forward_backward in partial_fc.py for arcface_torch ?
Open
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
Why do we explicitly need to code the backward part in forward_backward in partial_fc.py for arcface_torch?
can't PyTorch auto-differentiation take care of this?
I would really appreciate help on this.
Thanks
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.