deepinsight / deepinsight/insightface
partial fc precision
- Dominant language
- Python
- Stars
- 29.7k
- Forks
- 6.1k
- PR merge metrics
- No merged PRs in 30d
Description
I compared partial fc (r=0.2, pytorch version) with full softmax for my dataset (1 million identities). The precision of partial fc (r=0.2) is lower than that of softmax. Could you give some advices? Thanks!
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue mentions partial FC with r=0.2, the PyTorch version, and a comparison with full softmax, but names no file, test, or entry point. Start by locating the Partial FC PyTorch implementation and reproducing the precision comparison on the reported dataset scale. Done would require identifying whether the difference is expected or a reproducible implementation problem and documenting the evidence.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100