deepinsight / deepinsight/insightface

partial fc precision

Open
#1,606 6 comments 0 reactions 0 assignees View on GitHub
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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.