deepinsight / deepinsight/insightface

RetinaFace: Low inference speed using ResNet-50

Open
#1,031 0 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

我想用test.py测试一下预训练的ResNet-50速度,但是结果如下:
A uses 9.729929 seconds
A uses 9.730986 seconds
A uses 9.732174 seconds
X1 uses 9.735658 seconds
X2 uses 9.740575 seconds
X3 uses 9.742364 seconds
显卡是GTX1080Ti,图片尺寸是640*480,系统是Ubuntu16.04;
我把输入部分改成了:
`faces, landmarks = detector.detect([img,img,img], thresh, scales=scales, do_flip=flip)`
但是三次时间都一样
这个速度远低于ResNet-152,但是不知道原因在哪,求大佬解答

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.