Comments (7)
作者你好,我测试了你训练的mobilefacenet模型(mxnet),lfw,cfp-fp,agedb-30,上的指标非常高,基本与你的说明相同,但是我测试了自己的数据集(静态配合式人脸数据),发现与我自己训练的模型性比,性能差的较多。说明下,我训练的是 (mobilefacenet 128维,就是insightface中的模型,没有做什么修改,用的数据集也是glint 公开数据集,我训练的LFW, cfp-fp,agedb-30的指标都比较低,大概式99.2%,89.1%和 94.2%左右),我很疑惑,为什么你在验证集上的指标比我高了很多,为什么在我的数据集上性能却有较大差距呐?希望可以和你探讨下这个问题?不知道你有没有在自己的数据集上测试过。
你好,首先我选取模型标准以megaface为主,其次我训练数据是比赛数据,不是glint那个数据,比赛数据,详情见insightface
from facerecognize-for-mobile-phone.
@olojuwin 多谢你的回复,我疑问点是验证集指标为什么没有标示出模型的性能呐?
from facerecognize-for-mobile-phone.
@baishiruyue 你说的性能是指什么性能?
from facerecognize-for-mobile-phone.
@olojuwin 就是你训练出的模型的lfw,cfp-fp和agedb三个验证集指标都比我自己训的模型的这三个值高了许多,但是在实际测试集(我自己的一个1:10000的测试集,数据基本都是正对摄像头拍摄的人脸数据)上,误识率和漏报率,你的模型都要稍差些?
from facerecognize-for-mobile-phone.
@baishiruyue 主要是对齐方式不一样,还有你测试的注意RGB和BGR的区别
from facerecognize-for-mobile-phone.
@olojuwin 我也尝试了RGB和BGR两种方法,和insightface论文相同的RGB输入方式 比 BGR输出性能要好,但是在我自己的数据集上性能还是差了些,所以我也认为主要和对齐方式有关吧,你训练的时候是采用mtcnn对齐的,我是采用retinaface的检测结果进行对齐的,不过感觉性能差别还是有点儿大啊。。。
from facerecognize-for-mobile-phone.
@baishiruyue 我的训练数据也是retinface对齐的,训练数据不一样,怎么比?你应该有加格林深瞳亚洲人脸数据,或者说你有自己的私有数据。
from facerecognize-for-mobile-phone.
Related Issues (12)
- 请问模型输入的mean/scale是多少? HOT 2
- zwface的论文 HOT 1
- 我想复测一下模型在Megaface上的表现,但未找到run.sh里面的run_experiment.py HOT 5
- 模型跟原版insightface一样 为啥r100比原版慢10倍 ? HOT 5
- 训练方法后续会有公开吗? HOT 3
- 模型大小 HOT 6
- 可否分享训练代码 HOT 7
- caffe模型转换为openvino精度损失大 HOT 2
- 人脸对齐方式 HOT 6
- 请问,可以集成在安卓项目中吗?怎么集成 HOT 2
- 作者您好,我想请问下如何进行Megaface的Verification测评,我在devkit里测出来只有rank1 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from facerecognize-for-mobile-phone.