GithubHelp home page GithubHelp logo

LFW with JB about faceverification HOT 22 OPEN

happynear avatar happynear commented on August 15, 2024
LFW with JB

from faceverification.

Comments (22)

happynear avatar happynear commented on August 15, 2024

This line

tmp((testing-1)300+1:testing300,:) = [];

deletes the testing features out.

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

抱歉我可以打中文麻?

可是10-fold cross 不是就要將樣本分為10份,9份拿去訓練1份拿去測試?把那一行刪除不就等於把10份都拿去訓練?

from faceverification.

happynear avatar happynear commented on August 15, 2024

对,10-fold就是这个意思。
如果把

tmp((testing-1)300+1:testing300,:) = [];

删掉,就是全部拿去训练了。

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

那全部拿去訓練,這樣就不是10-fold cross了不是麻?不是應該拿9份去訓練?(如果把那行刪除,不就等於是10份都拿去訓練??)

還是是我對10-fold cross觀念有錯誤呢

from faceverification.

happynear avatar happynear commented on August 15, 2024

按我的代码就是标准的10-fold cross-validation。
你可以自己在matlab里试一下A(range) = [];的作用,就明白了。

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

所以照您說的把 tmp((testing-1)300+1:testing300,:) = []; 刪除就對了是麻?

from faceverification.

happynear avatar happynear commented on August 15, 2024

tmp((testing-1)300+1:testing300,:) = [];
要留着啊,这行代码的意思是把(testing-1)300+1:testing300部分的feature从tmp里删除掉。

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

是的
留著但是底下test的時候不就要是把這(testing-1)300+1:testing300部分的feature進行測試?
所以上下的testing必須一樣
testing = 10;
tmp = pairlist_lfw.IntraPersonPair;
tmp((testing-1)300+1:testing300,:) = [];
train_Intra = tmp;
idx = [idx;tmp(:)];
tmp = pairlist_lfw.ExtraPersonPair;
tmp((testing-1)300+1:testing300,:) = [];
train_Extra = tmp;
到這裡的意思不是從2701~3000的featrue刪除?

再這裡測試的時候不是要對2701~3000進行test? 所以底下的testing不能等於8要等於10?
testing = 8;
test_Intra = pairlist_lfw.IntraPersonPair((testing-1)300+1:testing300,:);
test_Extra = pairlist_lfw.ExtraPersonPair((testing-1)300+1:testing300,:);

from faceverification.

happynear avatar happynear commented on August 15, 2024

哦对,要把testing = 8;这句删掉,上下保持一致。

from faceverification.

happynear avatar happynear commented on August 15, 2024

而且要做10次,取平均。
for一下就好了。

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

是的,我就是改成上下一致,但是performance很差,想請教您怎麼會這樣

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

不好意思我還想請問您,用CASIA data的話 siamese中data是如何創造的?

from faceverification.

happynear avatar happynear commented on August 15, 2024

用dataset里的那几个脚本生成list就好了。
performance的话,这个不是一日之功啊。

from faceverification.

 avatar commented on August 15, 2024

”做10次取平均,for一下就好了“
我的理解是需要做10次,每次要从这10部分中随机选一部分作为test,剩下的9部分作为train,然后对这10次做平均,不是简单的重复10次吧?

from faceverification.

happynear avatar happynear commented on August 15, 2024

@pbypby 每次改testing那个变量呀。

from faceverification.

getengqing avatar getengqing commented on August 15, 2024

请问这几个.mat的数据集是从哪来的?是训练出来的还是下载的?

from faceverification.

 avatar commented on August 15, 2024

@getengqing 从JB作者的论文主页可以下载到

from faceverification.

m10303430 avatar m10303430 commented on August 15, 2024

我用您提供的 lbp_lfw.mat 這個特徵去跑您提供的JB+SVM,得到的結果也只有54%,請問有哪裡做錯了麻?

from faceverification.

getengqing avatar getengqing commented on August 15, 2024

可以给个JB作者的论文主页链接吗?谢谢

from faceverification.

tiankong1993 avatar tiankong1993 commented on August 15, 2024

请问你找到链接了吗 @getengqing

from faceverification.

tiankong1993 avatar tiankong1993 commented on August 15, 2024

mat文件需要从哪里下载呢请问一下 @m10303430

from faceverification.

tiankong1993 avatar tiankong1993 commented on August 15, 2024

可以给个lbp_lfw.mat的下载链接吗,找了好久都没找到,打扰了 @pby5

from faceverification.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.