Giter Club home page Giter Club logo

Comments (7)

lidq92 avatar lidq92 commented on July 4, 2024

@lllllllllllll-llll 现在qa领域里跨数据测试的时候非线性映射的常见做法有2种。
第一种是在整个测试数据集上做非线性拟合。这时候只需要算1次指标即可。
第二种是将测试数据集随机划分为用于非线性拟合的训练数据和测试数据,比如按80%:20%的比例划分1000次。这时候会得到指标的1000个值,一般汇报均值和标准差或者中值。

备注1:计算拟合前的srocc, krocc和拟合后的plcc, rmse, or。
备注2:非跨数据集测试的时候本身就有训练和测试数据,这个时候所有的方法都在训练数据上拟合,在测试数据上算指标。
备注3:需要进行超参数选择的时候,一般还需要划分验证集,用验证集的结果来指导超参数的选取,不能直接用测试集的结果选取超参数(有作弊的嫌疑)。
备注4:非线性映射的函数有很多,常见的有两种:一种是vqeg建议的四参数logistic函数,另一种是live数据集那篇文章TIP2006中的五参数logistic函数。推荐你使用四参数的,初值的设定可以参考我SFA那篇文章TMM2019中写的值。

from cnniqa.

lllllllllllll-llll avatar lllllllllllll-llll commented on July 4, 2024

感谢您的解答,那我用这个CNNIQA在live上训练的model在tid和csiq上测试的时候非线性映射可以就用您SFA文章中的初始值吗。再次感谢。

from cnniqa.

lidq92 avatar lidq92 commented on July 4, 2024

@lllllllllllll-llll MATLAB的话可以就用这个函数nonlinearfitting

from cnniqa.

lllllllllllll-llll avatar lllllllllllll-llll commented on July 4, 2024

非常感谢您

from cnniqa.

lllllllllllll-llll avatar lllllllllllll-llll commented on July 4, 2024

您好,我试了一下,srocc计算出来的值是负值,请问这是什么原因呢,我用的在live上跑的CNNIQA,求解答呢。还有一个问题想请教您,用live数据集上的dmos跑和dmos_realigned跑有啥区别呢。

from cnniqa.

lidq92 avatar lidq92 commented on July 4, 2024

@lllllllllllll-llll 你需要多阅读一些i/vqa相关的文献以及对这些数据集的信息有一些了解。

live中分数越大对应主观质量越差,而TID是分数越大主观质量越好。所以你算出来是负数是合理的,这个时候趋势相反应该取一个负号(如果算出来是正的反而说明实际的趋势预测错误了)。

另一个问题请你自己去看live数据集的文章了解。

from cnniqa.

lllllllllllll-llll avatar lllllllllllll-llll commented on July 4, 2024

好的,再次感谢您;-)

from cnniqa.

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.