Code Monkey home page Code Monkey logo

Comments (5)

ttaohe avatar ttaohe commented on July 17, 2024

请问这个问题解决了嘛

from efficientteacher.

BowieHsu avatar BowieHsu commented on July 17, 2024

@yjcreation 您好,我来检查一下代码,最近太忙了没有及时回复issue,十分抱歉

from efficientteacher.

BowieHsu avatar BowieHsu commented on July 17, 2024

@yjcreation 我看了这块的逻辑貌似是没有问题的,这里要传出去的就是obj的值,而不是cls的值,而事实上我们在训练的时候也是关掉了这个loss的

from efficientteacher.

yjcreation avatar yjcreation commented on July 17, 2024

@yjcreation 我看了这块的逻辑貌似是没有问题的,这里要传出去的就是obj的值,而不是cls的值,而事实上我们在训练的时候也是关掉了这个loss的

好的,谢谢!这里的逻辑是不是按照如下进行理解:
综合置信度 ≥ τ2,无监督的损失为分类损失+回归损失+置信度损失;
τ1<综合置信度<τ2,无监督的损失为回归损失+置信度损失;
综合置信度≤τ1,无监督的损失为置信度损失。
根据不同的阈值,每个伪标签计算方式从这三种里面选择一个
@BowieHsu

from efficientteacher.

yjcreation avatar yjcreation commented on July 17, 2024

您好!想请问一下1.
$$Y_{(h,w)}^{cls} , Y_{(h,w)}^{reg} , Y_{h,w}^{obj}$$

$$\hat{Y}{(h,w)}^{cls} , \hat{Y}{(h,w)}^{reg} , \hat{Y}_{h,w}^{obj}$$

有什么区别吗?不是都表示教师模型针对无标注数据的预测值吗?
2.

$$\hat{Y}_{h,w}^{obj}$$

$$\hat{obj}_{(h,w)}$$
有什么区别?可以针对以上两个问题具体解释一下吗?谢谢!

from efficientteacher.

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.