Coder Social home page Coder Social logo

sunshangquan / logit-standardization-kd Goto Github PK

View Code? Open in Web Editor NEW
216.0 216.0 6.0 83.6 MB

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

Python 13.22% Jupyter Notebook 86.68% Shell 0.10%
computer-vision cv cvpr cvpr2024 knowledge-distillation model-compression resnet vision-transformer

logit-standardization-kd's People

Contributors

sunshangquan avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

logit-standardization-kd's Issues

想问一下logit具体的计算方式

作者您好,以cifar100为例,想问一下您具体是怎么计算每一类的logit的,是将所有的测试集输入到模型中,然后将所有输出的logit求和,最终除以测试集大小吗。

迁移实验 & 学生模型

  1. 请问是否考虑过将蒸馏后的模型从CIFAR-100迁移到STL-10数据上?
  2. 请问是否可以提供学生模型?

交叉熵损失的作用是什么

  1. 您在算法部分出现Lce,对于它的作用我在文章中并没有找寻到(可能是我没有找到,如果是这样非常抱歉)
  2. 我现在在进行互相知识蒸馏,没有使用Lce,仅仅只使用了预处理部分代码可是效果并不理想
    希望您抽空解答一下我的疑问,非常感谢

实现层面

作者你好,请问在实现层面是否仅有对学生和老师的logit做Normalize操作呢?是否还有其它我没发现的地方需要处理?正在学习您的工作,希望可以得到回复。

关于蒸馏Vit的问题

请问蒸馏vit的代码是各个蒸馏方法通用的吗?另外,请问vit可以作为教师模型吗

想问一下关于CE_WEIGHT的问题

您好,您的工作非常棒!我最近正在学习知识蒸馏这块的最近工作,我看到您关于LOSS.CE_WEIGHT的设置在KD上是0.1,而在其他的蒸馏方法上均是1.0,想问一下这是因为什么呢,非常感谢 : )

config

Dear author:
能提供下在cifar100上蒸馏ResNet50,学生模型为WRN-16-2的配置文件吗,想学习一下

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.