Code Monkey home page Code Monkey logo

Comments (3)

swy0915 avatar swy0915 commented on August 22, 2024

我发现跑了几轮后 有出现这样的情况了，loss从0.1多变成1.0多了。。。最好的时候f1能到70出头，然后就就f1变的很小了。不知道为什么，好奇怪，我跑的时候批次是设置成8的。其他应该一样的

from kg-2019.

swy0915 avatar swy0915 commented on August 22, 2024

最后发现是因为我批次和苏神的不一样 我批次是8然后学习率还是0.001,就会有loss上升的情况,当我把batchsize设置为16,学习率改为0.0005的时候,之前的loss回升的情况就没有了

from kg-2019.

helloworldhellokitty avatar helloworldhellokitty commented on August 22, 2024

请问你一次epoch的时间大概是多久，我换了一下自己的数据集，代码其他的地方没有大的改动，但是训练到第四个epoch就特别特别慢了，到第四个epoch可能需要一个小时，第五个epoch就直接卡死

from kg-2019.

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.