Giter Club home page Giter Club logo

Comments (8)

Simon-LLong avatar Simon-LLong commented on May 28, 2024 1

@haneSier 嗯嗯,谢谢你。现在已经收敛了,训练了20个小时后,loss为0.5左右,nepoch到了15.每个epoch运行122次。在训练的时间上有什么优化的方式吗?

准确率是0可能是因为开始就没找到收敛点,你要多试几次,这个东西能不能训练上去有一定的随机性,要初始点比较好才能够上去,学习率0.001,要是训练样本比较难,你可能得换个base model

from crnn_chinese_characters_rec.

haneSier avatar haneSier commented on May 28, 2024

可以不同长度,train loss降到一定程度才有预测的能力

from crnn_chinese_characters_rec.

renxinlin avatar renxinlin commented on May 28, 2024

@haneSier 嗯嗯,谢谢你。现在已经收敛了,训练了20个小时后,loss为0.5左右,nepoch到了15.每个epoch运行122次。在训练的时间上有什么优化的方式吗?

from crnn_chinese_characters_rec.

haneSier avatar haneSier commented on May 28, 2024

训练速度和你的设备有关

from crnn_chinese_characters_rec.

renxinlin avatar renxinlin commented on May 28, 2024

@haneSier 我是用的虚拟机+cpu,理解了。非常感谢您的帮助!

from crnn_chinese_characters_rec.

renxinlin avatar renxinlin commented on May 28, 2024

训练时loss一直在4.5左右震荡,我设置了一个极小的学习率,依旧震荡,无法收敛。请问这是什么原因造成的?我的数据集如下
img4679

from crnn_chinese_characters_rec.

renxinlin avatar renxinlin commented on May 28, 2024

之前训练的时候会将左右切割掉一部分,使得样本中字符占比更大,训练收敛了!现在的样本无法收敛,学习率和batch都设置的很小

from crnn_chinese_characters_rec.

haneSier avatar haneSier commented on May 28, 2024

Batch有条件就设置大一点,初始学习率如果很小的话很有可能无法收敛,固定batch,设置学习率观察收敛趋势,不明显就换一个学习率

from crnn_chinese_characters_rec.

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.