Coder Social home page Coder Social logo

我使用softmax损失,10177个id, 20万张图片,loss从开始50左右,训练10个epoch后下降到19左右就在一直震荡,请问你们训练时这么大的数据集loss能下降到多少?而且准确率也不会提升。 about arcface-caffe HOT 8 CLOSED

xialuxi avatar xialuxi commented on August 16, 2024
我使用softmax损失,10177个id, 20万张图片,loss从开始50左右,训练10个epoch后下降到19左右就在一直震荡,请问你们训练时这么大的数据集loss能下降到多少?而且准确率也不会提升。

from arcface-caffe.

Comments (8)

xisi789 avatar xisi789 commented on August 16, 2024

No description provided.

你解决这个问题吗,我也遇到类似的了

from arcface-caffe.

Dian-Yi avatar Dian-Yi commented on August 16, 2024

No description provided.

你解决这个问题吗,我也遇到类似的了

你数据集规模是多大的?我当前20万的人脸已经能训正常,不过400万的脸的不正常

from arcface-caffe.

xisi789 avatar xisi789 commented on August 16, 2024

十万的ID和六百万的人脸

from arcface-caffe.

Dian-Yi avatar Dian-Yi commented on August 16, 2024

十万的ID和六百万的人脸

看来脸多了得要预训练模型慢慢调调,我没用预训练模型,训到一半每个类求得cosin角度都是接近与1,也不知道不知道什么原因造成得?

from arcface-caffe.

Dian-Yi avatar Dian-Yi commented on August 16, 2024

十万的ID和六百万的人脸

你用得什么数据集?这么大?

from arcface-caffe.

xisi789 avatar xisi789 commented on August 16, 2024

几个数据集拼在一起的,能调什么呢,我调学习率已经没啥用了

from arcface-caffe.

Dian-Yi avatar Dian-Yi commented on August 16, 2024

几个数据集拼在一起的,能调什么呢,我调学习率已经没啥用了

m和scale,加个imagenet得预训练模型再试试

from arcface-caffe.

xisi789 avatar xisi789 commented on August 16, 2024

我调小调大m训练情况更差了

from arcface-caffe.

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.