Giter VIP home page Giter VIP logo

Comments (8)

piaotq avatar piaotq commented on July 18, 2024

楼主 这个是我跑第一个epno的,预训练模型也加载了,我用model summary也看到了,感觉是不是没有起作用
image

from garbage_classify.

wusaifei avatar wusaifei commented on July 18, 2024

@piaotq 你好对于batch_size对分类准确率的影响还是挺大的,我做过实验batch32的效果好于16,16好于8,如果当batch_size的大小小于16时,准确率会下降很快。

from garbage_classify.

wusaifei avatar wusaifei commented on July 18, 2024

第一原因:batch选择的太小,一般情况下batch是16以及以上最佳,不然准确率会下降很多,如果是4的话几乎不可能达到很好的分类结果。第二个原因:默认尺寸是最好的,228太小了失去了很多信息。建议size改成380或者456,batch改成16以及以上,准确率就会上升啦。因为EfficientNet论文指明,尺寸对网络的影响非常大。

from garbage_classify.

piaotq avatar piaotq commented on July 18, 2024

楼主非常感谢你的经验。
我目前的input size是设置为456的,batch size如果要到32的话,16G的显存够用么?我在想租用阿里云的服务器试一下,这方面有啥好的推荐么。
另外昨天那个训练的问题,其实EfficientNetB5(weights='imagenet', 这个里边的下载链接其实失效了,然后我加载错了网络权重的文件。所以昨天晚上我加载了至少我认为正确的权重文件,训练16次就达到了前天30次的指标,今天继续再跑跑结果。
对了EfficientNetB5现在编译好的权重文件有待autoaugment和不带的,用哪个效果会一些呢

image

from garbage_classify.

piaotq avatar piaotq commented on July 18, 2024

楼主 我用nvida的P100跑 16G满了 也跑不到batch size16 能问下你用的是啥配置么?

from garbage_classify.

wusaifei avatar wusaifei commented on July 18, 2024

@piaotq 我之前用的是华为云参加比赛给的云服务器,4个P100是可以跑到32的,尺寸也是456。16G肯定是不够的可能至少需要48G的GPU。IImageNet那个参数可以自己收动下载的,然后读取它就行啦。AutoAugment那个预训练参数不是太好,准确率不是太高建议不要用,对了我记得AutoAugment是B6,B7的时候选用的。

from garbage_classify.

piaotq avatar piaotq commented on July 18, 2024

明白了,感谢哈哈,阿里云我看看怎么安排多GPU的

from garbage_classify.

wusaifei avatar wusaifei commented on July 18, 2024

@piaotq 不客气哈

from garbage_classify.

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.