Giter Site home page Giter Site logo

junwenzhang / garbage_calssify-by-resnet50- Goto Github PK

View Code? Open in Web Editor NEW

This project forked from qmh1234567/garbage_calssify-by-resnet50-

0.0 1.0 0.0 111.01 MB

使用迁移学习将resnet50用于垃圾分类,基于【华为云人工智能大赛·垃圾分类挑战杯】

Shell 1.59% Python 98.41%

garbage_calssify-by-resnet50-'s Introduction

garbage_calssify-by-resnet50-

根据该项目修改了预处理方式,并用了其中的一些小tricks:比如label smooth,random crop等。测试的地方使用了random crop,然后集成。

项目描述

  1. 任务是对垃圾图片进行分类,即首先识别出垃圾图片中物品的类别(比如易拉罐、果皮等),然后查询垃圾分类规则,输出该垃圾图片中物品属于可回收物、厨余垃圾、有害垃圾和其他垃圾中的哪一种。垃圾类别共40类。
  2. 训练数据集下载地址

准确率

  1. 在官方测试集上有0.893513。
  2. 我们团队也在网站上收集了每类20张左右的垃圾图片,共40类,800张。在该测试集上,模型准确率有0.86125。测试集名字是test_data。

改进过程

模型名称 主要内容 训练轮次 得分
官方baseline Resnet50 50 67
model1 数据集进行图片增强,添加dropout 50 77
model2 在model1的基础上,增加迁移学习和微调 3 71
model3 在model2的基础上,修改预处理方式(采用resnet50自带的) 5 85
model4 在model3的基础上,进行图片增广,每类1000张左右 5 85
model5 在model4的基础上修改预处理方式(resize成( 256,256)),并将图片增强和图片遮挡写入代码 5 89

总结

在该项目中,主要使用迁移学习将resnet50用于垃圾分类,迁移学习可以大大地节约训练时间,并在短时间内达到更高的准确率。这个分数是在我们团队努力一周改进后的结果,希望能对您有参考价值。该结果并不完美,还有很大的改进空间,下一步将继续对该项目进行改进,争取提高准确率。

garbage_calssify-by-resnet50-'s People

Contributors

qmh1234567 avatar

Watchers

James Cloos avatar

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.