Giter Club home page Giter Club logo

fashionai_tianchi_2018's Introduction


环境

  • ubuntu16.04/windows10
  • python 3.6.2
  • keras 2.1.6
  • tensroflow 1.8.0
  • opencv-python 3.4
  • imgaug 0.2.5

使用

  • 因为懒,代码写完就跑,跑完就算,没怎么优化与封装
  • config.py-------------配置了样本目录等信息
  • cal_std_mean.py------计算数据集的std与mean
  • Multitask_train.py----训练脚本
  • Multitask_predict-----预测脚本
  • dataset.py------------数据预处理
  • inceptionv4.py--------Inceptionv4模型API
  • 这里下载数据集,解压到datasets文件夹下,就可以执行python Multitask_train.py进行训练了

思路分享

  • 迁移学习+多任务学习+模型融合
  • 分别设计了两个多任务模型结构如下:
    • 长度类别多输出模型:
    • 领子类别多输出模型:
  • 融合Inceptionv4与Inceptionresnetv2,分别进行预测再对结果做平均
  • 对测试集样本进行增广

提高分数的技巧

  • shuffle很重要
  • 多任务学习比单任务学习成绩提高1-2%
  • 合适的图像增广,推荐使用imgaug,功能强大。dataset.py有详细代码,能提高2-3%
  • 图像标准化,计算本数据集的std与mean,而不是直接用imagenet的std与mean,提高0.5-1%
  • 增大图像输入尺寸可提高分类准确率,提高1-2%
  • finetune,算力允许的前提下finetune整个模型,对比只训练最后一层提高3-5%
  • 使用Adam先快速收敛,再用SGD慢慢调,效率会比较高
  • 模型融合,提高1-2%
  • 对测试集进行增广,本例选择了镜像,加上旋转5、10、15度进行预测,最后再取平均,提高0.5-1%

fashionai_tianchi_2018's People

Contributors

jeremyczhj 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.