Giter Club home page Giter Club logo

df-traffic_sign_detect's Introduction

基于RetinaNet检测器作为主干网络检测器来做的,预处理部分主要是对图像作了增强,从原图中扣取出400*400的图进行训练,更容易准确检测到目标。
测试集的话则根据之前比较好的测试结果来进行扣取测试图像。同时可以对多个检测模型的检测结果进行融合,取检测框的交集或者取并集具体根据自己的任务需求而定。
然后就是细致的调参过程了。

对于二阶检测算法不是太熟,尝试了mask RCNN,faster RCNN,可能是没有调好,线上只能调到0.8+,着实是一种遗憾,还是需要更加深入不断的学习。

最后其实关于数据增强方面有尝试随机裁剪原图像,效果应该可以更好,只是策略训练的太晚了,同时感觉对原图加一些图像增强及相关预处理效果可以更好。

总之,参加比赛嘛,一次学习和实践的过程,也着实在这个过程里学习到了不少的东西。分享给大家,交流学习一下

这里简单的补充下程序的使用方法:
首先运行crop_train.py文件,对原训练集进行裁剪,生成了data_train.csv标签文件;
然后运行data路径下的划分验证集和训练集的脚本,然后可以直接运行
Python train.py csv data/train_label.csv data/classes.csv --val_annotations data/val_label.csv. 一般即可正常开始训练。
训练完成后,需要运行crop_test.py对测试集进行裁剪,然后执行Python convert_model.py model1.h5 model2.h5,完成模型的转化才可以用于测试。
最后即可执行test文件,生成结果,并对裁剪后的生成结果进行还原(通过test_crop_result.py脚本),得到最终检测结果。
output路径下的ensemble脚本可以对多个检测结果进行融合。
调参方面需要自己进一步研究看下源码即可。如还存在问题,欢迎一起交流学习

df-traffic_sign_detect's People

Contributors

moyan007 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.