Skip to content

kaggle中的【State Farm Distracted Driver Detection】比赛的实现

Notifications You must be signed in to change notification settings

MLjian/PyTorch_DistractedDriverDetection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 

Repository files navigation

     

PyTorch_DistractedDriverDetection

1 项目概述:

1.1 项目来源:

kaggle中的【State Farm Distracted Driver Detection】比赛的实现。https://www.kaggle.com/c/state-farm-distracted-driver-detection

1.2 问题概述:

对一张关于驾驶员行为的图片进行分类,共10类:安全驾驶/左手打字/右手打电话/左右打电话/...
"example picture"

1.3 问题解决思路:

采用resnet34进行finetune

1.4 数据集下载地址:

https://pan.baidu.com/s/1l2RkXYOAdxuL_jiKWJm1cQ

2 程序运行相关:

2.1 运行环境:

windows/python3.5/pytorch0.4/visdom

2.2 运行前的准备:

s1:下载本repository至本地;
s2:在本目录下,建立文件夹如下,并下载train数据集至data文件夹下:

----data
--train
----trained_models

2.3运行:

s1.打开visdom后台:python -m visdom.server
s2.运行训练文件:python train.py

3 训练过程可视化:



About

kaggle中的【State Farm Distracted Driver Detection】比赛的实现

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages