Giter VIP home page Giter VIP logo

cnn_ucmerced-landuse_caffe's Introduction

CNN_UCMerced-LandUse_Caffe

(数据:http://vision.ucmerced.edu/datasets/landuse.html)

主要任务:

基于深度学习框架完成对光学遥感图像UCMerced LandUse数据集的分类。

数据特点:

共包含21类土地类型图片,每类100张,每张像素大小为256*256,数据类内距离大,类间小。

完成情况:

数据量太小,训练数据出现过拟合;为了克服这个问题,又减小训练时间,采用caffe框架,在别人训练好的bvlc_reference_caffenwt模型上进行fine-tune,对最后一层设置较大的学习速率,结果取得了93%的正确率;在这基础上又在fc7层上提取了每张图片的4096维特征,进行了SVM分类,取得了95%以上的分类正确率,并对结果做了可视化分析。

环境:

ubuntu14.04 + caffe + python(数据划分和增强在用windows10的3.5,其余都是unbuntu下用的2.7)

程序(相关路径需要修改)/步骤:

multi_divide_pic.py---多进程进行数据划分(cv2没装成功,建议用cv2,方便)
multi_augmentation_pic.py---多进程数据增强
make_caffe_lmdb.py---生成caffe训练需要的数据路径文件,然后修改caffe配置文件
bvlc_reference_caffenet.caffemodel---caffe模型,在上面进行finetune(http://dl.caffe.berkeleyvision.org/?from=message&isappinstalled=1)
binaryproto2npy.py---将caffe生成的均值文件转换成.npy格式
cnn_vision_caffe.py---对训练好的模型进行可视化分析
extract_features.py---获取每张图片在fc7层输出的4096维特征
svm_predict.py---使用svm对上述提取的特征进行训练预测
svm_vision.py---对svm模型进行可视化分析tsne.py---对数据进行降维可视化

cnn_ucmerced-landuse_caffe's People

Contributors

yangxue0827 avatar

Watchers

James Cloos avatar  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.