预览加载中,请您耐心等待几秒...
1/10
2/10
3/10
4/10
5/10
6/10
7/10
8/10
9/10
10/10

亲,该文档总共32页,到这已经超出免费预览范围,如果喜欢就直接下载吧~

如果您无法下载资料,请参考说明:

1、部分资料下载需要金币,请确保您的账户上有足够的金币

2、已购买过的文档,再次下载不重复扣费

3、资料包下载后请先用软件解压,在使用对应软件打开

基于卷积神经网络的花卉图像分类研究 161203107240 · 2020 的基于卷积神经网络的花卉图像 分类研究的研究的 的 的 202051 2020 基于卷积神经网络的花卉图像分类研究 花卉分类图像分类的研究花 的类的分类的研究 的的Oxford17Flowers花卉Python Tensorflow花卉图像分类经神经网络的基卷 积神经网络CNN,图像, 图像分类的的 68%0-16的花卉分类17类花 图像分类Tensorflow卷积神经网络 2020 Studyonflowerimageclassificationbasedonconvolutionalneural network Abstract Flowerclassificationhasalwaysbeenoneoftheimportantresearchpointsofimageclassi- ficationindeeplearning,whichismainlycausedbythesimilarityofflowersandthediffer- encebetweenclasses,andhasalwaysbeentheresearchdirectionofscientists.Thispaper selectsthefamousOxford17FlowersdatasetandUSEStheTensorflowmoduleinPython softwaretorealizetheflowerimageclassificationproblem.Firstly,thispaperconstructs theCNNmodelofconvolutionalneuralnetworkonthebasisofclassicalneuralnetwork toextractthefeaturesoftheimage.Then,thedesignedmodelisusedtoextractthetarget featuresfromcolor,brightness,shapeandotherfeatures,andthegradientdescentalgorithm isusedforimagerecognitionandclassification.Finally,theverificationaccuracyreached 68%,andthedatawereaccuratelyclassifiedaccordingtotheChineseflowernamelabelof 0-16,withatotalof17typesofflowers. Keywords:ImageclassificationTensorflowmoduleConvolutionalneuralnetworkGra- dientdescentalgorithm 2020 12 1.1研究.................................2 1.2研究的.................................2 1.3图像分类研究................................3 2卷积神经网络4 2.1卷积神经网络的基.........................4 2.1.1.................................4 2.1.2.................................5 2.2卷积神经网络................................5 2.2.1............