OGRLayerClassifier

根据机器学习模型和要考虑的功能列表对OGR层进行分类。

描述

该应用程序将对所选要素应用经过训练的机器学习模型,以获得OGR层中包含的每个几何图形的分类。功能列表必须与用于培训的列表匹配。预测标签将写入每个几何图形的用户定义字段中。

参数

Name of the input shapefile -inshp vectorfile Mandatory
Name of the input shapefile

XML file containing mean and variance of each feature -instats filename [dtype] Mandatory
XML file containing mean and variance of each feature.

Input model filename -insvm filename [dtype] Mandatory
Input model filename.

Features -feat string1 string2...
Features to be calculated

Field containing the predicted class -cfield string Default value: predicted
Field containing the predicted class

实例

从命令行执行以下操作:

otbcli_OGRLayerClassifier -inshp vectorData.shp -instats meanVar.xml -insvm svmModel.svm -feat perimeter -cfield predicted

来自Python的评论:

import otbApplication

app = otbApplication.Registry.CreateApplication("OGRLayerClassifier")

app.SetParameterString("inshp", "vectorData.shp")
app.SetParameterString("instats", "meanVar.xml")
app.SetParameterString("insvm", "svmModel.svm")
app.SetParameterStringList("feat", ['perimeter'])
app.SetParameterString("cfield", "predicted")

app.ExecuteAndWriteOutput()

局限性

实验性的。目前仅支持shapefile。