Spark MLlib Deep Learning Deep Belief Network (深度学习-深度信念网络)2.3

Spark MLlib Deep Learning Deep Belief Network (深度学习-深度信念网络)2.3

http://blog.csdn.net/sunbow0

第二章Deep Belief Network (深度信念网络)

实例

3.1 測试数据

依照上例数据，或者新建图片识别数据。

3.2 DBN实例

（读取固定样本:来源于经典优化算法測试函数Sphere
Model）***********//

//2 读取样本数据

Logger.getRootLogger.setLevel(Level.WARN)

valdata_path ="/user/huangmeiling/deeplearn/data1"

valexamples =sc.textFile(data_path).cache()

valtrain_d1 =examples.map { line =>

valf1 = line.split("\t")

valf =f1.map(f =>f.toDouble)

)

))

,f.length)

(,y.length,y),new
BDM(,x.length,x))

}

valtrain_d =train_d1.map(f => (f._2,
f._3))

valopts = Array(100.0,20.0,0.0)

//3 设置训练參数，建立DBN模型

valDBNmodel =new DBN().

setSize(Array(,
)).

setLayer().

setMomentum(0.1).

setAlpha(1.0).

DBNtrain(train_d,
opts)

//4 DBN模型转化为NN模型

)

valnnopts = Array(100.0,50.0,0.0)

valnumExamples =train_d.count()

println(s"numExamples = $numExamples.")

println(mynn._2)

tomynn._1.length
-) {

print(mynn._1(i) +"\t")

}

println()

println("mynn_W1")

)

totmpw1.rows
-) {

totmpw1.cols
-) {

print(tmpw1(i,j) +"\t")

}

println()

}

valNNmodel =new NeuralNet().

setSize(mynn._1).

setLayer(mynn._2).

setActivation_function("sigm").

setOutput_function("sigm").

setInitW(mynn._3).

NNtrain(train_d,
nnopts)

//5 NN模型測试

valNNforecast =NNmodel.predict(train_d)

valNNerror =NNmodel.Loss(NNforecast)

println(s"NNerror = $NNerror.")

),
f.)

println("预測结果——实际值：预測值：误差")

untilprintf1.length)

println(printf1(i)._1 +"\t"
+printf1(i)._2 +"\t"
+ (printf1(i)._2 -printf1(i)._1))

转载请注明出处：

http://blog.csdn.net/sunbow0