public ClassifierTheta(int FeatureLength, int CatSize) {
CatSize--;
this.FeatureLength = FeatureLength;
this.CatSize = CatSize;
W = DoubleMatrix.rand(FeatureLength, CatSize).subi(0.5);
b = DoubleMatrix.rand(CatSize, 1).subi(0.5);
Theta = new double[FeatureLength * CatSize + CatSize];
flatten();
}
public static void main(String argv[]) {
modshogun.init_shogun_with_defaults();
int dim = 7;
DoubleMatrix data = DoubleMatrix.rand(dim, dim);
RealFeatures feats = new RealFeatures(data);
DoubleMatrix data_T = data.transpose();
DoubleMatrix symdata = data.add(data_T);
int cols = (1 + dim) * dim / 2;
DoubleMatrix lowertriangle = DoubleMatrix.zeros(1, cols);
int count = 0;
for (int i = 0; i < dim; i++) {
for (int j = 0; j < dim; j++) {
if (j <= i) {
lowertriangle.put(0, count++, symdata.get(i, j));
}
}
}
CustomKernel kernel = new CustomKernel();
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle);
DoubleMatrix km_triangletriangle = kernel.get_kernel_matrix();
kernel.set_triangle_kernel_matrix_from_full(symdata);
DoubleMatrix km_fulltriangle = kernel.get_kernel_matrix();
kernel.set_full_kernel_matrix_from_full(data);
DoubleMatrix km_fullfull = kernel.get_kernel_matrix();
modshogun.exit_shogun();
}
protected void applyDropOutIfNecessary(DoubleMatrix input) {
if (dropOut > 0) {
this.doMask = DoubleMatrix.rand(input.rows, input.columns).gt(dropOut);
} else this.doMask = DoubleMatrix.ones(input.rows, input.columns);
// actually apply drop out
input.muli(doMask);
}
/** 训练模型 */
private void train() {
printInfo("训练数据载入完毕，开始训练模型………………训练数据规模" + train_set.rows + "x" + train_set.columns);
// 输入矩阵初始化 横向即每列为一组输入
/*
* 4 8 …… N
*
* 1 5 …… N
* 2 6 …… N
* 3 7 …… N
*/
P = new DoubleMatrix(NumberofInputNeurons, train_data_Count);
// 测试机输出矩阵 横向
T = new DoubleMatrix(NumberofOutputNeurons, train_data_Count);
// 初始化
for (int i = 0; i < train_data_Count; i++) {
for (int j = 0; j < totalColCount; j++) {
if (j < NumberofInputNeurons) {
// 输入部分
P.put(j, i, train_set.get(i, j));
} else {
T.put(j - NumberofInputNeurons, i, train_set.get(i, j));
}
}
}
printInfo("训练矩阵初始化完毕………………开始隐含层神经元权重与阈值");
// end 初始化
long start_time_train = System.currentTimeMillis();
// 随机初始化输入权值矩阵
// 行数为隐含层神经元个数，列数为输入层神经元
/**
* W11 W12 W13(第一个隐含神经元对应各输入的权值) W21 W22 W23(第二个隐含神经元对应各输入的权值) ………………………………(第N个隐含神经元对应各输入的权值)
*/
InputWeight = DoubleMatrix.rand(NumberofHiddenNeurons, NumberofInputNeurons);
// 初始化阈值
BiasofHiddenNeurons = DoubleMatrix.rand(NumberofHiddenNeurons, 1);
printInfo("隐含层神经元权重与阈值初始化完毕………………开始计算输入权重");
DoubleMatrix tmpH = new DoubleMatrix(NumberofHiddenNeurons, train_data_Count);
tmpH = InputWeight.mmul(P);
printInfo("输入矩阵计算权重完毕………………开始计算输入权重");
// 加阈值
// 注意横向问题
for (int i = 0; i < NumberofHiddenNeurons; i++) {
for (int j = 0; j < train_data_Count; j++) {
tmpH.put(i, j, tmpH.get(i, j) + BiasofHiddenNeurons.get(i, 0));
}
}
printInfo("输入矩阵计算阈值完毕………………开始计算输入激活函数");
// 输出矩阵
DoubleMatrix H = new DoubleMatrix(NumberofHiddenNeurons, train_data_Count);
if (func.startsWith("sig")) {
for (int i = 0; i < NumberofHiddenNeurons; i++) {
for (int j = 0; j < train_data_Count; j++) {
double tmp = tmpH.get(i, j);
tmp = 1.0f / (1 + Math.exp(-tmp));
H.put(i, j, tmp);
}
}
} else {
throw new IllegalArgumentException("不支持的激活函数类型");
}
printInfo("输出矩阵计算激活函数完毕，开始求解广义逆………………矩阵规模" + H.columns + "x" + H.rows);
// 将H转置
DoubleMatrix Ht = H.transpose();
// 求广义逆
DoubleMatrix Ht_MP = getMPMatrix(Ht);
printInfo("输出矩阵广义逆求解完毕………………开始求解输出矩阵权重");
// 隐含层输出权重矩阵= Ht_MP * Tt
OutputWeight = Ht_MP.mmul(T.transpose());
printInfo("输出矩阵权重求解完毕………………");
long end_time_train = System.currentTimeMillis();
TrainingTime = (end_time_train - start_time_train) * 1.0f / 1000;
printInfo("模型训练完毕………………开始评估模型");
// 误差评估
DoubleMatrix Yt = new DoubleMatrix(train_data_Count, NumberofOutputNeurons);
Yt = Ht.mmul(OutputWeight);
double MSE = 0;
printInfo("共有" + NumberofOutputNeurons + "个输出值");
for (int out = 0; out < NumberofOutputNeurons; out++) {
printInfo("计算第" + (out + 1) + "个输出值");
double mseTem = 0.0;
for (int i = 0; i < train_data_Count; i++) {
System.out.println(Yt.get(i, out) + " " + T.get(out, i));
mseTem += (Yt.get(i, out) - T.get(out, i)) * (Yt.get(i, out) - T.get(out, i));
}
printInfo(
"第" + NumberofOutputNeurons + "个输出值计算完毕,MSE=" + Math.sqrt(mseTem / train_data_Count));
MSE += mseTem;
}
TrainingAccuracy = Math.sqrt(MSE / train_data_Count);
printInfo("模型评估完毕………………");
}
