if __name__ == '__main__':
#step1 参数初始化
inputSize = 28 * 28
numClasses = 5
hiddenSize = 200
sparsityParam = 0.1
la = 3e-3
beta = 3
#step2 获取无标签数据集, 有标签训练数据集, 有标签测试数据集
unlabeledData, trainData, trainLabels, testData, testLabels = GetDivideSets(
)
#step3 用无标签数据集训练自编码的特征
theta = sparseAutoencoder.initiallize(hiddenSize, inputSize)
[X,cost,d]=sop.fmin_l_bfgs_b(lambda (x) :sparseAutoencoder.sparseAutoencoderCost(x, inputSize, \
hiddenSize, la, sparsityParam, beta, unlabeledData),x0=theta,maxiter=400,disp=1)
W1 = X[0:hiddenSize * inputSize].reshape(hiddenSize, inputSize)
W1 = W1.T
opttheta = X
#step4 获得有标签训练集的激活值并用来训练softmax分类器的权值
trainImages = feedforward(opttheta, hiddenSize, inputSize, trainData)
thetaSoftmax = softmax.initiallize(numClasses, hiddenSize)
la = 1e-4
[X, cost, d] = sop.fmin_l_bfgs_b(lambda (x): softmax.SoftmaxCost(
trainImages, trainLabels, x, la, hiddenSize, numClasses),
x0=thetaSoftmax,
maxiter=100,
disp=1)
if __name__ == '__main__':
#step1 两层隐含层的栈式神经网络的参数设置
inputSize = 28 * 28
numClasses = 10
hiddenSizeL1 = 200
hiddenSizeL2 = 200
sparsityParam = 0.1
la = 3e-3
beta = 3
#step2 读取MNIST数据集,只取1/3的数据集防止内存溢出
trainData, trainLabels, testData, testLabels = ReadMNIST()
length = trainData.shape[1] / 3
trainData = trainData[:, 0:length]
trainLabels = trainLabels[0:length]
sae1Theta = sparseAutoencoder.initiallize(hiddenSizeL1, inputSize)
#step3 训练第一层神经网络的权值
[sae1OptTheta, cost, d]=sop.fmin_l_bfgs_b(lambda (x) :sparseAutoencoder.sparseAutoencoderCost(x, inputSize, \
hiddenSizeL1, la, sparsityParam, beta, trainData),x0=sae1Theta,maxiter=400,disp=1)
sae1Features = feedforward(sae1OptTheta, hiddenSizeL1, inputSize,
trainData)
#step4 训练第二层神经网络的权值
sae2Theta = sparseAutoencoder.initiallize(hiddenSizeL2, hiddenSizeL1)
[sae2OptTheta, cost, d]=sop.fmin_l_bfgs_b(lambda (x) : sparseAutoencoder.sparseAutoencoderCost(x, hiddenSizeL1, \
hiddenSizeL2, la, sparsityParam, beta, sae1Features),x0=sae2Theta, maxiter=400,disp=1)
sae2Features = feedforward(sae2OptTheta, hiddenSizeL2, hiddenSizeL1,
sae1Features)
#step5 训练softmax权值
if __name__ == '__main__':
#step1 参数初始化
inputSize = 28*28
numClasses = 5
hiddenSize = 200
sparsityParam = 0.1
la = 3e-3
beta = 3
#step2 获取无标签数据集, 有标签训练数据集, 有标签测试数据集
unlabeledData, trainData, trainLabels, testData, testLabels = GetDivideSets()
#step3 用无标签数据集训练自编码的特征
theta = sparseAutoencoder.initiallize(hiddenSize, inputSize)
[X,cost,d]=sop.fmin_l_bfgs_b(lambda (x) :sparseAutoencoder.sparseAutoencoderCost(x, inputSize, \
hiddenSize, la, sparsityParam, beta, unlabeledData),x0=theta,maxiter=400,disp=1)
W1 = X[0:hiddenSize*inputSize].reshape(hiddenSize, inputSize)
W1 = W1.T
opttheta = X
#step4 获得有标签训练集的激活值并用来训练softmax分类器的权值
trainImages = feedforward(opttheta, hiddenSize, inputSize, trainData)
thetaSoftmax = softmax.initiallize(numClasses, hiddenSize)
la = 1e-4
[X,cost,d] = sop.fmin_l_bfgs_b(lambda (x) :softmax.SoftmaxCost(trainImages, trainLabels,x,la,hiddenSize,numClasses),x0=thetaSoftmax,maxiter=100,disp=1)
#step5 获得有标签测试集的激活值并且给出softmax分类准确率, 5分类的准确率应该在98%附近
testImages = feedforward(opttheta, hiddenSize, inputSize, testData)
optthetaSoftmax = X
if __name__ == '__main__':
#step1 两层隐含层的栈式神经网络的参数设置
inputSize = 28*28
numClasses = 10
hiddenSizeL1 = 200
hiddenSizeL2 = 200
sparsityParam = 0.1
la = 3e-3
beta = 3
#step2 读取MNIST数据集,只取1/3的数据集防止内存溢出
trainData, trainLabels, testData, testLabels = ReadMNIST()
length = trainData.shape[1]/3
trainData = trainData[:, 0:length]
trainLabels = trainLabels[0:length]
sae1Theta = sparseAutoencoder.initiallize(hiddenSizeL1, inputSize)
#step3 训练第一层神经网络的权值
[sae1OptTheta, cost, d]=sop.fmin_l_bfgs_b(lambda (x) :sparseAutoencoder.sparseAutoencoderCost(x, inputSize, \
hiddenSizeL1, la, sparsityParam, beta, trainData),x0=sae1Theta,maxiter=400,disp=1)
sae1Features = feedforward(sae1OptTheta, hiddenSizeL1, inputSize, trainData)
#step4 训练第二层神经网络的权值
sae2Theta = sparseAutoencoder.initiallize(hiddenSizeL2, hiddenSizeL1)
[sae2OptTheta, cost, d]=sop.fmin_l_bfgs_b(lambda (x) : sparseAutoencoder.sparseAutoencoderCost(x, hiddenSizeL1, \
hiddenSizeL2, la, sparsityParam, beta, sae1Features),x0=sae2Theta, maxiter=400,disp=1)
sae2Features = feedforward(sae2OptTheta, hiddenSizeL2, hiddenSizeL1, sae1Features)
#step5 训练softmax权值
saeSoftmaxTheta = softmax.initiallize(numClasses, hiddenSizeL2)
laSoftmax = 1e-4