第一次实现单层神经网络

看了吴恩达的课程，按他的公式做了一下编程练习。

题目是训练209*64*64*3的209张图片，再预测50*64*64*3的50张图片。

代码如下：

import numpy as npimport h5py    #加载数据集def load_dataset():    train_dataset = h5py.File('datasets/train_catvnoncat.h5', "r")    train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features    train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels    test_dataset = h5py.File('datasets/test_catvnoncat.h5', "r")    test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features    test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels    classes = np.array(test_dataset["list_classes"][:]) # the list of classes        train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))    test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))        return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes#激活函数activition functiondef ReLU(z):    mz,nz = z.shape    zero = np.zeros((mz,nz))    return np.maximum(zero,z)#RuntimeWarning: overflow encountered in expdef sigmoid(z):    return 1.0/(1+np.exp(-z))#将4维数组转换为2维def transformArray(inX):    shape = inX.shape    shape1 = shape[1]*shape[2]*shape[3]    transformedX = np.mat(np.zeros((shape1,shape[0])))    for i,item in enumerate(inX):        transformedItem = item.flatten().reshape(-1,1)        transformedX[:,i] = transformedItem    return transformedX#损失函数def lossFunc(A,y_train):    pass    #单层神经网络class myOneLNN:    def __init__(self,W1,b1,alpha,af,iterNum):        self.W = W1        self.b = b1        self.af = af        self.iterNum = iterNum        self.alpha = alpha            def trainFunc(self,X_train,y_train):        m = X_train.shape[1]        X = X_train        Y = y_train        Z = self.W*X + self.b        for i in range(iterNum):                    Z = self.W*X + self.b#            Z1 = np.dot(self.W,X)+b#            print(Z1.shape)            A = self.af(Z)              dZ = A - Y            dW =  dZ*X.T/m            db = np.sum(dZ)/m            self.W -= self.alpha*dW            self.b -= self.alpha*db        return self.W,self.b        def predictFunc(self,X_test):        Z_pred = self.W*X_test + self.b        '''此处为什么A_pred和y_pred是一样的？'''        A_pred = self.af(Z_pred)#        print(A_pred)        y_pred = np.zeros(A_pred.shape)        y_pred[0,np.nonzero(A_pred>0.5)[1]] = 1.0        return y_pred        def testErrors(self,y_test,y_pred):        m = y_test.shape[1]        errors = len(np.nonzero(y_test!=y_pred)[0])        errorRate = errors*1.0/m#        print('the total error number is: %d'%errors)#        print('the error rate is: %.2f'%errorRate)        return errorRateX_train,y_train,X_test,y_test,classes = load_dataset()#将数据集转换为2维:是否有更好的方法？X_train_transformed = transformArray(X_train)X_test_transformed = transformArray(X_test)L = 1       #1 layersn0 = X_train_transformed.shape[0]      #输入样本的维度m = X_train_transformed.shape[1]        #训练样本个数为mn1 = 1                                  #输出层单元数为1个W1 = np.random.randn(n1,n0)*0.001            #随机初始化W'''按公式，此处b和m有关，但测试集的m和训练集的m不相等，运行会出错个人觉得b的shape应该是(ni*1),ni为第i层单元的个数'''#b1 = np.zeros((n1,m))                   #b可以初始化为0b1 = 0iterNum = 500#交叉验证errList = []for i in range(10):    oneLNN = myOneLNN(W1,b1,alpha=0.001,af=sigmoid,iterNum=iterNum)    W,b = oneLNN.trainFunc(X_train_transformed,y_train)    y_pred = oneLNN.predictFunc(X_test_transformed)    errorRate = oneLNN.testErrors(y_test,y_pred)    errList.append(errorRate)print(errList)print(np.mean(errList))

单层神经网络的错误率为28%，遇到np.exp计算溢出的问题，暂时找不到好的解决方案。有任何问题欢迎交流。