Function nnCostFunction

NeuralNetwok/NeuralNetwork.py:96–130

(nn_params,input_layer_size,hidden_layer_size,num_labels,X,y,Lambda)

# 代价函数
def nnCostFunction(nn_params,input_layer_size,hidden_layer_size,num_labels,X,y,Lambda):
    length = nn_params.shape[0] # theta的中长度
    # 还原theta1和theta2
    Theta1 = nn_params[0:hidden_layer_size*(input_layer_size+1)].reshape(hidden_layer_size,input_layer_size+1)
    Theta2 = nn_params[hidden_layer_size*(input_layer_size+1):length].reshape(num_labels,hidden_layer_size+1)
    
    # np.savetxt("Theta1.csv",Theta1,delimiter=',')
    
    m = X.shape[0]
    class_y = np.zeros((m,num_labels))      # 数据的y对应0-9，需要映射为0/1的关系
    # 映射y
    for i in range(num_labels):
        class_y[:,i] = np.int32(y==i).reshape(1,-1) # 注意reshape(1,-1)才可以赋值
     
    '''去掉theta1和theta2的第一列，因为正则化时从1开始'''    
    Theta1_colCount = Theta1.shape[1]    
    Theta1_x = Theta1[:,1:Theta1_colCount]
    Theta2_colCount = Theta2.shape[1]    
    Theta2_x = Theta2[:,1:Theta2_colCount]
    # 正则化向theta^2
    term = np.dot(np.transpose(np.vstack((Theta1_x.reshape(-1,1),Theta2_x.reshape(-1,1)))),np.vstack((Theta1_x.reshape(-1,1),Theta2_x.reshape(-1,1))))
    
    '''正向传播,每次需要补上一列1的偏置bias'''
    a1 = np.hstack((np.ones((m,1)),X))      
    z2 = np.dot(a1,np.transpose(Theta1))    
    a2 = sigmoid(z2)
    a2 = np.hstack((np.ones((m,1)),a2))
    z3 = np.dot(a2,np.transpose(Theta2))
    h  = sigmoid(z3)    
    '''代价'''    
    J = -(np.dot(np.transpose(class_y.reshape(-1,1)),np.log(h.reshape(-1,1)))+np.dot(np.transpose(1-class_y.reshape(-1,1)),np.log(1-h.reshape(-1,1)))-Lambda*term/2)/m   
    #temp1 = (h.reshape(-1,1)-class_y.reshape(-1,1))
    #temp2 = (temp1**2).sum()
    #J = 1/(2*m)*temp2
    return np.ravel(J)

# 梯度
def nnGradient(nn_params,input_layer_size,hidden_layer_size,num_labels,X,y,Lambda):