简单的Tensorflow实现NN

# coding:utf-8'''Student: Danny HouDate: 2017-06-14Content:简单的神经网络练习'''import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt# def add layer, it would be very convenient that you build a CNN when adding a layerdef add_layer(inputs,in_size,out_size,activation_function=None):    Weights = tf.Variable(tf.random_normal([in_size,out_size])) # 初始化weight，为什么不用0？据说是效果不好。    biases = tf.Variable(tf.zeros(shape=[1,out_size])+0.1) # 初始化又不为0，据说是推荐这个值！！    Wx_plus_b = tf.matmul(inputs,Weights)+biases    if activation_function is None:        outputs = Wx_plus_b    else:        outputs=activation_function(Wx_plus_b)    return outputs# 开始捏造数据X = np.linspace(-1,1,3000,dtype=np.float32)[:, np.newaxis] # newaxis 就是把横变成竖的吧，（3000，1）noise = np.random.normal(0,0.05,X.shape).astype(np.float32) # 加点酌料，搞乱原本的数据，更接近现实y = np.square(X) - 0.5 + noise # y已经被搞乱了 :-P# 可以看下数据的情况fig = plt.figure()ax = fig.add_subplot(1,1,1) # 一行，一列，第一个ax.scatter(X,y)plt.ion() # 用于连续显示plt.show()# 定义占位符，我感觉是传入参数的定义，个人理解 :-Pxs = tf.placeholder(tf.float32,[None,1]) # None 代表N个，N到底是多少个？ys = tf.placeholder(tf.float32,[None,1])# 神经网络有多层，大致可以分为：输入层、隐藏层和输出层。# 这里定义隐藏层，xs为接收到的输入矩阵，1就是只有一个神经元（一个特征？），10代表输出给隐藏层有10个神经元，激活函数用relu。# xs为输入层l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)# l2 = add_layer(l1,10,15,activation_function=tf.nn.relu)# l3 = add_layer(l2,15,10,activation_function=tf.nn.relu)# 定义输出层,prediction = add_layer(l1, 10, 1, activation_function=None)# 定义loss/cost function,由于这里的问题是回归问题，所以一般都会用MSE（应该没有写错吧）loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))# 定义训练步骤train_step = tf.train.GradientDescentOptimizer(learning_rate=0.1).minimize(loss=loss)# 所有变量和步骤都定义好了，开始初始化init = tf.global_variables_initializer()sess = tf.Session()sess.run(init)# 定制训练次数并为模型传入对应的数据for i in range(1000):    sess.run(train_step,feed_dict={xs:X,ys:y})    if i % 50 ==0:        print(sess.run(loss,feed_dict={xs:X,ys:y}))        try:            ax.lines.remove(lines[0])        except Exception:            pass        prediction_value = sess.run(prediction,feed_dict={xs:X})        lines = ax.plot(X,prediction_value,'r-',lw=5)        plt.pause(0.5)

loss
0.188886
0.0142108
0.0086079
0.00696789
0.00589828
0.00524938
0.00492084
0.00475221
0.00464395
0.00456124
0.00449256
0.00442923
0.0043689
0.00431515
0.00426623
0.00422012
0.00417505
0.00413331
0.00409412
0.00405706
拟合过程：