import tensorflow as tf 
import numpy as np
import matplotlib.pyplot as plt
def add_layer(inputs,in_size,out_size,activation_function=None):
    #以高斯分布出现随机矩阵
    Weights = tf.Variable(tf.random_normal([in_size,out_size]))
    biases = tf.Variable(tf.zeros([1,out_size])+0.1)
    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

x_data = np.linspace(-1,1,300)#[:,np.newaxis]
x_data = x_data.reshape(300,1)
#print(x_data.shape)#(300,1)300行1列
noise = np.random.normal(0,0.5,x_data.shape)
y_data = np.square(x_data)-0.5+noise
#prediction = y_data-2
#预定位置，后面输入
xs = tf.placeholder(tf.float32,[None,1])
ys = tf.placeholder(tf.float32,[None,1])

l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=None)

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
#梯度下降步长为0.1，即学习率 
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
init = tf.global_variables_initializer()#全局初始化
sess = tf.Session()
sess.run(init)

fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()
plt.show()
for i in range(1000):
    #批量梯度下降训练
    sess.run(train_step,feed_dict = {xs:x_data,ys:y_data})
    if i%50 == 0:
        #每50次检查loss下降多少
        #print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
        try:
            ax.lines.remove(lines[0])
        except Exception:
            pass
        prediction_value = sess.run(prediction,feed_dict={xs:x_data})
        lines = ax.plot(x_data,prediction_value,'r-',lw=5)
        
        plt.pause(0.1)


#loss = tf.square(y_data-prediction)
#print(loss.shape)#300行一列(300,1)
#loss = tf.reduce_sum(tf.square(y_data-prediction),reduction_indices=[1])
#print(loss.shape)#(300,)
#loss = tf.reduce_mean(tf.reduce_sum(tf.square(y_data-prediction),reduction_indices=[1]))
#sess = tf.Session()
#print(sess.run(loss))