import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
x_data = np.linspace(-0.5, 0.5, 200)[:, np.newaxis]
noise = np.random.normal(0, 0.02, x_data.shape)
y_data = x_data**2 + noise
x = tf.placeholder(tf.float32, [None, 1])
y = tf.placeholder(tf.float32, [None, 1])
#定义神经网络中间层
Weight_L1 = tf.Variable(tf.random.normal([1, 10])) #input_size and output_size
baise_L1 = tf.Variable(tf.zeros([1, 10]))
Z_L1 = tf.matmul(x, Weight_L1) + baise_L1
A_L1 = tf.nn.tanh(Z_L1)
#定义输出层
Weight_L2 = tf.Variable(tf.random.normal([10, 1]))
biase_L2 = tf.Variable(tf.zeros([1, 1]))
Z_L2 = tf.matmul(A_L1, Weight_L2) + biase_L2
A_L2 = tf.nn.tanh(Z_L2)
loss = tf.reduce_mean((y-A_L2)**2)
train_step = tf.train.GradientDescentOptimizer(learning_rate=0.1).minimize(loss)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for _ in range(2000):
sess.run(train_step, feed_dict={x : x_data, y : y_data})
prediction_value = sess.run(A_L2, feed_dict={x : x_data})
plt.scatter(x_data, y_data)
plt.plot(x_data, prediction_value, 'r-', lw=5)
plt.show()