import tensorflow as tf
import numpy as np
def add_layer(inputs, in_size, out_size, activation_function=None):
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]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise
xs = tf.placeholder(tf.float32, [None, 1]) # inputs
ys = tf.placeholder(tf.float32, [None, 1]) # real_outputs
l1 = add_layer(xs, 1, 10, tf.nn.relu) # 隐层
prediction = add_layer(l1, 10, 1) # 预测输出层
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=1)) # 损失
optimizer = tf.train.GradientDescentOptimizer(0.1) # 梯度下降
train = optimizer.minimize(loss)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for steps in range(1000):
sess.run(train, feed_dict={xs: x_data, ys: y_data})
if steps % 50 == 0:
print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))