TensorFlow入门教程系列(二)：用神经网络拟合二次函数

通过TensorFlow用神经网络实现对二次函数的拟合。代码来自莫烦TensorFlow教程。

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

# Make up some real data
x_data = np.linspace(-1, 1, 300, dtype=np.float32)[:, np.newaxis]   # np.newaxis的作用就是在它所在的位置增加一个一维
noise = np.random.normal(0, 0.05, x_data.shape).astype(np.float32)
y_data = np.square(x_data) - 0.5 + noise

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])
# add hidden layer
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# add output layer
prediction = add_layer(l1, 10, 1, activation_function=None)

# the error between prediction and real data
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
# important step
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)

for i in range(500):
    # training
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        # to see the step improvement
        print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))

运行结果：

0.3695223
0.03633204
0.07279602
0.008672798
0.0063357423
0.0055126143
0.004952927
0.0045463713
0.0041970443
0.0038996863