TensorFlow-建造第一个神经网络

通过TensorFlow，实现一个两层的神经网络拟合二次函数

定义数据

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np

# fake data
x = np.linspace(-1, 1, 100)[:, np.newaxis]          # shape (100, 1)
noise = np.random.normal(0, 0.1, size=x.shape)
y = np.power(x, 2) + noise                          # shape (100, 1) + some noise

# plot data
plt.scatter(x, y)
plt.show()

numpy.linspace( )函数产生等差数列，noise为添加的噪声，使得y不完全拟合二次函数$y = x^2$。

添加占位符用作输入

tf_x = tf.placeholder(tf.float32, x.shape)     # input x
tf_y = tf.placeholder(tf.float32, y.shape)     # input y

添加隐藏层和输出层

# neural network layers
l1 = tf.layers.dense(tf_x, 10, tf.nn.relu)          # hidden layer
output = tf.layers.dense(l1, 1)                     # output layer

计算误差，并利用梯度下降，使其最小

loss = tf.losses.mean_squared_error(tf_y, output)   # compute cost
optimizer = tf.train.GradientDescentOptimizer(0.5)
train_op = optimizer.minimize(loss)  #训练节点

对变量进行初始化

sess = tf.Session()    # control training and others
init = tf.global_variables_initializer()
sess.run(init)         # initialize var in graph

绘制图像

plt.ion()   # something about plotting

for step in range(100):
    # train and net output
    _, l, pred = sess.run([train_op, loss, output], {tf_x: x, tf_y: y})
    if step % 20 == 0:
        # plot and show learning process
        plt.cla()
        plt.scatter(x, y)
        plt.plot(x, pred, 'r-', lw=5)
        plt.text(0.5, 0, 'Loss=%.4f' % l, fontdict={'size': 20, 'color': 'red'})
        plt.pause(0.1)
plt.ioff()
plt.show()

最后一次迭代效果如下图所示：