用tensorflow搭建一个神经网络

代码参考这里的大佬教程

import tensorflow as tf
import numpy as np

# 添加一个神经层


def add_layer(inputs, in_size, out_size, activation_function=None):
    # 权重生成
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    # 偏置值生成
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    # 计算输入
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    # 激活函数激活
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    # 返回输出
    return outputs


# 模拟导入数据
# linspace生成等差数列
x_data = np.linspace(-1, 1, 300, dtype=np.float32)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape).astype(np.float32)
y_data = np.square(x_data) - 0.5 + noise

# 定义tf占位符，这里的None代表无论输入有多少都可以，因为输入只有一个特征，所以这里是1
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

# 搭建网络
# 定义隐层
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
# 定义输出层
prediction = add_layer(l1, 10, 1, activation_function=None)
# 误差值计算，此处为均方误差
loss = tf.reduce_mean(tf.reduce_sum(
    tf.square(ys - prediction), reduction_indices=[1]))#reduction_indices=[1]是按行求和，即原来有几行就有几个输出，0则是列

#定义学习算法与误差
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

#初始化数据
init = tf.global_variables_initializer() 
#创建会话
sess = tf.Session()
sess.run(init)

#训练1000轮
# for i in range(1000):
#     # 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}))

import matplotlib.pyplot as plt

# plot the real data
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data, y_data)
plt.ion()#本次运行请注释，全局运行不要注释
plt.show()

for i in range(1000):
    # training
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
    if i % 50 == 0:
        # to visualize the result and improvement
        try:
            ax.lines.remove(lines[0])
        except Exception:
            pass
        prediction_value = sess.run(prediction, feed_dict={xs: x_data})
        # plot the prediction
        lines = ax.plot(x_data, prediction_value, 'r-', lw=5)
        plt.pause(0.5)