TensorFlow技术解析与实战 第8章： 第一个tensor

TensorFlow的运行方式分如下4步：

（1）加载数据及定义超参数

（2）构建网络

（3）训练模型

（4）评估模型和进行预测

---

# -*- coding: utf-8 -*-

import sys

import importlib

importlib.reload(sys)

#sys.setdefaultencoding('utf-8')

import tensorflow as tf

import numpy as np

# y = x^2 - 0.5

# 生成及加载数据

x_data = np.linspace(-1, 1, 300)[:, np.newaxis]  #构建了300个点

noise = np.random.normal(0, 0.05, x_data.shape)  #加入一些噪声点

y_data = np.square(x_data) - 0.5 + noise

xs = tf.placeholder(tf.float32, [None, 1])

ys = tf.placeholder(tf.float32, [None, 1])

# 构建网络模型

# y = weights*x + biases

def add_layer(inputs, in_size, out_size, activation_function=None):

weights = tf.Variable(tf.random_normal([in_size, out_size]))  # in_size * out_size 大小的矩阵

biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)  # 1 X out_size 的矩阵

Wx_plus_b = tf.matmul(inputs, weights) + biases  # 矩阵相乘

if activation_function is None:

outputs = Wx_plus_b

else:

outputs = activation_function(Wx_plus_b)

return outputs

# 构建隐藏层，假设隐藏层有10个神经元

h1 = add_layer(xs, 1, 20, activation_function=tf.nn.relu)

# 构建输出层，假设输出层和输入层一样，有1个神经元

prediction = add_layer(h1, 20, 1, activation_function=None)

# 计算预测值和真实值间的误差

loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))

train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# 训练模型

init = tf.global_variables_initializer()  #初始化所有变量

sess = tf.Session()

sess.run(init)

for i in range(1000):

sess.run(train_step, feed_dict={xs:x_data, ys:y_data})

if i % 50 == 0:

print(sess.run(loss, feed_dict={xs:x_data, ys:y_data}))

---

---