3 初识TensorFlow

搭建解决三好学生成绩问题的神经网络

3.1 score1a
程序：

import tensorflow as tf
#德、智、体数值输入
x1 = tf.placeholder(dtype=tf.float32)
x2 = tf.placeholder(dtype=tf.float32)
x3 = tf.placeholder(dtype=tf.float32)
#权重
w1 = tf.Variable(0.1, dtype=tf.float32)
w2 = tf.Variable(0.1, dtype=tf.float32)
w3 = tf.Variable(0.1, dtype=tf.float32)
#定义隐藏层节点
n1 = x1 * w1
n2 = x2 * w2
n3 = x3 * w3
#定义输出层
y = n1 + n2 + n3

sess = tf.Session()
#初始化所有可变参数
init = tf.global_variables_initializer()
sess.run(init)
#计算一次神经网络
result = sess.run([x1, x2, x3, w1, w2, w3, y], feed_dict={x1: 90, x2: 80, x3: 70})
print(result)

结果：

[array(90., dtype=float32), array(80., dtype=float32), array(70., dtype=float32), 0.1, 0.1, 0.1, 24.0]

训练神经网络

3.2 score1b
程序：

import tensorflow as tf

x1 = tf.placeholder(dtype=tf.float32)
x2 = tf.placeholder(dtype=tf.float32)
x3 = tf.placeholder(dtype=tf.float32)
yTrain = tf.placeholder(dtype=tf.float32)

w1 = tf.Variable(0.1, dtype=tf.float32)
w2 = tf.Variable(0.1, dtype=tf.float32)
w3 = tf.Variable(0.1, dtype=tf.float32)

n1 = x1 * w1
n2 = x2 * w2
n3 = x3 * w3

y = n1 + n2 + n3

loss = tf.abs(y - yTrain)

optimizer = tf.train.RMSPropOptimizer(0.001)

train = optimizer.minimize(loss)

sess = tf.Session()

init = tf.global_variables_initializer()

sess.run(init)

result = sess.run([train, x1, x2, x3, w1, w2, w3, y, yTrain, loss], feed_dict={x1: 90, x2: 80, x3: 70, yTrain: 85})
print(result)

result = sess.run([train, x1, x2, x3, w1, w2, w3, y, yTrain, loss], feed_dict={x1: 98, x2: 95, x3: 87, yTrain: 96})
print(result)

结果：

[None, array(90., dtype=float32), array(80., dtype=float32), array(70., dtype=float32), 0.1, 0.1, 0.1, 24.0, array(85., dtype=float32), 61.0]
[None, array(98., dtype=float32), array(95., dtype=float32), array(87., dtype=float32), 0.10316052, 0.10316006, 0.103159375, 28.884804, array(96., dtype=float32), 67.1152]

多轮训练

3.3 score1c
程序：

import tensorflow as tf

x1 = tf.placeholder(dtype=tf.float32)
x2 = tf.placeholder(dtype=tf.float32)
x3 = tf.placeholder(dtype=tf.float32)
yTrain = tf.placeholder(dtype=tf.float32)

w1 = tf.Variable(0.1, dtype=tf.float32)
w2 = tf.Variable(0.1, dtype=tf.float32)
w3 = tf.Variable(0.1, dtype=tf.float32)

n1 = x1 * w1
n2 = x2 * w2
n3 = x3 * w3

y = n1 + n2 + n3

loss = tf.abs(y - yTrain)

optimizer = tf.train.RMSPropOptimizer(0.001)

train = optimizer.minimize(loss)

sess = tf.Session()

init = tf.global_variables_initializer()

sess.run(init)

for i in range(2):
    result = sess.run([train, x1, x2, x3, w1, w2, w3, y, yTrain, loss], feed_dict={x1: 90, x2: 80, x3: 70, yTrain: 85})
    print(result)

    result = sess.run([train, x1, x2, x3, w1, w2, w3, y, yTrain, loss], feed_dict={x1: 98, x2: 95, x3: 87, yTrain: 96})
    print(result)

结果：

[None, array(90., dtype=float32), array(80., dtype=float32), array(70., dtype=float32), 0.1, 0.1, 0.1, 24.0, array(85., dtype=float32), 61.0]
[None, array(98., dtype=float32), array(95., dtype=float32), array(87., dtype=float32), 0.10316052, 0.10316006, 0.103159375, 28.884804, array(96., dtype=float32), 67.1152]
[None, array(90., dtype=float32), array(80., dtype=float32), array(70., dtype=float32), 0.10554425, 0.10563005, 0.1056722, 25.346441, array(85., dtype=float32), 59.653557]
[None, array(98., dtype=float32), array(95., dtype=float32), array(87., dtype=float32), 0.10740828, 0.107431844, 0.107439496, 30.079273, array(96., dtype=float32), 65.92073]