创建会话,启动会话
import tensorflow as tf
# 创建一个常量
m1 = tf.constant([[3,3]])
# 创建一个常量
m2 = tf.constant([[2],[3]])
# 矩阵乘法op
product = tf.matmul(m1, m2)
print(product)
Tensor("MatMul_3:0", shape=(1, 1), dtype=int32)
法一
#定义会话
sess = tf.Session()
# 调用sess中的run方法来执行矩阵乘法op
result = sess.run(product)
print(result)
sess.close()
[[15]]
法二
with tf.Session() as sess:
# 调用sess中的run方法来执行矩阵乘法op
result = sess.run(product)
print(result)
[[15]]
变量
# 定义一个变量
x = tf.Variable([1,2])
# 定义一个常量
a = tf.constant([3,3])
# 减法op
sub = tf.subtract(x, a)
# 加法op
add = tf.add(x,sub)
# 所有变量必须初始化!!!
init = tf.global_variables_initializer()
with tf.Session() as sess:
# 执行变量初始化
sess.run(init)
print(sess.run(sub))
print(sess.run(add))
[-2 -1]
[-1 1]
Fetch_Feed
fetch
# Fetch:可以在session中同时计算多个tensor或执行多个操作
# 定义三个常量
input1 = tf.constant(3.0)
input2 = tf.constant(2.0)
input3 = tf.constant(5.0)
# 加法op
add = tf.add(input2,input3)
# 乘法op
mul = tf.multiply(input1, add)
with tf.Session() as sess:
result1,result2 = sess.run([mul, add])
print(result1,result2)
21.0 7.0
feed
# Feed:先定义占位符,等需要的时候再传入数据
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
# 乘法op
output = tf.multiply(input1, input2)
with tf.Session() as sess:
print(sess.run(output, feed_dict={input1:8.0,input2:2.0}))
16.0
线性回归
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
x_data = np.random.rand(100)
noise = np.random.normal(0,0.01,x_data.shape)
y_data = x_data*0.1 + 0.2 + noise
plt.scatter(x_data,y_data)
plt.show()
# 构建一个线性模型
d = tf.Variable(np.random.rand(1))
k = tf.Variable(np.random.rand(1))
y = k*x_data + d
# 二次代价函数
loss = tf.losses.mean_squared_error(y_data, y)
# 定义一个梯度下降法优化器
optimizer = tf.train.GradientDescentOptimizer(0.3)
# 最小化代价函数
train = optimizer.minimize(loss)
# 初始化变量
init= tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for i in range(201):
sess.run(train)
if i%20==0:
print(i,sess.run([k,d]))
y_pred = sess.run(y)
plt.scatter(x_data,y_data)
plt.plot(x_data,y_pred,'r-',lw=3)
plt.show()
0 [array([0.42558686]), array([0.07772181])]
20 [array([0.24686251]), array([0.1212207])]
40 [array([0.17103131]), array([0.16282419])]
60 [array([0.13410329]), array([0.18308412])]
80 [array([0.1161202]), array([0.19295024])]
100 [array([0.10736286]), array([0.1977548])]
120 [array([0.10309823]), array([0.20009452])]
140 [array([0.10102146]), array([0.2012339])]
160 [array([0.10001012]), array([0.20178875])]
180 [array([0.09951763]), array([0.20205895])]
200 [array([0.09927779]), array([0.20219054])]
非线性回归
# numpy生成200个随机点
x_data = np.linspace(-0.5,0.5,200)[:,np.newaxis]
noise = np.random.normal(0,0.02,x_data.shape)
y_data = np.square(x_data) + noise
plt.scatter(x_data, y_data)
plt.show()
# 定义两个placeholder
x = tf.placeholder(tf.float32,[None,1])
y = tf.placeholder(tf.float32,[None,1])
# 神经网络结构:1-30-1
w1 = tf.Variable(tf.random_normal([1,30]))
b1 = tf.Variable(tf.zeros([30]))
wx_plus_b_1 = tf.matmul(x,w1) + b1
l1 = tf.nn.tanh(wx_plus_b_1)
w2 = tf.Variable(tf.random_normal([30,1]))
b2 = tf.Variable(tf.zeros([1]))
wx_plus_b_2 = tf.matmul(l1,w2) + b2
prediction = tf.nn.tanh(wx_plus_b_2)
# 二次代价函数
loss = tf.losses.mean_squared_error(y,prediction)
# 使用梯度下降法最小化loss
train = tf.train.GradientDescentOptimizer(0.1).minimize(loss)
with tf.Session() as sess:
# 变量初始化
sess.run(tf.global_variables_initializer())
for _ in range(3000):
sess.run(train,feed_dict={x:x_data,y:y_data})
# 获得预测值
prediction_value = sess.run(prediction,feed_dict={x:x_data})
# 画图
plt.scatter(x_data, y_data)
plt.plot(x_data, prediction_value, 'r-', lw=5)
plt.show()
MNIST数据集分类简单版本
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
# 批次大小
batch_size = 64
# 计算一个周期一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
# 定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
# 创建一个简单的神经网络:784-10
W = tf.Variable(tf.truncated_normal([784,10],stddev=0.1))
b = tf.Variable(tf.zeros([10]) + 0.1)
prediction = tf.nn.softmax(tf.matmul(x,W)+b)
# 二次代价函数
loss = tf.losses.mean_squared_error(y, prediction)
# 使用梯度下降法
train = tf.train.GradientDescentOptimizer(0.3).minimize(loss)
# 结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))
# 求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
with tf.Session() as sess:
# 变量初始化
sess.run(tf.global_variables_initializer())
# 周期epoch:所有数据训练一次,就是一个周期
for epoch in range(21):
for batch in range(n_batch):
# 获取一个批次的数据和标签
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
sess.run(train,feed_dict={x:batch_xs,y:batch_ys})
# 每训练一个周期做一次测试
acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))
交叉熵
loss = tf.losses.softmax_cross_entropy(y, prediction)
Dropout
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
#每个批次的大小
batch_size = 64
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#定义三个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)
# 784-1000-500-10
W1 = tf.Variable(tf.truncated_normal([784,1000],stddev=0.1))
b1 = tf.Variable(tf.zeros([1000])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)
W2 = tf.Variable(tf.truncated_normal([1000,500],stddev=0.1))
b2 = tf.Variable(tf.zeros([500])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)
W3 = tf.Variable(tf.truncated_normal([500,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3)
#交叉熵
loss = tf.losses.softmax_cross_entropy(y,prediction)
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
with tf.Session() as sess:
sess.run(init)
for epoch in range(31):
for batch in range(n_batch):
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.5})
test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
print("Iter " + str(epoch) + ",Testing Accuracy " + str(test_acc) +",Training Accuracy " + str(train_acc))
正则化
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
#每个批次的大小
batch_size = 64
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)
# 784-1000-500-10
#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,1000],stddev=0.1))
b1 = tf.Variable(tf.zeros([1000])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)
W2 = tf.Variable(tf.truncated_normal([1000,500],stddev=0.1))
b2 = tf.Variable(tf.zeros([500])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)
W3 = tf.Variable(tf.truncated_normal([500,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3)
#正则项
l2_loss = tf.nn.l2_loss(W1) + tf.nn.l2_loss(b1) + tf.nn.l2_loss(W2) + tf.nn.l2_loss(b2) + tf.nn.l2_loss(W3) + tf.nn.l2_loss(b3)
#交叉熵
loss = tf.losses.softmax_cross_entropy(y,prediction) + 0.0005*l2_loss
#使用梯度下降法
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
with tf.Session() as sess:
sess.run(init)
for epoch in range(31):
for batch in range(n_batch):
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:1.0})
test_acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
train_acc = sess.run(accuracy,feed_dict={x:mnist.train.images,y:mnist.train.labels,keep_prob:1.0})
print("Iter " + str(epoch) + ",Testing Accuracy " + str(test_acc) +",Training Accuracy " + str(train_acc))