TensorFlow学习笔记1：入门

TensorFlow 简介

什么是数据流图(Data Flow Graph)

有向图

有向图

有向图

tensors

flow

TensorFlow的特性

基本使用

Sessions

tensors

Variables

feeds

fetches

概览

ops

ops

Tensors

Tensors

Tensor

[batch,
height, width, channels]

Session

Session

numpy
ndarray

tensorflow::Tensor

图计算

session

创建图

Constant

ops

ops

ops构造器

ops构造器

import tensorflow as tf

# Create a Constant op that produces a 1x2 matrix.  The op is
# added as a node to the default graph.
#
# The value returned by the constructor represents the output
# of the Constant op.
matrix1 = tf.constant([[3., 3.]])

# Create another Constant that produces a 2x1 matrix.
matrix2 = tf.constant([[2.],[2.]])

# Create a Matmul op that takes 'matrix1' and 'matrix2' as inputs.
# The returned value, 'product', represents the result of the matrix
# multiplication.
product = tf.matmul(matrix1, matrix2)

Constant()

matmul()

session

在Session中执行图计算

# Launch the default graph.
sess = tf.Session()

# To run the matmul op we call the session 'run()' method, passing 'product'
# which represents the output of the matmul op.  This indicates to the call
# that we want to get the output of the matmul op back.
#
# All inputs needed by the op are run automatically by the session.  They
# typically are run in parallel.
#
# The call 'run(product)' thus causes the execution of threes ops in the
# graph: the two constants and matmul.
#
# The output of the op is returned in 'result' as a numpy `ndarray` object.
result = sess.run(product)
print(result)
# ==> [[ 12.]]

# Close the Session when we're done.
sess.close()

with

with

with tf.Session() as sess:
result = sess.run([product])
print(result)

with tf.Session() as sess:
with tf.device("/gpu:1"):
matrix1 = tf.constant([[3., 3.]])
matrix2 = tf.constant([[2.],[2.]])
product = tf.matmul(matrix1, matrix2)
...

"/cpu:0"

"/gpu:0"

"/gpu:1"

交互环境下的使用

Session

Session.run()

InteractiveSession

Tensor.eval()

Operation.run()

# Enter an interactive TensorFlow Session.
import tensorflow as tf
sess = tf.InteractiveSession()

x = tf.Variable([1.0, 2.0])
a = tf.constant([3.0, 3.0])

# Initialize 'x' using the run() method of its initializer op.
x.initializer.run()

# Add an op to subtract 'a' from 'x'.  Run it and print the result
sub = tf.sub(x, a)
print(sub.eval())
# ==> [-2. -1.]

# Close the Session when we're done.
sess.close()

Tensors

tensor

tensor

变量(Variables)

# Create a Variable, that will be initialized to the scalar value 0.
state = tf.Variable(0, name="counter")

# Create an Op to add one to `state`.

one = tf.constant(1)
new_value = tf.add(state, one)
update = tf.assign(state, new_value)

# Variables must be initialized by running an `init` Op after having
# launched the graph.  We first have to add the `init` Op to the graph.
init_op = tf.initialize_all_variables()

# Launch the graph and run the ops.
with tf.Session() as sess:
# Run the 'init' op
sess.run(init_op)
# Print the initial value of 'state'
print(sess.run(state))
# Run the op that updates 'state' and print 'state'.
for _ in range(3):
sess.run(update)
print(sess.run(state))

# output:

# 0
# 1
# 2
# 3

assign()

add()

run()

抓取(Fetches)

ops

session

run

print

input1 = tf.constant(3.0)
input2 = tf.constant(2.0)
input3 = tf.constant(5.0)
intermed = tf.add(input2, input3)
mul = tf.mul(input1, intermed)

with tf.Session() as sess:
result = sess.run([mul, intermed])
print(result)

# output:
# [array([ 21.], dtype=float32), array([ 7.], dtype=float32)]

填充(Feeds)

input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.mul(input1, input2)

with tf.Session() as sess:
print(sess.run([output], feed_dict={input1:[7.], input2:[2.]}))

# output:
# [array([ 14.], dtype=float32)]

placeholder()

示例：曲线拟合

# 简化调用库名
import tensorflow as tf
import numpy as np

# 模拟生成100对数据对, 对应的函数为y = x * 0.1 + 0.3
x_data = np.random.rand(100).astype("float32")
y_data = x_data * 0.1 + 0.3

# 指定w和b变量的取值范围（注意我们要利用TensorFlow来得到w和b的值）
W = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
b = tf.Variable(tf.zeros([1]))
y = W * x_data + b

# 最小化均方误差
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)

# 初始化TensorFlow参数
init = tf.initialize_all_variables()

# 运行数据流图（注意在这一步才开始执行计算过程）
sess = tf.Session()
sess.run(init)

# 观察多次迭代计算时，w和b的拟合值
for step in xrange(201):
sess.run(train)
if step % 20 == 0:
print(step, sess.run(W), sess.run(b))

# 最好的情况是w和b分别接近甚至等于0.1和0.3

MNIST手写体识别任务

MNIST数据集介绍

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

xs

ys

tensor

3

Softmax Regression模型

9

8

6

Softmax Regression的程序实现

import tensorflow as tf

x = tf.placeholder(tf.float32, [None, 784])

None

Variable

W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))

y = tf.nn.softmax(tf.matmul(x, W) + b)

matmul

模型的训练

y_ = tf.placeholder(tf.float32, [None, 10])

cross_entropy = -tf.reduce_sum(y_*tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

init = tf.initialize_all_variables()

sess = tf.Session()
sess.run(init)

for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

模型的评价

tf.argmax()

tf.equal()

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

tf.cast()

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

print(sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

完整代码及运行结果

__author__ = 'chapter'

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
print("Download Done!")

x = tf.placeholder(tf.float32, [None, 784])
# paras
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)y_ = tf.placeholder(tf.float32, [None, 10])
# loss func
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# init
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
# train
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
correct_prediction = tf.equal(tf.arg_max(y, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Accuarcy on Test-dataset: ", sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))