本文用于记录下自己的学习过程
一、输入、变量、输出和操作
import tensorflow as tf
import numpy as np
import os
# Defining the graph and session
graph = tf.Graph() # Creates a graph
session = tf.InteractiveSession(graph=graph) # Creates a session
# Building the graph
# A placeholder is an symbolic input
x = tf.placeholder(shape=[1,10],dtype=tf.float32,name='x')
# Variable
W = tf.Variable(tf.random_uniform(shape=[10,5], minval=-0.1, maxval=0.1, dtype=tf.float32),name='W')
# Variable
b = tf.Variable(tf.zeros(shape=[5],dtype=tf.float32),name='b')
h = tf.nn.sigmoid(tf.matmul(x,W) + b) # Operation to be performed
# Executing operations and evaluating nodes in the graph
tf.global_variables_initializer().run() # Initialize the variables
# Run the operation by providing a value to the symbolic input x
h_eval = session.run(h,feed_dict={x: np.random.rand(1,10)})
print(h_eval)
session.close() # Frees all the resources associated with the session
用餐厅点餐的例子来说,
graph中的每一个小项相当于你点的菜,所有你点的菜(订单)来组成整个graph
服务员相当于session,他将你的订单传达到后台,当你走了之后这个session就结束了
服务员收到订单之后将订单告诉厨房经理,厨房经理此时相当于分布式中的主服务器
厨房经理将需要的菜分配给两个worker,worker1是主厨(操作执行器),worker2是厨师(参数服务器)
graph中定义自变量需要用tf.placeholder(占位符)、定义参数常量用variable(可变)constant(不可变)、定义函数tf.nn.sigmoid(或其他函数)可以用tf.cast来进行类型转换如:tf.cast(x,dtype=tf.float32)
大体执行过程:
先申请graph session,然后定义其中的自变量,参数常量,需要的一些函数,然后调用session.run得到输出结果。
二、通道
通道是用来处理大量数据的。使用并行的方式来处理数据,主要用于可以从硬盘中读取数据,然后提供给需要处理的函数,包含以下元素:
- 文件名列表
- 文件名队列,用于为输入读取器生成文件名
- 记录读取器
- 解码器,用于解码读取的记录
- 预处理步骤(可选)
- 解码输入的队列
# Defining the graph and session
graph = tf.Graph() # Creates a graph
session = tf.InteractiveSession(graph=graph) # Creates a session
# The filename queue
filenames = ['test%d.txt'%i for i in range(1,4)]
filename_queue = tf.train.string_input_producer(filenames, capacity=3, shuffle=True,name='string_input_producer')
# check if all files are there
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
else:
print('File %s found.'%f)
# Reader which takes a filename queue and
# read() which outputs data one by one
reader = tf.TextLineReader()
# ready the data of the file and output as key,value pairs
# We're discarding the key
key, value = reader.read(filename_queue, name='text_read_op')
# if any problems encountered with reading file
# this is the value returned
record_defaults = [[-1.0], [-1.0], [-1.0], [-1.0], [-1.0], [-1.0], [-1.0], [-1.0], [-1.0], [-1.0]]
# decoding the read value to columns
col1, col2, col3, col4, col5, col6, col7, col8, col9, col10 = tf.decode_csv(value, record_defaults=record_defaults)
features = tf.stack([col1, col2, col3, col4, col5, col6, col7, col8, col9, col10])
# output x is randomly assigned a batch of data of batch_size
# where the data is read from the txt files
x = tf.train.shuffle_batch([features], batch_size=3,
capacity=5, name='data_batch',
min_after_dequeue=1,num_threads=1)
# QueueRunner retrieve data from queues and we need to explicitly start them
# Coordinator coordinates multiple QueueRunners
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord, sess=session)
# Building the graph by defining the variables and calculations
W = tf.Variable(tf.random_uniform(shape=[10,5], minval=-0.1, maxval=0.1, dtype=tf.float32),name='W') # Variable
b = tf.Variable(tf.zeros(shape=[5],dtype=tf.float32),name='b') # Variable
h = tf.nn.sigmoid(tf.matmul(x,W) + b) # Operation to be performed
# Executing operations and evaluating nodes in the graph
tf.global_variables_initializer().run() # Initialize the variables
# Calculate h with x and print the results for 5 steps
for step in range(5):
x_eval, h_eval = session.run([x,h])
print('========== Step %d =========='%step)
print('Evaluated data (x)')
print(x_eval)
print('Evaluated data (h)')
print(h_eval)
print('')
# We also need to explicitly stop the coordinator
# otherwise the process will hang indefinitely
coord.request_stop()
coord.join(threads)
session.close()
x = tf.train.shuffle_batch([features], batch_size=3,
capacity=5, name='data_batch',
min_after_dequeue=1,num_threads=1)
batch_size是采样的 批次大小,capacity是数据队列的容量,min_after_dequeue是出队后留在队列中的最小元素数量。
num_threads定义用于生成一批数据的线程数,tf.train.shuffle_batch函数对应生成通道。
coord = tf.train.Coordinator()//线程管理器
threads = tf.train.start_queue_runners(coord=coord, sess=session)//创建线程