【转载】 tensorflow的单层静态与动态RNN比较
原文地址:
https://www.jianshu.com/p/1b1ea45fab47
-----------------------------------------------------------------------------------
static_rnn和dynamic_rnn
1: static_rnn
x = tf.placeholder("float", [None, n_steps, n_input])
x1 = tf.unstack(x, n_steps, 1)
lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
outputs, states = tf.contrib.rnn.static_rnn(lstm_cell, x1, dtype=tf.float32)
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None)
2: dynamic_rnn
x = tf.placeholder("float", [None, n_steps, n_input])
lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
outputs,_ = tf.nn.dynamic_rnn(lstm_cell ,x,dtype=tf.float32)
outputs = tf.transpose(outputs, [1, 0, 2])
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None)
(num_units: 是指一个Cell中神经元的个数,forget_bias:忘记门记住多少,1.0代表全部记住)
静态 rnn的意思就是按照样本时间序列个数(n_steps)展开,在图中创建(n_steps)个序列的cell
动态rnn的意思是只创建样本中的一个序列RNN,其他序列数据会通过循环进入该RNN运算。 通过静态static_rnn生成的RNN网络,生成过程所需的时间会更长,网络所占有的内存会更多,导出的模型会更大。static_rnn模型中会带有第个序列中间态的信息,利于调试。static_rnn在使用时必须与训练的样本序列个数相同。dynamic_rnn通过动态生成的RNN网络,所占用内存较少。dynamic_rnn模型中只会有最后的状态,在使用时还能支持不同的序列个数。
区别
1.tf.nn.dynamic_rnn与tf.contrib.rnn.static_rnn输入格式不同。
2.tf.nn.dynamic_rnn与tf.contrib.rnn.static_rnn输出格式不同。
3.tf.nn.dynamic_rnn与tf.contrib.rnn.static_rnn内部训练方式。
请仔细对比以下区别:
动态rnn
import tensorflow as tf
# 导入 MINST 数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("c:/user/administrator/data/", one_hot=True)
n_input = 28 # MNIST data 输入 (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST 列别 (0-9 ,一共10类)
batch_size = 128
tf.reset_default_graph() # tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
outputs,_ = tf.nn.dynamic_rnn(lstm_cell,x,dtype=tf.float32)
outputs = tf.transpose(outputs, [1, 0, 2])
#取最后一条输出信息,(outputs[-1])
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None) learning_rate = 0.001
training_iters = 100000 display_step = 10 # Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
if step % display_step == 0:
# 计算批次数据的准确率
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print (" Finished!") # 计算准确率 for 128 mnist test images
test_len = 128
test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input))
test_label = mnist.test.labels[:test_len]
print ("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
静态RNN
import tensorflow as tf
# 导入 MINST 数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("c:/user/administrator/data/", one_hot=True)
n_input = 28 # MNIST data 输入 (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST 列别 (0-9 ,一共10类)
batch_size = 128
tf.reset_default_graph() # tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
x1 = tf.unstack(x, n_steps, 1)
lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
outputs, states = tf.contrib.rnn.static_rnn(lstm_cell, x1, dtype=tf.float32)
#取最后一条输出信息,(outputs[-1])
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None) learning_rate = 0.001
training_iters = 100000 display_step = 10 # Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
if step % display_step == 0:
# 计算批次数据的准确率
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print (" Finished!") # 计算准确率 for 128 mnist test images
test_len = 128
test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input))
test_label = mnist.test.labels[:test_len]
print ("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
本代码源自:
凯文自学TensorFlow
# -*- coding: utf-8 -*- import tensorflow as tf
# 导入 MINST 数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("c:/user/administrator/data/", one_hot=True)
n_input = 28 # MNIST data 输入 (img shape: 28*28)
n_steps = 28 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 10 # MNIST 列别 (0-9 ,一共10类)
batch_size = 128
tf.reset_default_graph() # tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])
#重置x以适合tf.contrib.rnn.static_rnn所要求的格式
#x1 = tf.unstack(x, n_steps, 1) #BasicLSTMCell(num_units: 是指一个Cell中神经元的个数,forget_bias:忘记门记住多少,1.0代表全部记住)
#静态 (tf.contrib.rnn.static_rnn)的意思就是按照样本时间序列个数(n_steps)展开,在图中创建(n_steps)个序列的cell;
#动态(tf.nn.dynamic_rnn)的意思是只创建样本中的一个序列RNN,其他序列数据会通过循环进入该RNN运算
"""
通过静态生成的RNN网络,生成过程所需的时间会更长,网络所占有的内存会更多,导出的模型会更大
。模型中会带有第个序列中间态的信息,利于调试。在使用时必须与训练的样本序列个数相同。通过动
态生成的RNN网络,所占用内存较少。模型中只会有最后的状态,在使用时还能支持不同的序列个数。
"""
#lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden, forget_bias=1.0)
#outputs, states = tf.contrib.rnn.static_rnn(lstm_cell, x1, dtype=tf.float32)
"""
#2 LSTMCell,LSTM实现的一个高级版本(use_peepholes:默认False,True表示启用peephole连接)
cell_clip:是否在输出前对cell状态按照给定值进行截断处理
initializer:指定初始化函数
num_proj:通过projection进行模型压缩的输出维度
proj_clip:将num_proj按照给定的proj_clip截断
"""
#lstm_cell = tf.contrib.rnn.LSTMCell(n_hidden, forget_bias=1.0)
#outputs, states = tf.contrib.rnn.static_rnn(lstm_cell, x1, dtype=tf.float32) #3 gru类定义
#gru = tf.contrib.rnn.GRUCell(n_hidden)
#outputs = tf.contrib.rnn.static_rnn(gru, x1, dtype=tf.float32) #4 创建动态RNN,此时的输入是x,是动态的[None, n_steps, n_input]LIST
#具体定义参考https://blog.csdn.net/mzpmzk/article/details/80573338
gru = tf.contrib.rnn.GRUCell(n_hidden)
outputs,_ = tf.nn.dynamic_rnn(gru,x,dtype=tf.float32)
outputs = tf.transpose(outputs, [1, 0, 2])
#取最后一条输出信息,(outputs[-1])
pred = tf.contrib.layers.fully_connected(outputs[-1],n_classes,activation_fn = None) learning_rate = 0.001
training_iters = 100000 display_step = 10 # Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) # Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) # 启动session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
if step % display_step == 0:
# 计算批次数据的准确率
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
# Calculate batch loss
loss = sess.run(cost, feed_dict={x: batch_x, y: batch_y})
print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
step += 1
print (" Finished!") # 计算准确率 for 128 mnist test images
test_len = 128
test_data = mnist.test.images[:test_len].reshape((-1, n_steps, n_input))
test_label = mnist.test.labels[:test_len]
print ("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: test_data, y: test_label}))
-----------------------------------------------------------------------------------
【转载】 tensorflow的单层静态与动态RNN比较的更多相关文章
- RNN静态与动态
静态.多层RNN:import numpy as np import tensorflow as tf # 导入 MINST 数据集 from tensorflow.examples.tutorial ...
- Delphi DLL的创建、静态及动态调用
转载:http://blog.csdn.net/welcome000yy/article/details/7905463 结合这篇博客:http://www.cnblogs.com/xumenger/ ...
- [源码解析] TensorFlow 分布式环境(6) --- Master 动态逻辑
[源码解析] TensorFlow 分布式环境(6) --- Master 动态逻辑 目录 [源码解析] TensorFlow 分布式环境(6) --- Master 动态逻辑 1. GrpcSess ...
- [源码解析] TensorFlow 分布式环境(7) --- Worker 动态逻辑
[源码解析] TensorFlow 分布式环境(7) --- Worker 动态逻辑 目录 [源码解析] TensorFlow 分布式环境(7) --- Worker 动态逻辑 1. 概述 1.1 温 ...
- Android中BroadcastReceiver的两种注册方式(静态和动态)详解
今天我们一起来探讨下安卓中BroadcastReceiver组件以及详细分析下它的两种注册方式. BroadcastReceiver也就是"广播接收者"的意思,顾名思义,它就是用来 ...
- 生成lua的静态库.动态库.lua.exe和luac.exe
前些日子准备学习下关于lua coroutine更为强大的功能,然而发现根据lua 5.1.4版本来运行一段代码的话也会导致 "lua: attempt to yield across me ...
- 3D touch 静态、动态设置及进入APP的跳转方式
申明Quick Action有两种方式:静态和动态 静态是在info.plist文件中申明,动态则是在代码中注册,系统支持两者同时存在. -系统限制每个app最多显示4个快捷图标,包括静态和动态 静态 ...
- C/C++ 跨平台交叉编译、静态库/动态库编译、MinGW、Cygwin、CodeBlocks使用原理及链接参数选项
目录 . 引言 . 交叉编译 . Cygwin简介 . 静态库编译及使用 . 动态库编译及使用 . MinGW简介 . CodeBlocks简介 0. 引言 UNIX是一个注册商标,是要满足一大堆条件 ...
- RT-Thread创建静态、动态线程
RT-Thread 实时操作系统核心是一个高效的硬实时核心,它具备非常优异的实时性.稳定性.可剪裁性,当进行最小配置时,内核体积可以到 3k ROM 占用. 1k RAM 占用. RT-Thread ...
随机推荐
- C#-阿里云OSSAPI
Nuget导入包 共用类 using System; using System.Collections.Generic; using System.IO; using System.Linq; usi ...
- 谈谈OAuth1,OAuth2异同
##一.写在前面在收集资料时,我查询和学习了许多介绍OAuth的文章,这些文章有好有坏,但大多是从个例出发.因此我想从官方文档出发,结合在stackoverflow上的一些讨论,一并整理一下.整理的内 ...
- 记一次至今懵逼的bug
<update id="falseDeleteBatchByPKArr" parameterType="java.lang.String"> U ...
- 23.centos7基础学习与积累-009-linux目录
从头开始积累centos7系统运用 大牛博客:https://blog.51cto.com/yangrong/p5 linux目录的特点: 1. /是所有目录的顶点. 2. 目录结构像一颗倒挂的树. ...
- 2013.9.3 - OpenNER第十一天
下午接受了天猫某高管的交叉面试,在图书馆电面的,感觉面的不怎么好,他先问了我飞天的情况,还有我做了什么,他感觉和我聊不到一起去,我感觉应该是下午在地下铁喝的那杯咖啡让我慌了神,后来他又问了大数组抽取最 ...
- centos7最小安装后无法联网解决方法
1 进入目录 cd /etc/sysconfig/network-scripts/ # 编辑网卡的配置文件 # 多网卡会对应多个配置文件,均以ifcfg-enp开头 # 新环境配置可任意选择,建议按一 ...
- PAT甲级1007题解——贪心
题目分析:对于每一个点来说,如果选择合并入包含前一个点的序列那么只有在前一个点的序列不为负数(这里指的是包含前一个位置的数的一个连续序列的和不为负数),当前点才会将自己也加入这个子序列,否则,当前点则 ...
- ThinkPHP模型中的HAS_ONE,BELONG_TO,HAS_MANY实践
因为很熟悉DJANGO,所以对TP,要慢慢适应. 1,SQL文件 /* Navicat MySQL Data Transfer Source Server : localhost_3306 Sourc ...
- 数组,字符串,json互相转换
数组转字符串 var arr = [1,2,3,4,'巴德','merge']; var str = arr.join(','); console.log(str); // 1,2,3,4,巴德,me ...
- kubectl kubernetes cheatsheet
from : https://cheatsheet.dennyzhang.com/cheatsheet-kubernetes-a4 PDF Link: cheatsheet-kubernetes-A4 ...