LSTM预测MNIST手写数字张量流图分析

看LSTM的代码感觉封装的太厉害，看的有些模糊，现画了个MNIST的张量流图，便于分析代码

原始代码如下

# View more python learning tutorial on my Youtube and Youku channel!!!

# Youtube video tutorial: https://www.youtube.com/channel/UCdyjiB5H8Pu7aDTNVXTTpcg
# Youku video tutorial: http://i.youku.com/pythontutorial

"""
This code is a modified version of the code from this link:
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
His code is a very good one for RNN beginners. Feel free to check it out.
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
tf.reset_default_graph()
# set random seed for comparing the two result calculations
tf.set_random_seed(1)

# this is data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

# hyperparameters
lr = 0.001
training_iters = 100000
batch_size = 128

n_inputs = 28 # MNIST data input (img shape: 28*28)
n_steps = 28 # time steps
n_hidden_units = 128 # neurons in hidden layer
n_classes = 10 # MNIST classes (0-9 digits)

# tf Graph input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])

# Define weights
weights = {
# (28, 128)
'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
# (128, 10)
'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
# (128, )
'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
# (10, )
'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}

def RNN(X, weights, biases):
# hidden layer for input to cell
########################################
#X default is [128,28,28]
# transpose the inputs shape from
# X ==> (128 batch * 28 steps, 28 inputs)
X = tf.reshape(X, [-1, n_inputs])

# into hidden
# X_in = (128 batch * 28 steps, 128 hidden)
#weights_in = [28,128]
X_in = tf.matmul(X, weights['in']) + biases['in']
# X_in ==> (128 batch, 28 steps, 128 hidden)
X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])

# cell
##########################################

# basic LSTM Cell.
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
else:
cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units)
print("cell=",cell)
# lstm cell is divided into two parts (c_state, h_state)
# c_state = [128,128] h_state = [128,128]
init_state = cell.zero_state(batch_size, dtype=tf.float32)
print("init_state.shape=",init_state)
# You have 2 options for following step.
# 1: tf.nn.rnn(cell, inputs);
# 2: tf.nn.dynamic_rnn(cell, inputs).
# If use option 1, you have to modified the shape of X_in, go and check out this:
# https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
# In here, we go for option 2.
# dynamic_rnn receive Tensor (batch, steps, inputs) or (steps, batch, inputs) as X_in.
# Make sure the time_major is changed accordingly. =
#outputs.shape= [128, 28, 128]
outputs, final_state = tf.nn.dynamic_rnn(cell, X_in, initial_state=init_state, time_major=False)
#outputs.shape= [128, 28, 128] final_state.shape 中包含两个tuple,其中每个是c=[128,128] h=[128,128]
print("outputs.shape=",outputs.shape.as_list(),"final_state.shape=",len(final_state))
print("final_state.shape=",final_state)
# hidden layer for output as the final results
#############################################
# results = tf.matmul(final_state[1], weights['out']) + biases['out']

# # or
# unpack to list [(batch, outputs)..] * steps 此处是[128,128]*28
#tf.unstack(value, num=None, axis=0, name=’unstack’)以指定的轴axis，将一个维度为R的张量数组转变成一个维度为R-1的张量
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
outputs = tf.unpack(tf.transpose(outputs, [1, 0, 2])) # states is the last outputs
else:
outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))
print("unstack 后的outputs",len(outputs))
print("now outputs",outputs)
results = tf.matmul(outputs[-1], weights['out']) + biases['out'] # shape = (128, 10)

return results

pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)

correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

with tf.Session() as sess:
# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
init = tf.initialize_all_variables()
else:
init = tf.global_variables_initializer()
sess.run(init)
step = 0
while step * batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
print("batch_xs.shape=",batch_xs.shape,"batch_ys.shape=",batch_ys,"len(batch_ys)=",len(batch_ys))
batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
print("after reshaping batch_xs.shape=",batch_xs.shape)
sess.run([train_op], feed_dict={
x: batch_xs,
y: batch_ys,
})
if step % 20 == 0:
print(sess.run(accuracy, feed_dict={
x: batch_xs,
y: batch_ys,
}))
step += 1

#########################################################################

LSTM预测取最后一组数据进行预测，因为直到最后一组数据输入完成才能最大程度利用时间序列信息对结果进行预测，o这就好比于翻译时，只有等到说者将这句话的最后一个字说完，才能开始翻译一样，同理，分析一个图片时只有，从上到下逐行扫描图片，只有最后一行像素扫描完成时才可以有把握对该图片最终表示的是几进行预测，这也是为什么取图片输入完成时最后一刻的输出结果作为最终结果

results = tf.matmul(outputs[-1], weights['out']) + biases['out'] # shape = (128, 10)

LSTM预测MNIST手写数字张量流图分析相关推荐

用tensorflow搭建RNN(LSTM)进行MNIST 手写数字辨识
用tensorflow搭建RNN(LSTM)进行MNIST 手写数字辨识循环神经网络RNN相比传统的神经网络在处理序列化数据时更有优势,因为RNN能够将加入上(下)文信息进行考虑.一个简单的RNN如 ...
如何为MNIST手写数字分类开发CNN
导言 MNIST手写数字分类问题是计算机视觉和深度学习中使用的标准数据集. 虽然数据集得到了有效的解决,但它可以作为学习和实践如何开发,评估和使用卷积深度学习神经网络从头开始进行图像分类的基础.这包括 ...
TF之LSTM：利用多层LSTM算法对MNIST手写数字识别数据集进行多分类
TF之LSTM:利用多层LSTM算法对MNIST手写数字识别数据集进行多分类目录设计思路实现代码设计思路更新-- 实现代码 # -*- coding:utf-8 -*- import ten ...
DL之CNN：利用卷积神经网络算法(2→2,基于Keras的API-Functional)利用MNIST(手写数字图片识别)数据集实现多分类预测
DL之CNN:利用卷积神经网络算法(2→2,基于Keras的API-Functional)利用MNIST(手写数字图片识别)数据集实现多分类预测目录输出结果设计思路核心代码输出结果下边两张 ...
DL之CNN：利用卷积神经网络算法(2→2,基于Keras的API-Sequential)利用MNIST(手写数字图片识别)数据集实现多分类预测
DL之CNN:利用卷积神经网络算法(2→2,基于Keras的API-Sequential)利用MNIST(手写数字图片识别)数据集实现多分类预测目录输出结果设计思路核心代码输出结果 1.10 ...
DL之DNN：利用DNN【784→50→100→10】算法对MNIST手写数字图片识别数据集进行预测、模型优化
DL之DNN:利用DNN[784→50→100→10]算法对MNIST手写数字图片识别数据集进行预测.模型优化导读目的是建立三层神经网络,进一步理解DNN内部的运作机制目录输出结果设计思路 ...
DL之LiRDNNCNN：利用LiR、DNN、CNN算法对MNIST手写数字图片(csv)识别数据集实现(10)分类预测
DL之LiR&DNN&CNN:利用LiR.DNN.CNN算法对MNIST手写数字图片(csv)识别数据集实现(10)分类预测目录输出结果设计思路核心代码输出结果数据集:Da ...
DL之DNN：利用DNN算法对mnist手写数字图片识别数据集(sklearn自带,1797*64)训练、预测(95%)
DL之DNN:利用DNN算法对mnist手写数字图片识别数据集(sklearn自带,1797*64)训练.预测(95%) 目录数据集展示输出结果设计代码数据集展示先查看sklearn自带di ...
TF之DNN：利用DNN【784→500→10】对MNIST手写数字图片识别数据集(TF自带函数下载)预测(98%)+案例理解DNN过程
TF之DNN:利用DNN[784→500→10]对MNIST手写数字图片识别数据集(TF自带函数下载)预测(98%)+案例理解DNN过程目录输出结果案例理解DNN过程思路代码设计输出结果案 ...

LSTM预测MNIST手写数字张量流图分析

LSTM预测MNIST手写数字张量流图分析相关推荐

最新文章

热门文章