tensorflow实现残差网络方式(mnist数据集)

介绍

残差网络是何凯明大神的神作，效果非常好，深度可以达到1000层。但是，其实现起来并没有那末难，在这里以tensorflow作为框架，实现基于mnist数据集上的残差网络，当然只是比较浅层的。

如下图所示：

实线的Connection部分，表示通道相同，如上图的第一个粉色矩形和第三个粉色矩形，都是3x3x64的特征图，由于通道相同，所以采用计算方式为H(x)=F(x)+x

虚线的的Connection部分，表示通道不同，如上图的第一个绿色矩形和第三个绿色矩形，分别是3x3x64和3x3x128的特征图，通道不同，采用的计算方式为H(x)=F(x)+Wx，其中W是卷积操作，用来调整x维度的。

根据输入和输出尺寸是否相同，又分为identity_block和conv_block，每种block有上图两种模式，三卷积和二卷积，三卷积速度更快些，因此在这里选择该种方式。

具体实现见如下代码：

#tensorflow基于mnist数据集上的VGG11网络，可以直接运行
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
#tensorflow基于mnist实现VGG11
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

#x=mnist.train.images
#y=mnist.train.labels
#X=mnist.test.images
#Y=mnist.test.labels
x = tf.placeholder(tf.float32, [None,784])
y = tf.placeholder(tf.float32, [None, 10])
sess = tf.InteractiveSession()

def weight_variable(shape):
#这里是构建初始变量
 initial = tf.truncated_normal(shape, mean=0,stddev=0.1)
#创建变量
 return tf.Variable(initial)

def bias_variable(shape):
 initial = tf.constant(0.1, shape=shape)
 return tf.Variable(initial)

#在这里定义残差网络的id_block块，此时输入和输出维度相同
def identity_block(X_input, kernel_size, in_filter, out_filters, stage, block):
 """
 Implementation of the identity block as defined in Figure 3

 Arguments:
 X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
 kernel_size -- integer, specifying the shape of the middle CONV's window for the main path
 filters -- python list of integers, defining the number of filters in the CONV layers of the main path
 stage -- integer, used to name the layers, depending on their position in the network
 block -- string/character, used to name the layers, depending on their position in the network
 training -- train or test

 Returns:
 X -- output of the identity block, tensor of shape (n_H, n_W, n_C)
 """

 # defining name basis
 block_name = 'res' + str(stage) + block
 f1, f2, f3 = out_filters
 with tf.variable_scope(block_name):
  X_shortcut = X_input

  #first
  W_conv1 = weight_variable([1, 1, in_filter, f1])
  X = tf.nn.conv2d(X_input, W_conv1, strides=[1, 1, 1, 1], padding='SAME')
  b_conv1 = bias_variable([f1])
  X = tf.nn.relu(X+ b_conv1)

  #second
  W_conv2 = weight_variable([kernel_size, kernel_size, f1, f2])
  X = tf.nn.conv2d(X, W_conv2, strides=[1, 1, 1, 1], padding='SAME')
  b_conv2 = bias_variable([f2])
  X = tf.nn.relu(X+ b_conv2)

  #third

  W_conv3 = weight_variable([1, 1, f2, f3])
  X = tf.nn.conv2d(X, W_conv3, strides=[1, 1, 1, 1], padding='SAME')
  b_conv3 = bias_variable([f3])
  X = tf.nn.relu(X+ b_conv3)
  #final step
  add = tf.add(X, X_shortcut)
  b_conv_fin = bias_variable([f3])
  add_result = tf.nn.relu(add+b_conv_fin)

 return add_result

#这里定义conv_block模块，由于该模块定义时输入和输出尺度不同，故需要进行卷积操作来改变尺度，从而得以相加
def convolutional_block( X_input, kernel_size, in_filter,
    out_filters, stage, block, stride=2):
 """
 Implementation of the convolutional block as defined in Figure 4

 Arguments:
 X -- input tensor of shape (m, n_H_prev, n_W_prev, n_C_prev)
 kernel_size -- integer, specifying the shape of the middle CONV's window for the main path
 filters -- python list of integers, defining the number of filters in the CONV layers of the main path
 stage -- integer, used to name the layers, depending on their position in the network
 block -- string/character, used to name the layers, depending on their position in the network
 training -- train or test
 stride -- Integer, specifying the stride to be used

 Returns:
 X -- output of the convolutional block, tensor of shape (n_H, n_W, n_C)
 """

 # defining name basis
 block_name = 'res' + str(stage) + block
 with tf.variable_scope(block_name):
  f1, f2, f3 = out_filters

  x_shortcut = X_input
  #first
  W_conv1 = weight_variable([1, 1, in_filter, f1])
  X = tf.nn.conv2d(X_input, W_conv1,strides=[1, stride, stride, 1],padding='SAME')
  b_conv1 = bias_variable([f1])
  X = tf.nn.relu(X + b_conv1)

  #second
  W_conv2 =weight_variable([kernel_size, kernel_size, f1, f2])
  X = tf.nn.conv2d(X, W_conv2, strides=[1,1,1,1], padding='SAME')
  b_conv2 = bias_variable([f2])
  X = tf.nn.relu(X+b_conv2)

  #third
  W_conv3 = weight_variable([1,1, f2,f3])
  X = tf.nn.conv2d(X, W_conv3, strides=[1, 1, 1,1], padding='SAME')
  b_conv3 = bias_variable([f3])
  X = tf.nn.relu(X+b_conv3)
  #shortcut path
  W_shortcut =weight_variable([1, 1, in_filter, f3])
  x_shortcut = tf.nn.conv2d(x_shortcut, W_shortcut, strides=[1, stride, stride, 1], padding='VALID')

  #final
  add = tf.add(x_shortcut, X)
  #建立最后融合的权重
  b_conv_fin = bias_variable([f3])
  add_result = tf.nn.relu(add+ b_conv_fin)

 return add_result

x = tf.reshape(x, [-1,28,28,1])
w_conv1 = weight_variable([2, 2, 1, 64])
x = tf.nn.conv2d(x, w_conv1, strides=[1, 2, 2, 1], padding='SAME')
b_conv1 = bias_variable([64])
x = tf.nn.relu(x+b_conv1)
#这里操作后变成14x14x64
x = tf.nn.max_pool(x, ksize=[1, 3, 3, 1],
    strides=[1, 1, 1, 1], padding='SAME')

#stage 2
x = convolutional_block(X_input=x, kernel_size=3, in_filter=64, out_filters=[64, 64, 256], stage=2, block='a', stride=1)
#上述conv_block操作后，尺寸变为14x14x256
x = identity_block(x, 3, 256, [64, 64, 256], stage=2, block='b' )
x = identity_block(x, 3, 256, [64, 64, 256], stage=2, block='c')
#上述操作后张量尺寸变成14x14x256
x = tf.nn.max_pool(x, [1, 2, 2, 1], strides=[1,2,2,1], padding='SAME')
#变成7x7x256
flat = tf.reshape(x, [-1,7*7*256])

w_fc1 = weight_variable([7 * 7 *256, 1024])
b_fc1 = bias_variable([1024])

h_fc1 = tf.nn.relu(tf.matmul(flat, w_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
w_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2

#建立损失函数，在这里采用交叉熵函数
cross_entropy = tf.reduce_mean(
 tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=y_conv))

train_step = tf.train.AdamOptimizer(1e-3).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#初始化变量

sess.run(tf.global_variables_initializer())

print("cuiwei")
for i in range(2000):
 batch = mnist.train.next_batch(10)
 if i%100 == 0:
 train_accuracy = accuracy.eval(feed_dict={
 x:batch[0], y: batch[1], keep_prob: 1.0})
 print("step %d, training accuracy %g"%(i, train_accuracy))
 train_step.run(feed_dict={x: batch[0], y: batch[1], keep_prob: 0.5})

以上这篇tensorflow实现残差网络方式(mnist数据集)就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持我们。