残差网络实现
残差网络可以解决多层神经网络问题，这里使用mnist数据集实现一下残差网络。
网络模型如下：
该代码可以在普通VGG网络中随意添加残差层（ResNet(x1, x2, layer_name)），方便建立自己的网络模型。
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
import numpy as np
import os
def maxPoolLayer(x, layer_name, ksize=2, strides=2):
'''池化层'''
'''池化窗口大小：ksize=[1，height，width，1]'''
'''滑动步长大小：strides=[batch滑动步长, height方向滑动步长, width方向滑动步长, channels方向滑动步长]'''
return tf.nn.max_pool(x, ksize=[1, ksize, ksize, 1], strides=[1, strides, strides, 1], padding='SAME', name=layer_name)
def con2d_layer(x, out_chs, ksize, layer_name, strides=1):
'''卷积层'''
d_in = x.get_shape()[-1].value
with tf.variable_scope(layer_name):
'''卷积核：shape=[filter_height, filter_width, in_channels, out_channels]'''
w = tf.get_variable('weights', shape=[ksize, ksize, d_in, out_chs],
initializer=tf.truncated_normal_initializer(stddev=0.1)) # 初始化权重值
# '''shape=[out_channels]'''
b = tf.get_variable('bias', shape=[out_chs],
initializer=tf.truncated_normal_initializer(stddev=0.1)) # 初始化偏执值
y = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w, strides=[1, strides, strides, 1], padding='SAME'), b)) # 卷积运算
return y
def fc_layer(x, out_kernels, layer_name):
'''全连接层'''
n_in = x.get_shape()[-1].value
with tf.variable_scope(layer_name):
w = tf.get_variable('weights', shape=[n_in, out_kernels], dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
b = tf.get_variable('bias', shape=[out_kernels], dtype=tf.float32, trainable=True,
initializer=tf.truncated_normal_initializer(stddev=0.1))
y = tf.nn.relu(tf.nn.bias_add(tf.matmul(x, w), b))
return y
def ResNet(x1, x2, layer_name):
'''残差计算'''
'''x1为前卷积层'''
'''x2为后卷积层'''
with tf.variable_scope(layer_name):
if x1.shape[1] == x2.shape[1] and x1.shape[3] == x2.shape[3]: # 当两个卷积结果维度相同时，直接将两卷积求和
conv_add = tf.nn.relu(tf.add(x1, x2))
else: # 当两个卷积结果维度不同时，将想x1进行卷积操作，使x1与x2维度相同
w = tf.get_variable('weights', shape=[1, 1, x1.shape[3], x2.shape[3]], dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
conv = tf.nn.conv2d(x1, w, strides=[1, x1.shape[1]//x2.shape[1], x1.shape[1]//x2.shape[1], 1], padding='VALID') # 通常情况下，卷积后图像大小不会变大，通过计算可以获取步长
conv_add = tf.nn.relu(tf.add(conv, x2))
return conv_add
def VGG11(x, _dropout, n_cls):
'''输入：28*28*1'''
'''输出：14*14*64'''
conv1_1 = con2d_layer(x, 64, 2, 'conv1_1', strides=2)
pool1 = maxPoolLayer(conv1_1, 'pool1', ksize=3, strides=1)
'''输入：14*14*64'''
'''输出：14*14*64'''
conv2_1 = con2d_layer(pool1, 64, 1, 'conv2_1', strides=1)
'''输入：14*14*64'''
'''输出：14*14*256'''
conv2_2 = con2d_layer(conv2_1, 64, 3, 'conv2_2', strides=1)
conv2_3 = con2d_layer(conv2_2, 256, 1, 'conv2_3', strides=1)
'''输入：x1=14*14*64, x2=14*14*256'''
'''输出：14*14*256'''
residual2 = ResNet(pool1, conv2_3, 'residual2')
'''输入：14*14*256'''
'''输出：14*14*64'''
conv3_1 = con2d_layer(residual2, 64, 1, 'conv3_1', strides=1)
'''输入：14*14*64'''
'''输出：14*14*64'''
conv3_2 = con2d_layer(conv3_1, 64, 3, 'conv3_2', strides=1)
'''输入：14*14*64'''
'''输出：14*14*256'''
conv3_3 = con2d_layer(conv3_2, 256, 1, 'conv3_3', strides=1)
'''输入：x1=14*14*256, x2=14*14*256'''
'''输出：14*14*256'''
residual3 = ResNet(residual2, conv3_3, 'residual3')
'''输入：14*14*256'''
'''输出：14*14*64'''
conv4_1 = con2d_layer(residual3, 64, 1, 'conv4_1', strides=1)
'''输入：14*14*64'''
'''输出：14*14*64'''
conv4_2 = con2d_layer(conv4_1, 64, 3, 'conv4_2', strides=1)
'''输入：14*14*64'''
'''输出：14*14*256'''
conv4_3 = con2d_layer(conv4_2, 256, 1, 'conv4_3', strides=1)
'''输入：x1=14*14*256, x2=14*14*256'''
'''输出：14*14*256'''
residual4 = ResNet(residual3, conv4_3, 'residual4')
'''输入：x1=14*14*256'''
'''输出：7*7*256'''
pool4 = maxPoolLayer(residual4, 'pool4', ksize=2, strides=2)
'''将pool_5变换为一维向量'''
pool4_flatten_dims = int(np.prod(pool4.get_shape().as_list()[1:]))
pool4_flatten = tf.reshape(pool4, [-1, pool4_flatten_dims])
'''(7*7*256) * 1024'''
fc5 = fc_layer(pool4_flatten, 1024, 'fc5')
dropout5 = tf.nn.dropout(fc5, _dropout)
'''1024 * n_cls全连接层'''
w = tf.Variable(tf.truncated_normal(shape=[1024, n_cls], mean=0, stddev=0.1))
b = tf.Variable(tf.constant(0.1, shape=[n_cls]))
fc6 = tf.matmul(dropout5, w) + b
# fc2 = fc_layer(dropout1, n_cls, 'fc2')
return fc6
# tensorflow基于mnist实现VGG11
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
n_cls = 10 # 识别种类
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, n_cls])
sess = tf.InteractiveSession()
x1 = tf.reshape(x, [-1, 28, 28, 1])
keep_prob = tf.placeholder(tf.float32)
y_conv = VGG11(x1, keep_prob, n_cls)
# 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))
tf.summary.scalar('accuracy', accuracy)
# 初始化变量
sess.run(tf.global_variables_initializer())
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter("./log", sess.graph)
for i in range(3001):
batch = mnist.train.next_batch(10)
if i % 100 == 0:
result = sess.run(merged, feed_dict={
x: batch[0], y: batch[1], keep_prob: 1.0})
writer.add_summary(result, i)
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})
# print("test accuracy %g"%accuracy.eval(feed_dict={
# x: mnist.test.images, y: mnist.test.labels, keep_prob: 1.0}))
writer.close()
sess.close()
源码下载链接：https://download.csdn.net/download/OEMT_301/12571313