卷积神经网络对CIFAR数据集分类

本例通过一个具有全局平局池化层的神经网络对CIFAR数据集分类

1.导入头文件引入数据集

这部分使用cifar10_input里面的代码，在cifar10文件夹下建立卷积文件，部分代码如下：

import cifar10_input
import tensorflow as tf
import numpy as np

batch_size = 128
data_dir = 'cifar-10-batches-bin/'
print("begin")
images_train, labels_train = cifar10_input.inputs(eval_data = False, data_dir = data_dir, batch_size = batch_size)
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir = data_dir, batch_size = batch_size)
print("bedin data")

2.定义网络结构

对于权重w的定义，统一用函数truncated_normal 来生成标准差为0.1的随机数为其初始化，对于权重b的定义，统一初始化为0.1。

#定义网络结构
def weight_variable(shape):
    initial = tf.truncated_normal(shape = shape,stddev = 0.1)
    return tf.Variable(initial)

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

def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding = 'SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME' )

def avg_pool_6x6(x):
    return tf.nn.avg_pool(x, ksize = [1, 6, 6, 1], strides = [1, 6, 6, 1], padding = 'SAME')

#定义占位符
x = tf.placeholder(tf.float32, [None, 24, 24, 3])#cifar data的shape为24*24*3
y = tf.placeholder(tf.float32, [None, 10])#0~9数字分类=>10 classes

W_conv1 = weight_variable([5, 5, 3, 64])
b_conv1 = bias_variable([64])

x_image = tf.reshape(x, [-1, 24, 24, 3])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 64, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_conv3 = weight_variable([5, 5, 64, 10])
b_conv3 = bias_variable([10])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)

nt_hpool3 = avg_pool_6x6(h_conv3)#10
nt_hpool3_flat = tf.reshape(nt_hpool3, [-1,10])
y_conv = tf.nn.softmax(nt_hpool3_flat)

cross_entropy = -tf.reduce_sum(y*tf.log(y_conv))

train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_perdiction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_perdiction, "float"))

3.运行session进行训练

启动session，迭代15000次。

sess = tf.Session()
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess = sess)
for i in range(15000):#20000
    image_batch, label_batch = sess.run([images_train, labels_train])
    label_b = np.eye(10, dtype = float)[label_batch]#one hot编码

    train_step.run(feed_dict = {x:image_batch, y:label_b}, session = sess)

    if i%200 == 0:
        train_accuracy = accuracy.eval(feed_dict = {x:image_batch, y:label_b}, session = sess)
        print("step %d, training accuracy %g "%(i, train_accuracy))

4.评估结果

从测试数据集里面将数据取出，放到模型里面运行，查看模型的正确率。

image_batch, label_batch = sess.run([images_test, labels_test])
label_b = np.eye(10, dtype = float)[label_batch]  #onehot编码
print("Finished! test accuracy %g" %accuracy.eval(feed_dict = {x: image_batch, y: label_b}, session = sess))

运行代码后，输出如下（部分截图）：

识别效果得到了收敛，正确率在0.6左右，正确率不高，主要是模型相对较为简单，只用了两层卷积操作，需要进行优化来提高准确率。