1.CIFAR-10数据集介绍
本节使用的是比较经典的数据集叫CIFAR-10,包含60000张32*32的彩色图像(总算不像MNIST,是灰度图了,灰度图是单通道),因为是彩色图像,所以这个数据集是三通道的,分别是R,G,B三个通道。CIFAR-10,一共有10类图片,每一类图片有6000张,有飞机,鸟,猫,狗等,而且其中没有任何重叠的情况(现实社会中肯定不止那么多类啦)。现在还有一个兄弟版本,CIFAR-100,里面有100类,工程量已经蛮大的了,如果有兴趣,小伙伴们可以尝试一下哦!
这里还要提到一个数据增广的问题,对于数据集比较小,数据量远远不够的情况下,我们可以对图片进行翻转、随机剪切等增加数据,制造出更加多的样本,提高对图片的利用率。
2.数据准备
这个要事先下载Tensorflow Models库,以便使用CIFAR-10数据的类
git clone https://github.com/tensorflow/models.git
cd models/tutorials/image/cifar10
3.卷积神经网络的代码实现
这里我们先载入一些常用的库,比如Numpy和time,并载入tensorflow中下载和读取CIFAR-10数据的类。我这里开头加了from future import division,这是因为在代码最后我的true_count,total_sample_count都是整型,但我要通过这两个数相除,得到准确率,在python2中,如果不添加这个future函数,得出的结果是0,没法得到正确的结果。小伙伴们可以运行代码的时候注释掉这一行试一下,当然如果是python3版本的就不存在这个问题了。
from __future__ import division
import cifar10, cifar10_input
import tensorflow as tf
import numpy as np
import time
设置迭代的最大步数为3000,数据下载默认的地址在/tmp/cifar10_data/,所以我这里定义的地址就是这个位置,这个位置后来是用来读取数据,和对数据进行增广的时候使用的
max_steps = 3000
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'
定义初始化weight的函数,并增加L2正则项,通过筛选出最有效的特征,减少特征的权重防止过拟合。
def variable_with_weight_loss(shape, stddev, w1):
var = tf.Variable(tf.truncated_normal(shape, stddev = stddev))
if w1 is not None:
weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name = 'weight_loss')
tf.add_to_collection('losses', weight_loss)
return var
下载并提取CIFAR-10数据集,并展开到前文所说的位置
cifar10.maybe_download_and_extract()
对数据进行增广
images_train, labels_train = cifar10_input.distorted_inputs(data_dir = data_dir, batch_size = batch_size)
再次利用cifar10_input.inputs函数生成测试数据,这里不需要像训练数据一样对图片进行翻转、随机剪裁等,只需要裁剪图片正中间的24*24大小的区域,并进行数据标准化操作。
images_test, labels_test = cifar10_input.inputs(eval_data = True, data_dir = data_dir, batch_size = batch_size)
设定palceholder的尺寸
image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])
创建第一个卷积层
weight1 = variable_with_weight_loss(shape = [5, 5, 3, 64], stddev = 5e-2, w1 = 0.0)
kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding = 'SAME')
bias1 = tf.Variable(tf.constant(0.0, shape = [64]))
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1))
pool1 = tf.nn.max_pool(conv1, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'SAME')
norm1 = tf.nn.lrn(pool1, 4, bias = 1.0, alpha = 0.001 / 9.0, beta = 0.75)
创建第二个卷积层
weight2 = variable_with_weight_loss(shape = [5, 5, 64, 64], stddev = 5e-2, w1 = 0.0)
kernel2 = tf.nn.conv2d(norm1, weight2, [1, 1, 1, 1], padding = 'SAME')
bias2 = tf.Variable(tf.constant(0.1, shape = [64]))
conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2))
norm2 = tf.nn.lrn(conv2, 4, bias = 1.0, alpha = 0.001 / 9.0, beta = 0.75)
pool2 = tf.nn.max_pool(norm2, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'SAME')
创建第一个全连接层
reshape = tf.reshape(pool2, [batch_size, -1])
dim = reshape.get_shape()[1].value
weight3 = variable_with_weight_loss(shape = [dim, 384], stddev = 0.04, w1 = 0.004)
bias3 = tf.Variable(tf.constant(0.1, shape = [384]))
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3)
创建第二个全连接层
weight4 = variable_with_weight_loss(shape = [384, 192], stddev = 0.04, w1 = 0.004)
bias4 = tf.Variable(tf.constant(0.1, shape = [192]))
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4)
最后一层
weight5 = variable_with_weight_loss(shape = [192, 10], stddev = 1.0 / 192.0, w1 = 0.0)
bias5 = tf.Variable(tf.constant(0.0, shape = [10]))
logits = tf.add(tf.matmul(local4, weight5), bias5)
定义损失函数,注意腰把L2的损失也要加到总的损失中去
def loss(logits, labels):
labels = tf.cast(labels, tf.int32)
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits = logits, labels = labels, name = 'cross_entropy_per_example')
cross_entropy_mean = tf.reduce_mean(cross_entropy, name = 'cross_entropy')
tf.add_to_collection('losses', cross_entropy_mean)
return tf.add_n(tf.get_collection('losses'), name = 'total_loss')
接着将logits节点和label_placeholder传入loss函数获得最终的loss
loss = loss(logits, label_holder)
选择优化器Adam,学习率设为1e-3
train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)
使用tf.nn.in_top_k函数求输出结果中top k 的准确率,默认使用top 1,也就是输出分数最高的那一类的准确率。
top_k_op = tf.nn.in_top_k(logits, label_holder, 1)
初始化模型参数
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
启动模型线程
tf.train.start_queue_runners()
开始训练,我的GPU是GTX TITAN X训练大概每个batch需要0.08s左右,如果用其它的GPU,可能时间会有长短不太一致。
for step in range(max_steps):
start_time = time.time()
image_batch, label_batch = sess.run([images_train, labels_train])
_, loss_value = sess.run([train_op, loss], feed_dict = {image_holder: image_batch, label_holder: label_batch})
duration = time.time() - start_time
if step % 10 == 0:
examples_per_sec = batch_size / duration
sec_per_batch = float(duration)
format_str = ('step %d, loss = %.2f(%.1f examples/sec; %.3f sec/batch)')
print(format_str % (step, loss_value, examples_per_sec, sec_per_batch))
评测模型在测试集上的准确率
num_examples = 10000
import math
num_iter = int(math.ceil(num_examples / batch_size))
true_count = 0
total_sample_count = num_iter * batch_size
# print total_sample_count
step = 0
while step < num_iter:
image_batch, label_batch = sess.run([images_test, labels_test])
predictions = sess.run([top_k_op], feed_dict = {image_holder: image_batch, label_holder: label_batch})
true_count += np.sum(predictions)
step += 1
# print(true_count)
输出准确率的评测结果
precision = true_count / total_sample_count
print('precision @ 1 = %.3f' %precision)
代码好像越写越长,数据集也开始慢慢复杂起来了,但是只要每天进步一点点,就好O(∩_∩)O