cifar10tfcnn - juedaiyuer/researchNote GitHub Wiki

CIFAR-10数据集的CNN

1. 关于数据集

想了解更多信息请参考CIFAR-10 page,以及Alex Krizhevsky写的技术报告

Cifar-10是由Hinton的两个大弟子Alex Krizhevsky、Ilya Sutskever收集的一个用于普适物体识别的数据集。Cifar是加拿大政府牵头投资的一个先进科学项目研究所。

说白了,就是看你穷的没钱搞研究,就施舍给你。Hinton、Bengio和他的学生在2004年拿到了Cifar投资的少量资金,建立了神经计算和自适应感知项目。

这个项目结集了不少计算机科学家、生物学家、电气工程师、神经科学家、物理学家、心理学家,加速推动了DL的进程。从这个阵容来看,DL已经和ML系的数据挖掘分的很远了。

DL强调的是自适应感知和人工智能,是计算机与神经科学交叉。DM强调的是高速、大数据、统计数学分析,是计算机和数学的交叉。

Cifar-10由60000张32*32的RGB彩色图片构成,共10个分类(airplane,automobile,bird,cat,deer,dog,frog,horse,ship,truck)。50000张训练,10000张测试(交叉验证)。这个数据集最大的特点在于将识别迁移到了普适物体,而且应用于多分类(姊妹数据集Cifar-100达到100类,ILSVRC比赛则是1000类)。

许多论文中都对这个数据集进行性能测试,state-of-the-art达到了3.5%的错误率

2. 下载models库

对于版本在v1.0以上的需要下载Tensorflow Models库,以便使用其中提供的Cifar-10数据的类

$ git clone https://github.com/tensorflow/models.git
$ cd models/tutorials/image/cifar10

3. 定义初始化weight函数

Note:对weights进行L2的正则化

def variable_with_weight_loss(shape, stddev, wl):
	var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))
	if wl is not None:
	    weight_loss = tf.multiply(tf.nn.l2_loss(var), wl, name='weight_loss')
	    tf.add_to_collection('losses', weight_loss)
	return var

wl:loss的参数,控制loss的影响,越大影响越大

tf.nn.l2_loss(var),计算了weight的L2 Loss

4. 数据集操作

下载,解压,展开到默认位置

cifar10.maybe_download_and_extract()

cifar10_input类中的distorted_inputs函数产生训练需要使用的数据,包括特征及其对应的label,返回的是封装好的tensor

Note:对数据进行了数据增强操作Data Augmentation

输入数据的placeholder,样本条数需要被预先设定

image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])

4.1 数据增强

Data Augmentation

它可以给单幅图增加多个副本,提高图片的利用率,防止学习过拟合

根据Alex在cuda-convnet上的测试结果,如果不用数据增强,错误率最低可以下降到17%;使用数据增强,错误率下降到11%,模型性能的提升非常显著

5. 第一个卷积层

卷积核:5×5

颜色通道:3个

卷积核数目:64个

weight初始化函数:标准差0.05,wl=0(不进行L2的正则)

weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, wl=0.0)

卷积操作

kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding='SAME')

偏置参数初始化为0

bias1 = tf.Variable(tf.constant(0.0, shape=[64]))

卷积结果加上bias1

tf.nn.bias_add(kernel1, bias1)

最大池化层处理数据

pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],padding='SAME')

用LRN对结果进行处理

norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)

6. 第二个卷积层

上一层的卷积核数量为64(即输出64个通道),即第三个参数相应改为64.

weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64], stddev=5e-2, wl=0.0)

先进行LRN层处理,再使用最大池化层

7. 第一个全连接层

隐含节点数:384

将第二个卷积层的输出结果flatten(翻译:扁平化,即变为1维数据),使用tf.reshape函数

reshape = tf.reshape(pool2, [batch_size, -1])

获取数据扁平化后的长度

dim = reshape.get_shape()[1].value

8. 第二个全连接层

隐含节点数:192

9. 最后一层

不使用softmax输出最后结果

以上是CNN的模型构建,整个网络inference的部分

loss

交叉熵 cross entropy

softmax计算和cross entropy loss计算的合并tf.nn.sparse_softmax_cross_entropy_with_logits

源代码如下

import cifar10,cifar10_input
import tensorflow as tf
import numpy as np
import time

max_steps = 3000
batch_size = 128
data_dir = '/tmp/cifar10_data/cifar-10-batches-bin'


def variable_with_weight_loss(shape, stddev, wl):
	var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))
	if wl is not None:
	    weight_loss = tf.multiply(tf.nn.l2_loss(var), wl, name='weight_loss')
	    tf.add_to_collection('losses', weight_loss)
	return var


def loss(logits, labels):
#      """Add L2Loss to all the trainable variables.
#      Add summary for "Loss" and "Loss/avg".
#      Args:
#        logits: Logits from inference().
#        labels: Labels from distorted_inputs or inputs(). 1-D tensor
#                of shape [batch_size]
#      Returns:
#        Loss tensor of type float.
#      """
#      # Calculate the average cross entropy loss across the batch.
	labels = tf.cast(labels, tf.int64)
	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)

  # The total loss is defined as the cross entropy loss plus all of the weight
  # decay terms (L2 loss).
	return tf.add_n(tf.get_collection('losses'), name='total_loss')
  
###

cifar10.maybe_download_and_extract()


images_train, labels_train = cifar10_input.distorted_inputs(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)
#images_train, labels_train = cifar10.distorted_inputs()
#images_test, labels_test = cifar10.inputs(eval_data=True)

image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3])
label_holder = tf.placeholder(tf.int32, [batch_size])

#logits = inference(image_holder)

weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, wl=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)


weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64], stddev=5e-2, wl=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')

reshape = tf.reshape(pool2, [batch_size, -1])
dim = reshape.get_shape()[1].value
weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, wl=0.004)
bias3 = tf.Variable(tf.constant(0.1, shape=[384]))
local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3)

weight4 = variable_with_weight_loss(shape=[384, 192], stddev=0.04, wl=0.004)
bias4 = tf.Variable(tf.constant(0.1, shape=[192]))
local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4)

weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1/192.0, wl=0.0)
bias5 = tf.Variable(tf.constant(0.0, shape=[10]))
logits = tf.add(tf.matmul(local4, weight5), bias5)

loss = loss(logits, label_holder)


train_op = tf.train.AdamOptimizer(1e-3).minimize(loss) #0.72

top_k_op = tf.nn.in_top_k(logits, label_holder, 1)

sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

tf.train.start_queue_runners()
###
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))
	
###
num_examples = 10000
import math
num_iter = int(math.ceil(num_examples / batch_size))
true_count = 0  
total_sample_count = num_iter * batch_size
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

precision = true_count / total_sample_count
print('precision @ 1 = %.3f' % precision)

source