《tensorflow实战》之实现复杂的卷积网络（五）

一 基本概念

1. 正则化

L1正则化和L2正则化的定义：

• L1正则化是指权值向量w中各个元素的绝对值之和，通常表示为||w||1。
• L2正则化是指权值向量w中各个元素的平方和然后再求平方根（可以看到Ridge回归的L2正则化项有平方符号），通常表示为||w||2。

L1正则化和L2正则化的作用

• L1正则化可以产生稀疏权值矩阵，即产生一个稀疏模型，可以用于特征选择，大部分无用特征的值置为0。
• L2正则化可以防止模型过拟合（overfitting），让权重不过大，使得特征权重比较平均；一定程度上，L1也可以防止过拟合。

2.LRN

LRN层模仿了生物神经系统的“侧抑制”机制，对局部神经元的活动产生创建竞争环境，使得其中响应较大的值变的相对更大并且抑制其他反馈较小的神经元，增强了模型的泛化能力。局部响应归一化包含两种模式：一种是通道间归一化，局部区域范围在相邻通道内，没有空间拓展；另一种是通道内归一化，局部区域在空间上扩展，但是只针对独立通道进行。

二 Tensorflow实现

1.导入库

• batch_size是训练批次大小
• max_steps训练轮数

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'

2.定义初始化函数

• 用wl控制L2loss的大小，用tf.nn.l2_loss产生L2 loos，将其与wl相乘，即为weight loss。
• 用tf.nn.sparse_softmax_cross_entropy_with_logits一次性计算了softmax和cross entropy loos。
• total_loss是最终的loos，其包含了weight loss和cross entropy loos。

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):
    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)
    return tf.add_n(tf.get_collection('losses'), name='total_loss')

3.初始化模型结构

• cifar10.maybe_download_and_extract()下载数据并解压
• tf.nn.in_top_k求输出分数最高的准确率。
• tf.train.start_queue_runners()用了16路线程进行加速。
  

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()

4.模型训练和测试

• 第一个sess.run产生一个批次的数据
• 第二个sess.run计算loos和优化数据
• feed_dict喂入数据

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)