本文主要有以下几个内容:
1.AlexNet模型介绍
在2012 ILSVRC竞赛(Large Scale Visual Recognition Challenge)中,AlexNet模型赢得了第一名,Top-5错误率为15.3%,比上一年冠军下降了10个百分点。从此,AlexNet成为CNN领域内具有重要历史意义的一个网络模型。LZ之前在博客中已经讲了怎么安装最新的tensorflow框架,以及配置其它依赖库的方法,这里就不再赘述。如果想要阅读相关文献可以阅读“ImageNet classification with deep convolutional neural network”的内容。
AlexNet共有八层,有60M以上的参数量,包含5个卷积层和3个全连接层,最后一个全连接层的输出有1000个输出的softmax。网络最后优化目标是最大化平均的multinomial logistic regression。
下面先贴出代码,然后在具体解释
#coding=utf-8
from __future__ import print_function
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/home/frr/MNIST_data", one_hot=True)
import tensorflow as tf
# 定义网络超参数
learning_rate = 0.001
training_iters = 200000
batch_size = 64
display_step = 20
# 定义网络参数
n_input = 784 # 输入的维度
n_classes = 10 # 标签的维度
dropout = 0.8 # Dropout 的概率
# 占位符输入
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32)
# 卷积操作
def conv2d(name, l_input, w, b):
return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
# 最大下采样操作
def max_pool(name, l_input, k):
return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
# 归一化操作
def norm(name, l_input, lsize=4):
return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
# 定义整个网络
def alex_net(_X, _weights, _biases, _dropout):
# 向量转为矩阵
_X = tf.reshape(_X, shape=[-1, 28, 28, 1])
# 卷积层
conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
# 下采样层
pool1 = max_pool('pool1', conv1, k=2)
# 归一化层
norm1 = norm('norm1', pool1, lsize=4)
# Dropout
norm1 = tf.nn.dropout(norm1, _dropout)
# 卷积
conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
# 下采样
pool2 = max_pool('pool2', conv2, k=2)
# 归一化
norm2 = norm('norm2', pool2, lsize=4)
# Dropout
norm2 = tf.nn.dropout(norm2, _dropout)
# 卷积
conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
# 下采样
pool3 = max_pool('pool3', conv3, k=2)
# 归一化
norm3 = norm('norm3', pool3, lsize=4)
# Dropout
norm3 = tf.nn.dropout(norm3, _dropout)
# 全连接层,先把特征图转为向量
dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]])
dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
# 全连接层
dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation
# 网络输出层
out = tf.matmul(dense2, _weights['out']) + _biases['out']
return out
# 存储所有的网络参数
weights = {
'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),
'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])),
'wd2': tf.Variable(tf.random_normal([1024, 1024])),
'out': tf.Variable(tf.random_normal([1024, 10]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([64])),
'bc2': tf.Variable(tf.random_normal([128])),
'bc3': tf.Variable(tf.random_normal([256])),
'bd1': tf.Variable(tf.random_normal([1024])),
'bd2': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# 构建模型
pred = alex_net(x, weights, biases, keep_prob)
# 定义损失函数和学习步骤
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = pred, labels = y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# 测试网络
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# 初始化所有的共享变量
init = tf.initialize_all_variables()
# 开启一个训练
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
# 获取批数据
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
if step % display_step == 0:
# 计算精度
acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
# 计算损失值
loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy = " + "{:.5f}".format(acc))
step += 1
print ("Optimization Finished!")
# 计算测试精度
print ("Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.}))
这么多代码手敲一遍工程量还是有一些哈,python 还是有点要注意,就是空格的对其问题,如果不对齐什么的,可能也会报错,所以,有可能的话,还是自己手敲一遍代码,逼着自己把代码通读一遍,况且这个代码很短,有兴趣的话还可以把tensorflow的源码再读一读。
我这里运行比较快啦,用了大概一分钟,训练的正确率再0.96左右,网络没有收敛,而且初始值是随机给定的,所以跑出来的答案会有些浮动,这个就是简单的一个tensorflow的实战啦。
后续,会按照我学习的进度继续更新的啦O(∩_∩)O