版权声明：欢迎转载，转载请注明出处：土豆洋芋山药蛋 https://blog.csdn.net/qq_33414271/article/details/86496900
前景回顾：
【手把手TensorFlow】一、从开始使用TensorFlow到弄清楚“搭建神经网络套路”
【手把手TensorFlow】二、神经网络优化
【手把手TensorFlow】三、神经网络搭建完整框架+MNIST数据集实践
【手把手TensorFlow】四、输入手写数字并输出识别结果
全连接 NN：每个神经元与前后相邻层的每一个神经元都有连接关系，输入是特征，输出为预测的结果。
参数个数：∑ （前层 × 后层 + 后层）
但待优化的参数过多，容易导致模型过拟合，在实际应用中，会先对原始图像进行特征提取，把提取到的特征喂给全连接网络，再让全连接网络计算出分类评估值。
一、卷积神经网络
1.1卷积
卷积是一种有效提取图片特征的方法。一般用一个正方形卷积核，遍历图片上的每一个像素点。图片与卷积核重合区域内相对应的每一个像素值乘卷积核内相对应点的权重，然后求和，再加上偏置后，最后得到输出图片中的一个像素值。
1.2全零填充 Padding
有时会在输入图片周围进行全零填充，这样可以保证输出图片的尺寸和输入图片一致。
使用 padding 和不使用 padding 的输出维度：
上一行公式是使用 padding 的输出图片边长，下一行公式是不使用 padding的输出图片边长。公式如果不能整除，需要向上取整数。如果用全零填充，也就是 padding=SAME。如果不用全零填充，也就是 padding=VALID。
1.3TensorFlow中的计算
计算卷积：
池化：
舍弃 Dropout：
在神经网络的训练过程中，将一部分神经元按照一定概率从神经网络中暂时舍弃。使用时被舍弃的神经元恢复链接。Dropout 可以有效减少过拟合。
输出=tf.nn.dropout（上层输出，暂时舍弃神经元的概率）
1.4卷积神经网络的发展史
卷积神经网络的主要模块：
二、实践代码
mnist_lenet5_forward.py
主要改动为前向传播过程的网络体系架构搭建。
#coding:utf-8
import tensorflow as tf
IMAGE_SIZE = 28#图片分辨率为28*28
NUM_CHANNELS = 1#灰度图像通道个数为1
CONV1_SIZE = 5 #第一层卷积大小为5
CONV1_KERNEL_NUM = 32 #第一层卷积核个数为32
CONV2_SIZE = 5 #第二层卷积核大小为5
CONV2_KERNEL_NUM = 64 #第二层卷积核个数为64
FC_SIZE = 512 #全连接神经元个数为512个，第一层512个
OUTPUT_NODE = 10 #输出节点为10个
# =============================================================================
# 获取权重
# =============================================================================
def get_weight(shape, regularizer):
w = tf.Variable(tf.truncated_normal(shape,stddev=0.1))
if regularizer != None: tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
return w
# =============================================================================
# 获取偏置
# =============================================================================
def get_bias(shape):
b = tf.Variable(tf.zeros(shape))
return b
# =============================================================================
# 卷积层计算函数
# =============================================================================
def conv2d(x,w):
return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME')
'''
tf.nn.conv2d(输入描述，卷积核描述，核滑动步长，填充模式)
输入描述【batch,行分辨率，列分辨率，通道数】
卷积核描述【行分辨率，列分辨率，通道数，卷积核个数】
核滑动步长【1，行步长，列步长，1】
下面池化层的描述类似
'''
# =============================================================================
# 最大池化层计算函数
# =============================================================================
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# =============================================================================
# 前向传播过程
# =============================================================================
def forward(x, train, regularizer):
#第一层卷积
conv1_w = get_weight([CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_KERNEL_NUM], regularizer)
conv1_b = get_bias([CONV1_KERNEL_NUM])
conv1 = conv2d(x, conv1_w)
relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_b))
pool1 = max_pool_2x2(relu1)
#第二层卷积
conv2_w = get_weight([CONV2_SIZE, CONV2_SIZE, CONV1_KERNEL_NUM, CONV2_KERNEL_NUM],regularizer)
conv2_b = get_bias([CONV2_KERNEL_NUM])
conv2 = conv2d(pool1, conv2_w)
relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_b))
pool2 = max_pool_2x2(relu2)
#第二层池化层的输出pool2矩阵转化为全连接层输入格式
pool_shape = pool2.get_shape().as_list()
nodes = pool_shape[1] * pool_shape[2] * pool_shape[3]
reshaped = tf.reshape(pool2, [pool_shape[0], nodes])
#类似原来的第一次全连接
fc1_w = get_weight([nodes, FC_SIZE], regularizer)
fc1_b = get_bias([FC_SIZE])
fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_w) + fc1_b)
if train: fc1 = tf.nn.dropout(fc1, 0.5)
#类似原来第二次全连接
fc2_w = get_weight([FC_SIZE, OUTPUT_NODE], regularizer)
fc2_b = get_bias([OUTPUT_NODE])
y = tf.matmul(fc1, fc2_w) + fc2_b
return y
mnist_lenet5_backward.py
#coding:utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_lenet5_forward
import os
import numpy as np
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.005
LEARNING_RATE_DECAY = 0.99
REGULARIZER = 0.0001
STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH="./model/"
MODEL_NAME="mnist_model"
# =============================================================================
# 反向传播过程
# =============================================================================
def backward(mnist):
x = tf.placeholder(tf.float32,[
BATCH_SIZE,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.NUM_CHANNELS])
y_ = tf.placeholder(tf.float32, [None, mnist_lenet5_forward.OUTPUT_NODE])
y = mnist_lenet5_forward.forward(x,True, REGULARIZER)
global_step = tf.Variable(0, trainable=False)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
cem = tf.reduce_mean(ce)
loss = cem + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
mnist.train.num_examples / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
ema_op = ema.apply(tf.trainable_variables())
with tf.control_dependencies([train_step, ema_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
for i in range(STEPS):
xs, ys = mnist.train.next_batch(BATCH_SIZE)
reshaped_xs = np.reshape(xs,(
BATCH_SIZE,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.NUM_CHANNELS))
_, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: reshaped_xs, y_: ys})
if i % 100 == 0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
def main():
mnist = input_data.read_data_sets("./data/", one_hot=True)
backward(mnist)
if __name__ == '__main__':
main()
mnist_lenet5_test.py
#coding:utf-8
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import mnist_lenet5_forward
import mnist_lenet5_backward
import numpy as np
TEST_INTERVAL_SECS = 5
def test(mnist):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32,[
mnist.test.num_examples,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.NUM_CHANNELS])
y_ = tf.placeholder(tf.float32, [None, mnist_lenet5_forward.OUTPUT_NODE])
y = mnist_lenet5_forward.forward(x,False,None)
ema = tf.train.ExponentialMovingAverage(mnist_lenet5_backward.MOVING_AVERAGE_DECAY)
ema_restore = ema.variables_to_restore()
saver = tf.train.Saver(ema_restore)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(mnist_lenet5_backward.MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
reshaped_x = np.reshape(mnist.test.images,(
mnist.test.num_examples,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.IMAGE_SIZE,
mnist_lenet5_forward.NUM_CHANNELS))
accuracy_score = sess.run(accuracy, feed_dict={x:reshaped_x,y_:mnist.test.labels})
print("After %s training step(s), test accuracy = %g" % (global_step, accuracy_score))
else:
print('No checkpoint file found')
return
time.sleep(TEST_INTERVAL_SECS)
def main():
mnist = input_data.read_data_sets("./data/", one_hot=True)
test(mnist)
if __name__ == '__main__':
main()