學習《Tensorflow入門教程》記錄 

卷積神經網路流程框圖如下：

First Conv and Pool Layers ——Second Conv and Pool Layers——First Fully Connected Layer——Dropout Layer——Second Fully Connected Layer——Final Layer
池化層簡單理解：把卷積得到的結果進行降維處理。

示例程式碼：

import tensorflow as tf
import random
import numpy as np
import matplotlib.pyplot as plt
import datetime

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("data/", one_hot=True)

tf.reset_default_graph()
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape = [None, 28,28,1])
y_ = tf.placeholder("float", shape = [None, 10])

#5*5的卷積核  1個通道的輸入影象  32個不同的卷積核，得到32個特徵圖
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1))
#偏置
b_conv1 = tf.Variable(tf.constant(.1, shape = [32]))

#進行卷積運算
#[1, 1, 1, 1] 中間2個1，卷積每次滑動的步長
#padding='SAME' 邊緣自動補充
h_conv1 = tf.nn.conv2d(input=x, filter=W_conv1, strides=[1, 1, 1, 1], padding='SAME') + b_conv1
h_conv1 = tf.nn.relu(h_conv1)
#進行池化
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

#定義為函式
def conv2d(x, W):
    return tf.nn.conv2d(input=x, filter=W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')

#全連線層
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(.1, shape = [64]))
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#First Fully Connected Layer
#經過了2次卷積和池化 28*28*1變成了7*7*64  定義得到了1024維特徵
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(.1, shape = [1024]))
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])   #把特徵拉成1條
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#Dropout Layer，防止過擬合
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

#第二次全連線層
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(.1, shape = [10]))

#Final Layer
y = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

crossEntropyLoss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_, logits = y))
trainStep = tf.train.AdamOptimizer().minimize(crossEntropyLoss)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

sess.run(tf.global_variables_initializer())

batchSize = 50
for i in range(1000):
    batch = mnist.train.next_batch(batchSize)
    trainingInputs = batch[0].reshape([batchSize,28,28,1])
    trainingLabels = batch[1]
    if i%100 == 0:
        trainAccuracy = accuracy.eval(session=sess, feed_dict={x:trainingInputs, y_: trainingLabels, keep_prob: 1.0})
        print ("step %d, training accuracy %g"%(i, trainAccuracy))
    trainStep.run(session=sess, feed_dict={x: trainingInputs, y_: trainingLabels, keep_prob: 0.5})

 

執行結果：
step 0, training accuracy 0.2
step 100, training accuracy 0.84
step 200, training accuracy 1
step 300, training accuracy 0.96
step 400, training accuracy 1
step 500, training accuracy 0.96
step 600, training accuracy 1
step 700, training accuracy 0.96
step 800, training accuracy 0.96
step 900, training accuracy 0.96