使用tensorflow實現一個簡單的卷積神經，使用的數據集是MNIST，本節將使用兩個卷積層加一個全連接層，構建一個簡單有代表性的卷積網絡。

代碼是按照書上的敲的，第一步就是導入數據庫，設置節點的初始值，Tf.nn.conv2d是tensorflow中的2維卷積，參數x是輸入，W是卷積的參數，比如【5,5,1,32】，前面兩個數字代表卷積核的尺寸，第三個數字代表有幾個通道，比如灰度圖是1，彩色圖是3.最后一個代表卷積的數量，總的實現代碼如下：

from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf mnist = input_data.read_data_sets("MNSIT_data/", one_hot=True) sess = tf.InteractiveSession()   # In[2]: #由于W和b在各層中均要用到，先定義乘函數。 #tf.truncated_normal：截斷正態分布，即限制范圍的正態分布 def weight_variable(shape):   initial = tf.truncated_normal(shape, stddev=0.1)   return tf.Variable(initial)   # In[7]: #bias初始化值0.1. def bias_variable(shape):   initial = tf.constant(0.1, shape=shape)   return tf.Variable(initial)   # In[12]: #tf.nn.conv2d:二維的卷積 #conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None,data_format=None, name=None) #filter:A 4-D tensor of shape #   `[filter_height, filter_width, in_channels, out_channels]` #strides:步長，都是1表示所有點都不會被遺漏。1-D 4值，表示每歌dim的移動步長。 # padding:邊界的處理方式，“SAME"、"VALID”可選 def conv2d(x, W):   return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')  #tf.nn.max_pool:最大值池化函數，即求2*2區域的最大值，保留最顯著的特征。 #max_pool(value, ksize, strides, padding, data_format="NHWC", name=None) #ksize:池化窗口的尺寸 #strides:[1,2,2,1]表示橫豎方向步長為2 def max_pool_2x2(x):   return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides = [1, 2, 2, 1], padding='SAME')   x = tf.placeholder(tf.float32, [None, 784]) y_ = tf.placeholder(tf.float32, [None, 10]) #tf.reshape:tensor的變形函數。 #-1：樣本數量不固定 #28,28：新形狀的shape #1:顏色通道數 x_image = tf.reshape(x, [-1, 28, 28, 1])   #卷積層包含三部分：卷積計算、激活、池化 #[5,5,1,32]表示卷積核的尺寸為5×5, 顏色通道為1, 有32個卷積核 W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1)   W_conv2 = weight_variable([5, 5, 32, 64]) b_conv2 = bias_variable([64]) h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2)   #經過2次2×2的池化后，圖像的尺寸變為7×7,第二個卷積層有64個卷積核，生成64類特征，因此，卷積最后輸出為7×7×64. #tensor進入全連接層之前，先將64張二維圖像變形為1維圖像，便于計算。 W_fc1 = weight_variable([7*7*64, 1024]) b_fc1 = bias_variable([1024]) h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)   #對全連接層做dropot keep_prob = tf.placeholder(tf.float32) h_fc1_dropout = tf.nn.dropout(h_fc1, keep_prob)   #又一個全連接后foftmax分類 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv = tf.nn.softmax(tf.matmul(h_fc1_dropout, W_fc2) + b_fc2)   cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y_conv), reduction_indices=[1])) #AdamOptimizer：Adam優化函數 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)    correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y_conv, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))   #訓練，并且每100個batch計算一次精度 tf.global_variables_initializer().run() for i in range(20000):   batch = mnist.train.next_batch(50)   if i%100 == 0:     train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_:batch[1], keep_prob:1.0})     print("step %d, training accuracy %g" %(i, train_accuracy))   train_step.run(feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5})   #在測試集上測試 print("test accuracy %g"%accuracy.eval(feed_dict={x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0}))