首先看一下卷積神經網路模型，如下圖：
卷積神經網路（CNN）由輸入層、卷積層、啟用函式、池化層、全連線層組成，即INPUT-CONV-RELU-POOL-FC
池化層：為了減少運算量和資料維度而設定的一種層。
程式碼如下：
n_input = 784 # 28*28的灰度圖 n_output = 10 # 完成一個10分類的操作 weights = { #'權重引數': tf.Variable(tf.高期([feature的H, feature的W, 當前feature連線的輸入的深度, 最終想得到多少個特徵圖], 標準差=0.1)), 'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)), 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)), #'全連線層引數': tf.Variable(tf.高斯([特徵圖H*特徵圖W*深度, 最終想得到多少個特徵圖], 標準差=0.1)), 'wd1': tf.Variable(tf.random_normal([7*7*128, 1024], stddev=0.1)), 'wd2': tf.Variable(tf.random_normal([1024, n_output], stddev=0.1)) } biases = { #'偏置引數': tf.Variable(tf.高斯([第1層有多少個偏置項], 標準差=0.1)), 'bc1': tf.Variable(tf.random_normal([64], stddev=0.1)), 'bc2': tf.Variable(tf.random_normal([128], stddev=0.1)), 'bd1': tf.Variable(tf.random_normal([1024], stddev=0.1)), 'bd2': tf.Variable(tf.random_normal([n_output], stddev=0.1)) } #卷積神經網路 def conv_basic(_input, _w, _b, _keepratio): #將輸入資料轉化成一個四維的[n, h, w, c]tensorflow格式資料 #_input_r = tf.將輸入資料轉化成tensorflow格式(輸入, shape=[batch_size大小, H, W, 深度]) _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1]) #第1層卷積 #_conv1 = tf.nn.卷積(輸入, 權重引數, 步長=[batch_size大小, H, W, 深度], padding='建議選擇SAME') _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME') #_conv1 = tf.nn.非線性啟用函式(tf.nn.加法(_conv1, _b['bc1'])) _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1'])) #第1層池化 #_pool1 = tf.nn.池化函式(_conv1, 指定池化視窗的大小=[batch_size大小, H, W, 深度], strides=[1, 2, 2, 1], padding='SAME') _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') #隨機殺死一些節點，不讓所有神經元都加入到訓練中 #_pool_dr1 = tf.nn.dropout(_pool1, 保留比例) _pool_dr1 = tf.nn.dropout(_pool1, _keepratio) #第2層卷積 _conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME') _conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2'])) _pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') _pool_dr2 = tf.nn.dropout(_pool2, _keepratio) #全連線層 #轉化成tensorflow格式 _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]]) #第1層全連線層 _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1'])) _fc_dr1 = tf.nn.dropout(_fc1, _keepratio) #第2層全連線層 _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2']) #返回值 out = { 'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool1_dr1': _pool_dr1, 'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'dense1': _dense1, 'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out } return out print ("CNN READY") #設定損失函式&最佳化器（程式碼說明：略 請看前面文件） learning_rate = 0.001 x = tf.placeholder("float", [None, nsteps, diminput]) y = tf.placeholder("float", [None, dimoutput]) myrnn = _RNN(x, weights, biases, nsteps, 'basic') pred = myrnn['O'] cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) optm = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) # Adam Optimizer accr = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(pred,1), tf.argmax(y,1)), tf.float32)) init = tf.global_variables_initializer() print ("Network Ready!") #訓練（程式碼說明：略 請看前面文件） training_epochs = 5 batch_size = 16 display_step = 1 sess = tf.Session() sess.run(init) print ("Start optimization") for epoch in range(training_epochs): avg_cost = 0. #total_batch = int(mnist.train.num_examples/batch_size) total_batch = 100 # Loop over all batches for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) batch_xs = batch_xs.reshape((batch_size, nsteps, diminput)) # Fit training using batch data feeds = {x: batch_xs, y: batch_ys} sess.run(optm, feed_dict=feeds) # Compute average loss avg_cost += sess.run(cost, feed_dict=feeds)/total_batch # Display logs per epoch step if epoch % display_step == 0: print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost)) feeds = {x: batch_xs, y: batch_ys} train_acc = sess.run(accr, feed_dict=feeds) print (" Training accuracy: %.3f" % (train_acc)) testimgs = testimgs.reshape((ntest, nsteps, diminput)) feeds = {x: testimgs, y: testlabels, istate: np.zeros((ntest, 2*dimhidden))} test_acc = sess.run(accr, feed_dict=feeds) print (" Test accuracy: %.3f" % (test_acc)) print ("Optimization Finished.")