卷积神经网络比神经网络稍微复杂一些，因为其多了一个卷积层(convolutional layer)和池化层(pooling layer)。
使用mnist数据集，n个数据，每个数据的像素为28*28*1=784。先让这些数据通过第一个卷积层，在这个卷积上指定一个3*3*1的feature，这个feature的个数设为64。接着经过一个池化层，让这个池化层的窗口为2*2。然后在经过一个卷积层，在这个卷积上指定一个3*3*64的feature，这个featurn的个数设置为128,。接着经过一个池化层，让这个池化层的窗口为2*2。让结果经过一个全连接层，这个全连接层大小设置为1024，在经过第二个全连接层，大小设置为10，进行分类。
import numpy as np import tensorflow as tf import matplotlib.pyplot as plt from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('data/', one_hot=True) trainimg = mnist.train.images trainlabel = mnist.train.labels testimg = mnist.test.images testlabel = mnist.test.labels print ("MNIST ready")
#像素点为784 n_input = 784 #十分类 n_output = 10 #wc1，第一个卷积层参数，3*3*1，共有64个 #wc2，第二个卷积层参数，3*3*64，共有128个 #wd1，第一个全连接层参数，经过两个池化层被压缩到7*7 #wd2，第二个全连接层参数 weights = { '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)), '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 = { '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)) }
定义前向传播函数。先将输入数据预处理，变成tensorflow支持的四维图像；进行第一层的卷积层处理，调用conv2d函数；将卷积结果用激活函数进行处理（relu函数）；将结果进行池化层处理，ksize代表窗口大小；将池化层的结果进行随机删除节点；进行第二层卷积和池化...；进行全连接层，先将数据进行reshape（此处为7*7*128）；进行激活函数处理；得出结果。前向传播结束。
def conv_basic(_input, _w, _b, _keepratio): # INPUT _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1]) # CONV LAYER 1 _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME') _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1'])) _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') _pool_dr1 = tf.nn.dropout(_pool1, _keepratio) # CONV LAYER 2 _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) # VECTORIZE _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]]) # FULLY CONNECTED LAYER 1 _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1'])) _fc_dr1 = tf.nn.dropout(_fc1, _keepratio) # FULLY CONNECTED LAYER 2 _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2']) # RETURN 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")
定义损失函数，定义优化器
x = tf.placeholder(tf.float32, [None, n_input]) y = tf.placeholder(tf.float32, [None, n_output]) keepratio = tf.placeholder(tf.float32) # FUNCTIONS _pred = conv_basic(x, weights, biases, keepratio)['out'] cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(_pred, y)) optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost) _corr = tf.equal(tf.argmax(_pred,1), tf.argmax(y,1)) accr = tf.reduce_mean(tf.cast(_corr, tf.float32)) init = tf.global_variables_initializer() # SAVER save_step = 1 saver = tf.train.Saver(max_to_keep=3) print ("GRAPH READY")
进行迭代
do_train = 1 sess = tf.Session() sess.run(init) training_epochs = 15 batch_size = 16 display_step = 1 if do_train == 1: for epoch in range(training_epochs): avg_cost = 0. total_batch = int(mnist.train.num_examples/batch_size) # Loop over all batches for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) # Fit training using batch data sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio:0.7}) # Compute average loss avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})/total_batch # Display logs per epoch step if epoch % display_step == 0: print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost)) train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.}) print (" Training accuracy: %.3f" % (train_acc)) #test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.}) #print (" Test accuracy: %.3f" % (test_acc))print ("OPTIMIZATION FINISHED")