原理就不多讲了,直接上代码,有详细注释。
#coding:utf-8 import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets(‘MNIST_data‘,one_hot=True) #每个批次的大小 batch_size = 100 n_batch = mnist.train._num_examples // batch_size def weight_variable(shape): initial = tf.truncated_normal(shape,stddev=0.1) #生成一个截断的正态分布 return tf.Variable(initial) def bias_variable(shape): initial = tf.constant(0.1,shape = shape) return tf.Variable(initial) #卷基层 def conv2d(x,W): return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding=‘SAME‘) #池化层 def max_pool_2x2(x): return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding=‘SAME‘) #定义两个placeholder x = tf.placeholder(tf.float32, [None,784]) y = tf.placeholder(tf.float32,[None,10]) #改变x的格式转为4D的向量[batch,in_height,in_width,in_channels] x_image = tf.reshape(x, [-1,28,28,1]) #初始化第一个卷基层的权值和偏置 W_conv1 = weight_variable([5,5,1,32]) #5*5的采样窗口 32个卷积核从一个平面抽取特征 32个卷积核是自定义的 b_conv1 = bias_variable([32]) #每个卷积核一个偏置值 #把x_image和权值向量进行卷积,再加上偏置值,然后应用于relu激活函数 h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1) h_pool1 = max_pool_2x2(h_conv1) #进行max-pooling #初始化第二个卷基层的权值和偏置 W_conv2 = weight_variable([5,5,32,64]) # 5*5的采样窗口 64个卷积核从32个平面抽取特征 由于前一层操作得到了32个特征图 b_conv2 = bias_variable([64]) #每一个卷积核一个偏置值 #把h_pool1和权值向量进行卷积 再加上偏置值 然后应用于relu激活函数 h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2) #进行max-pooling #28x28的图片第一次卷积后还是28x28 第一次池化后变为14x14 #第二次卷积后 变为14x14 第二次池化后变为7x7 #通过上面操作后得到64张7x7的平面 #初始化第一个全连接层的权值 W_fc1 = weight_variable([7*7*64,1024])#上一层有7*7*64个神经元,全连接层有1024个神经元 b_fc1 = bias_variable([1024]) #1024个节点 #把第二个池化层的输出扁平化为一维 h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64]) #求第一个全连接层的输出 h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1) #keep_prob用来表示神经元的输出概率 keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob) #初始化第二个全连接层 W_fc2 = weight_variable([1024,10]) b_fc2 = bias_variable([10]) #计算输出 prediction = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2) #交叉熵代价函数 cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction)) #使用AdamOptimizer进行优化 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #结果存放在一个布尔列表中 correct_prediction = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1)) #argmax返回一维张量中最大的值所在的位置 #求准确率 accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) saver = tf.train.Saver() with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for epoch in range(50): for batch in range(n_batch): batch_xs,batch_ys = mnist.train.next_batch(batch_size) sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.7}) acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0}) print ("Iter "+ str(epoch) + ", Testing Accuracy= " + str(acc)) saver.save(sess,save_path=‘/home/xxx/logs/mnistmodel‘,global_step=1)#将训练出来的权重参数保存
结果
Iter 0, Testing Accuracy= 0.8517 Iter 1, Testing Accuracy= 0.9612 Iter 2, Testing Accuracy= 0.9769 Iter 3, Testing Accuracy= 0.9804 Iter 4, Testing Accuracy= 0.9832 Iter 5, Testing Accuracy= 0.9844 Iter 6, Testing Accuracy= 0.988 Iter 7, Testing Accuracy= 0.9882 Iter 8, Testing Accuracy= 0.9875 Iter 9, Testing Accuracy= 0.9889 Iter 10, Testing Accuracy= 0.9891 Iter 11, Testing Accuracy= 0.9897 Iter 12, Testing Accuracy= 0.9891 Iter 13, Testing Accuracy= 0.9897 Iter 14, Testing Accuracy= 0.9905 Iter 15, Testing Accuracy= 0.9913 Iter 16, Testing Accuracy= 0.9908 Iter 17, Testing Accuracy= 0.9909 Iter 18, Testing Accuracy= 0.9913 Iter 19, Testing Accuracy= 0.9915 Iter 20, Testing Accuracy= 0.9902 Iter 21, Testing Accuracy= 0.9899 Iter 22, Testing Accuracy= 0.9912 Iter 23, Testing Accuracy= 0.9911 Iter 24, Testing Accuracy= 0.9907 Iter 25, Testing Accuracy= 0.9918 Iter 26, Testing Accuracy= 0.9919 Iter 27, Testing Accuracy= 0.9916 Iter 28, Testing Accuracy= 0.9899 Iter 29, Testing Accuracy= 0.9924 Iter 30, Testing Accuracy= 0.9913 Iter 31, Testing Accuracy= 0.992 Iter 32, Testing Accuracy= 0.9927 Iter 33, Testing Accuracy= 0.9919 Iter 34, Testing Accuracy= 0.9922 Iter 35, Testing Accuracy= 0.9918 Iter 36, Testing Accuracy= 0.9932 Iter 37, Testing Accuracy= 0.9924 Iter 38, Testing Accuracy= 0.9917 Iter 39, Testing Accuracy= 0.9919 Iter 40, Testing Accuracy= 0.9933 Iter 41, Testing Accuracy= 0.9924 Iter 42, Testing Accuracy= 0.9926 Iter 43, Testing Accuracy= 0.9932 Iter 44, Testing Accuracy= 0.9922 Iter 45, Testing Accuracy= 0.9925 Iter 46, Testing Accuracy= 0.9928 Iter 47, Testing Accuracy= 0.9935 Iter 48, Testing Accuracy= 0.9922 Iter 49, Testing Accuracy= 0.9926
# load MNIST datafrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("Mnist_data/", one_hot=True) # start tensorflow interactiveSessionimport tensorflow as tfsess = tf.InteractiveSession()batch_size = 50 n_batch = mnist.train._num_examples // batch_size # weight initializationdef weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) def bias_variable(shape): initial = tf.constant(0.1, shape = shape) return tf.Variable(initial) # convolutiondef conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding=‘SAME‘)# poolingdef max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding=‘SAME‘) # Create the model# placeholderx = tf.placeholder("float", [None, 784])y_ = tf.placeholder("float", [None, 10])# variablesW = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x,W) + b) # first convolutinal layerw_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32]) x_image = tf.reshape(x, [-1, 28, 28, 1]) h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1) # second convolutional layerw_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) # densely connected layerw_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) # dropoutkeep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # readout layerw_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10]) y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, w_fc2) + b_fc2) # train and evaluate the modelcross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))train_step = tf.train.AdagradOptimizer(1e-4).minimize(cross_entropy)correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))sess.run(tf.initialize_all_variables()) 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, train accuracy %g" %(i, train_accuracy)) train_step.run(feed_dict={x:batch[0], y_:batch[1], keep_prob:0.5}) print ("test accuracy %g" % accuracy.eval(feed_dict={x:mnist.test.images, y_:mnist.test.labels, keep_prob:1.0}))
原文地址:https://www.cnblogs.com/shuimuqingyang/p/9967961.html
时间: 2024-11-05 12:21:41