Tensorflow中mnist数据使用CNN训练

实验代码如下：

import tensorflow as tfimport tensorflow.examples.tutorials.mnist.input_data as input_datamnist = input_data.read_data_sets('MNIST_data', one_hot=True)sess = tf.InteractiveSession()def 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)def conv2d(x, W):  return tf.nn.conv2d(x, 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')x = tf.placeholder("float", shape=[None, 784])y_ = tf.placeholder("float", shape=[None, 10])W_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)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)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)keep_prob = tf.placeholder("float")h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))train_step = tf.train.AdamOptimizer(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, training 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}))

测试结果：

Extracting MNIST_data\train-images-idx3-ubyte.gzExtracting MNIST_data\train-labels-idx1-ubyte.gzExtracting MNIST_data\t10k-images-idx3-ubyte.gzExtracting MNIST_data\t10k-labels-idx1-ubyte.gz2017-06-01 14:15:54.606155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.606155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE2 instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.606155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.607155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.607155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.608155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.608155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.2017-06-01 14:15:54.608155: W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.WARNING:tensorflow:From F:\python35workspace\NLP\tensorflow\cnntest.py:42: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.Instructions for updating:Use `tf.global_variables_initializer` instead.step 0, training accuracy 0.12step 100, training accuracy 0.82step 200, training accuracy 0.9step 300, training accuracy 0.84step 400, training accuracy 0.96step 500, training accuracy 0.92step 600, training accuracy 0.92step 700, training accuracy 0.96step 800, training accuracy 1step 900, training accuracy 0.96step 1000, training accuracy 1step 1100, training accuracy 0.9step 1200, training accuracy 0.98step 1300, training accuracy 0.98step 1400, training accuracy 0.94step 1500, training accuracy 0.94step 1600, training accuracy 0.98step 1700, training accuracy 1step 1800, training accuracy 0.98step 1900, training accuracy 0.96step 2000, training accuracy 0.98step 2100, training accuracy 0.92step 2200, training accuracy 0.98step 2300, training accuracy 1step 2400, training accuracy 1step 2500, training accuracy 0.94step 2600, training accuracy 1step 2700, training accuracy 1step 2800, training accuracy 0.98step 2900, training accuracy 0.98step 3000, training accuracy 1step 3100, training accuracy 0.98step 3200, training accuracy 1step 3300, training accuracy 0.98step 3400, training accuracy 0.96step 3500, training accuracy 1step 3600, training accuracy 0.96step 3700, training accuracy 0.96step 3800, training accuracy 0.98step 3900, training accuracy 0.96step 4000, training accuracy 0.98step 4100, training accuracy 1step 4200, training accuracy 1step 4300, training accuracy 1step 4400, training accuracy 0.96step 4500, training accuracy 1step 4600, training accuracy 0.98step 4700, training accuracy 1step 4800, training accuracy 1step 4900, training accuracy 1step 5000, training accuracy 0.98step 5100, training accuracy 1step 5200, training accuracy 0.98step 5300, training accuracy 0.94step 5400, training accuracy 0.98step 5500, training accuracy 1step 5600, training accuracy 0.98step 5700, training accuracy 1step 5800, training accuracy 0.98step 5900, training accuracy 1step 6000, training accuracy 1step 6100, training accuracy 1step 6200, training accuracy 0.98step 6300, training accuracy 1step 6400, training accuracy 1step 6500, training accuracy 0.96step 6600, training accuracy 0.98step 6700, training accuracy 1step 6800, training accuracy 1step 6900, training accuracy 1step 7000, training accuracy 1step 7100, training accuracy 0.98step 7200, training accuracy 1step 7300, training accuracy 1step 7400, training accuracy 1step 7500, training accuracy 1step 7600, training accuracy 0.98step 7700, training accuracy 1step 7800, training accuracy 1step 7900, training accuracy 0.96step 8000, training accuracy 1step 8100, training accuracy 1step 8200, training accuracy 1step 8300, training accuracy 1step 8400, training accuracy 1step 8500, training accuracy 1step 8600, training accuracy 1step 8700, training accuracy 0.98step 8800, training accuracy 1step 8900, training accuracy 1step 9000, training accuracy 1step 9100, training accuracy 0.98step 9200, training accuracy 0.98step 9300, training accuracy 1step 9400, training accuracy 1step 9500, training accuracy 0.98step 9600, training accuracy 0.98step 9700, training accuracy 0.96step 9800, training accuracy 1step 9900, training accuracy 1step 10000, training accuracy 0.98step 10100, training accuracy 1step 10200, training accuracy 0.98step 10300, training accuracy 1step 10400, training accuracy 0.98step 10500, training accuracy 1step 10600, training accuracy 0.98step 10700, training accuracy 0.96step 10800, training accuracy 1step 10900, training accuracy 0.98step 11000, training accuracy 0.98step 11100, training accuracy 1step 11200, training accuracy 1step 11300, training accuracy 1step 11400, training accuracy 0.98step 11500, training accuracy 1step 11600, training accuracy 1step 11700, training accuracy 1step 11800, training accuracy 0.98step 11900, training accuracy 1step 12000, training accuracy 1step 12100, training accuracy 1step 12200, training accuracy 0.98step 12300, training accuracy 0.98step 12400, training accuracy 1step 12500, training accuracy 1step 12600, training accuracy 1step 12700, training accuracy 1step 12800, training accuracy 1step 12900, training accuracy 1step 13000, training accuracy 1step 13100, training accuracy 1step 13200, training accuracy 1step 13300, training accuracy 1step 13400, training accuracy 1step 13500, training accuracy 1step 13600, training accuracy 1step 13700, training accuracy 1step 13800, training accuracy 1step 13900, training accuracy 1step 14000, training accuracy 1step 14100, training accuracy 1step 14200, training accuracy 0.98step 14300, training accuracy 1step 14400, training accuracy 1step 14500, training accuracy 1step 14600, training accuracy 1step 14700, training accuracy 1step 14800, training accuracy 1step 14900, training accuracy 1step 15000, training accuracy 1step 15100, training accuracy 1step 15200, training accuracy 1step 15300, training accuracy 1step 15400, training accuracy 1step 15500, training accuracy 1step 15600, training accuracy 0.98step 15700, training accuracy 1step 15800, training accuracy 1step 15900, training accuracy 1step 16000, training accuracy 1step 16100, training accuracy 1step 16200, training accuracy 1step 16300, training accuracy 1step 16400, training accuracy 1step 16500, training accuracy 1step 16600, training accuracy 1step 16700, training accuracy 1step 16800, training accuracy 1step 16900, training accuracy 1step 17000, training accuracy 1step 17100, training accuracy 1step 17200, training accuracy 1step 17300, training accuracy 1step 17400, training accuracy 1step 17500, training accuracy 1step 17600, training accuracy 1step 17700, training accuracy 1step 17800, training accuracy 1step 17900, training accuracy 1step 18000, training accuracy 1step 18100, training accuracy 1step 18200, training accuracy 1step 18300, training accuracy 1step 18400, training accuracy 0.98step 18500, training accuracy 1step 18600, training accuracy 1step 18700, training accuracy 1step 18800, training accuracy 1step 18900, training accuracy 1step 19000, training accuracy 1step 19100, training accuracy 1step 19200, training accuracy 1step 19300, training accuracy 1step 19400, training accuracy 1step 19500, training accuracy 1step 19600, training accuracy 1step 19700, training accuracy 1step 19800, training accuracy 1step 19900, training accuracy 1test accuracy 0.9928

实验代码解释：

http://wiki.jikexueyuan.com/project/tensorflow-zh/tutorials/mnist_pros.html