数据集#
60000行的训练数据集（mnist.train）和10000行的测试数据集（mnist.test）
每张图片包含28x28=784个像素点，用数字数组来表示：
其中像素的强度值介于0和1之间，如何展开这个数组（数字间的顺序）不重要（因此损失了结构化信息），只要保持各个图片采用相同的方式展开成784维的向量。
Feature最后成为一个60000x784的矩阵。
Label介于0到9之间，用一个长度为10的向量表示，例如标签0将表示成([1,0,0,0,0,0,0,0,0,0,0])。
分类器#
- Softmax回归
Softmax回归本质上是Logistic回归在多分类问题上的推广，可以估算每一种label出现的概率。
http://ufldl.stanford.edu/wiki/index.php/Softmax%E5%9B%9E%E5%BD%92
其准确率为91% - CNN（卷积神经网络）
CNN是深度学习算法在图像处理领域的一个应用。
http://blog.csdn.net/stdcoutzyx/article/details/41596663
其准确率为99.2%
代码#
'''定义模型''' import tensorflow as tf x = tf.placeholder(tf.float32, [None, 784]) W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x,W) + b) y_ = tf.placeholder("float", [None,10]) '''定义错误衡量方式交互熵''' cross_entropy = -tf.reduce_sum(y_*tf.log(y)) '''利用梯度下降优化优化交互熵''' train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy) init = tf.initialize_all_variables() sess = tf.Session() sess.run(init) '''实际上是随机梯度下降，每次取100个数据，重复1000次''' for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) ''''正确率预测''' correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
import tensorflow as tf import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) x = tf.placeholder("float", shape=[None, 784]) y_ = tf.placeholder("float", shape=[None, 10]) 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') 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_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1])) 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, tf.float32)) sess = tf.InteractiveSession() 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}))
本文参考Tensorflow官方中文教程
