MNIST手写数字识别
1. MNIST数据集
导入数据集:
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
数据集结构
图片集为二维矩阵:一张图片占一行,尺寸为28x28=784。
标签集为二维矩阵:一个标签占一行,one-hot:一个标签用10维向量表示。
- mnist.train.images:训练集:55000 张图片。[55000,784]
- mnist.train.labels:训练集标签。[55000,10]
- mnist.validation.images:验证集:5000 张图片
- mnist.validation.labels:验证集标签
- mnist.test.images:测试集:10000 张 图片
- mnist.test.labels:测试集标签
2. 一层神经网络
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
import tensorflow as tf
# creat placeholder
x = tf.placeholder(tf.float32, [None, 784],name="x_input")
y_ = tf.placeholder("float", [None,10])
# creat variable
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
# define how to compute
y = tf.nn.softmax(tf.matmul(x,W) + b)
tf.add_to_collection('predict', y) #用于加载模型获取要预测的网络结构
# define cost function
cross_entropy = -tf.reduce_sum(y_*tf.log(y))
# define optinizer
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
# define how to compute accuracy
# tf.argmax给出tensor对象在某一维上的数据最大值所在的索引值。0:列最大;1:航最大
# tf.equal元素比较,相等为True,不等为False。
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
#tf.cast数据类型转换
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
#define initialize operation
init = tf.global_variables_initializer()
#creat a Session
sess = tf.Session()
total_step = 0
sess.run(init)
for i in range(1000):
total_step += 1
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
if total_step % 100 == 0:
# Calculate batch accuracy
print(sess.run(accuracy, feed_dict={x: batch_xs, y_: batch_ys}))
# Calculate batch loss
print(loss = sess.run(cross_entropy, feed_dict={x: batch_xs, y_: batch_ys}))
# Calculate testset accuracy
print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
sess.close()
3. CNN
import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
import tensorflow as tf
sess = tf.InteractiveSession()
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_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(2000):
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}))