Tensorflow学习:卷积神经网络CNN应用于手写数字识别(MNIST数据集分类)
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNST_data", one_hot=True)
batch_size = 100
n_batch = mnist.train.num_examples // batch_size
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):
'''conv2d:是一个二维的卷积操作,
x:输入的tensor(数据),数据的形状[batch(批次的大小:100),in_height(长:输入层的长),
in_width(宽:输入层的宽),in_channels(通道数,如果是黑白的照片就是1,如果是彩色的照片就是2)]
W:滤波器或者说是卷积核,也是一个tensor(数据),形状[filter_height(滤波器的长),filter_width(滤波器的宽),
in_channels(输入通道数),out_channels](输出通道数)
strides:步长,strides[0]=strides[3]=1,strides[1]:代表x方向的步长,strides[2]代表y方向的步长
padding:same,valid'''
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
'''输入的tensor(数据),数据的形状[batch(批次的大小:100),in_height(长:输入层的长),
in_width(宽:输入层的宽),in_channels(通道数,如果是黑白的照片就是1,如果是彩色的照片就是2)]
ksize:ksize[0]=ksize[3]=1,ksize[0]:x方向的大小,ksize[2]:y方向的大小
strides:步长,strides[0]=strides[3]=1,strides[1]:代表x方向的步长,strides[2]代表y方向的步长
padding:same,valid
'''
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
'''[batch,in_height,in_width,in_channels]:
batch:一个批次的大小:前面设置的100,之后会赋值为100
in_height,in_width:长宽,把784复原为原来28*28的二维的
in_channels:(通道数,如果是黑白的照片就是1,如果是彩色的照片就是2)
'''
x_image = tf.reshape(x, [-1, 28, 28, 1])
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
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)
'''28*28的图片第一次卷积后还是28*28,第一次池化后变成14*14,
第二次卷积后还是14*14,第二次池化后变成:7*7,
通过上面的卷积和池化操作后,得到64张7*7的特征图(平面)'''
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_drop = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_drop)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for step in range(21):
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_drop: 0.7})
acc = sess.run(accuracy, feed_dict={
x: mnist.test.images, y: mnist.test.labels, keep_drop: 1.0})
print("Iter " + str(step) + ",Testing Accuracy=" + str(acc))
运行结果:
