import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# 60000行的训练数据集(mnist.train)和10000行的测试数据集(mnist.test)
# (每一行包含28*28=784个像素点)
# Import data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# init weight
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.01)
return tf.Variable(initial)
# init bias
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
# create CNN layer
def conv2d(x, W):
# stride [1,x_movement,y_movement,1],stride[0] and stride[3] must be 1
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') ### ???
# create pooling ,in order to reduce the loss of info when cutting the image
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# def compute_accuracy
def comput_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_pre = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pre, tf.float32))
result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
return result
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape) #[n_sample.28,28,1]
# conv1 layer
W_conv1 = weight_variable([5, 5, 1, 32]) # patch 5x5,in size 1,out size 32
b_conv1 = bias_variable([32])
hide_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
# relu: let data nonlinear , output size 28x28x32
hide_pool1 = max_pool_2x2(hide_conv1) # output size 14x14x32
# conv2 layer
W_conv2 = weight_variable([5, 5, 32, 64]) # patch 5x5,in size 32,out size 64
b_conv2 = bias_variable([64])
hide_conv2 = tf.nn.relu(conv2d(hide_pool1, W_conv2) + b_conv2) # relu: let data nonlinear , output size 14x14x64
hide_pool2 = max_pool_2x2(hide_conv2) # output size 7x7x64
# func1 layer
W_fc1 = weight_variable([7*7*64, 1024]) # 全连接
b_fc1 = bias_variable([1024])
# [n_samples,7,7,64] ->> [n_samples,7*7*64]
h_pool2_flat = tf.reshape(hide_pool2, [-1, 7*7*64]) # 转化为1维
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) # 点积
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# func2 layer
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# the error between the prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# create session
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if i % 40 == 0:
print(comput_accuracy(mnist.test.images, mnist.test.labels))
-