训练卷积神经网络,并将训练得到的模型保存。
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
sess = tf.Session()
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1}) #(10000,10)
correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1)) #比较是否相等,返回bool
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) #将比较结果转换成tf.float32,并计算平均值
result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
return result
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')
keep_prob = tf.placeholder(tf.float32)
with tf.name_scope('inputs'):
xs = tf.placeholder(tf.float32, [None, 784], name='x_input') #28x28
ys = tf.placeholder(tf.float32, [None, 10], name='y_input')
x_image = tf.reshape(xs, [-1, 28, 28, 1])
#print("n_samples:", x_image.shape)
#conv1 layer
W_conv1 = weight_variable([5, 5, 1, 32]) #patch 5x5 in size=1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1) # 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])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2) # size 7x7x64
#func1 layer
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)
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)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),
reduction_indices=[1])) #loss
tf.summary.scalar('loss', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
init = tf.global_variables_initializer()
#summary writer goes in here
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter('D:/deng/logs/train', sess.graph)
test_writer = tf.summary.FileWriter('D:/deng/logs/test', sess.graph)
sess.run(init)
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 % 50 == 0:
print(compute_accuracy(
mnist.test.images, mnist.test.labels
))
saver = tf.train.Saver()
model_path = "D:/deng/model/model.ckpt"
saver.save(sess, model_path)
训练结果:
最终,准确率达到90%以上。
保存模型: