欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

【深度学习】LeNet卷积神经网络(MNIST 计算机视觉数据集)

程序员文章站 2024-03-14 11:41:34
...

MNIST 是一个入门级的计算机视觉数据集
相当于"Hello Word"

MNIST数据集链接:https://pan.baidu.com/s/1KfLFnmoXhDwTd9ZebNFz2Q
提取码:y1kn

LeNet神经网络介绍:

https://www.jianshu.com/p/cd73bc979ba9

效果

【深度学习】LeNet卷积神经网络(MNIST 计算机视觉数据集)

code:
import input_data
import tensorflow as tf
import matplotlib.pyplot as plt

mnist = input_data.read_data_sets("data/", one_hot = True)

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')

x = tf.placeholder("float", shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])

sess = tf.InteractiveSession()

# 28×28×1->12×12×6
# 第一层 卷积层 + 第二层 池化层
W_conv1 = weight_variable([5, 5, 1, 6])
b_conv1 = bias_variable([6])
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)

# 12×12×6->4×4×16
# 第三层 卷积层 + 第四层 池化层
W_conv2 = weight_variable([5, 5, 6, 16])
b_conv2 = bias_variable([16])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# 4×4×16->256, 256->120
# 第五层 全连接层
pool_shape=h_pool2.get_shape().as_list()
nodes = pool_shape[1]*pool_shape[2]*pool_shape[3]
h_pool2_flat = tf.reshape(h_pool2,[-1,nodes])

W_fc1 = weight_variable([nodes, 120])
b_fc1 = bias_variable([120])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# 120->84
# 第六层 全连接层
W_fc2 = weight_variable([120, 84])
b_fc2 = bias_variable([84])
h_fc2 = tf.nn.relu(tf.matmul(h_fc1, W_fc2) + b_fc2)

keep_prob = tf.placeholder("float")
h_fc2_drop = tf.nn.dropout(h_fc2, keep_prob)

#84->10
# 第七层 输出层
W_fc3 = weight_variable([84, 10])
b_fc3 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc2_drop, W_fc3) + b_fc3)

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())
ans=[]
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 %f"%(i, train_accuracy))
    ans.append(train_accuracy)
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

print ("test accuracy %f"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

plt.plot(ans, 'g--')
plt.show()

参考链接

https://www.w3cschool.cn/tensorflow_python/tensorflow_python-c1ov28so.html
https://www.jianshu.com/p/cd73bc979ba9