【深度学习】LeNet卷积神经网络(MNIST 计算机视觉数据集)

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

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