数据链接:https://pan.baidu.com/s/1ICxdODACssxtbf3hs_PT3w 密码:rsx3
# 加载MNIST数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
# 查看数据集图片
import matplotlib.pyplot as plt
n = mnist.train.images[2].reshape(28, 28)
plt.imshow(n, cmap='gray')
import tensorflow as tf
sess = tf.InteractiveSession()
1、Softmax 回归模型
x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
sess.run(tf.global_variables_initializer())
y = tf.matmul(x, W) + b
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(labels=y_, logits=y))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
for _ in range(1000):
batch = mnist.train.next_batch(100)
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
2、 TensorFlow实现简单的CNN
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
sess = tf.InteractiveSession()
# 1、 创建权重和偏置的初始化函数以便重复使用
def weight_variable(shape):
# 制造随机噪声用以打破完全对称,如 截断的正态分布噪声,标准差为0.1
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
# 为偏置增加一些小的正值0.1,避免dead neurons
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial
# 2、定义卷积层和池化层
def conv2d(x, W):
# tf.nn.conv2d
# x: 输入
# W: 卷积参数,如 [5, 5, 1, 32]表示卷积核的大小为5x5,通道个数为1,卷积核个数为32
# strides: 移动的步长
# padding: 边界处理方式
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
# tf.nn.max_pool
# x: 输入的tensor [batch, height, width, channels]
# ksize: 核的大小,[1, 2, 2, 1]表示在1个样本上,2x2大小的核,1个通道
# strides:与ksize类似
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
# 3、定义placeholder,x为特征,y_为真实的标签
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1]) # reshape为28x28的图像,1个通道,-1表示样本数量不固定
# 4、定义第一个卷积层
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)
# 5、定义第二个卷积层
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)
# 6、经过两次步长为2x2的池化,大小为原始图像的1/4,即7x7定义最后的全连接层
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)
# 8、为避免过拟合,使用一个Dropout层,训练时随机丢弃一部分节点的数据来减轻过拟合
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# 9、将Dropout层连接最终的Softmax层,得到最终的概率输出
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# 10、定义损失函数和优化算法
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# 11、定义准确率的计算
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 12、开始训练过程
tf.global_variables_initializer().run()
# for i in range(20000):
for i in range(1000):
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 %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
# 13、训练完后,在测试集上进行测试
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))