使用卷积神经网络对mnist数据集进行分析
使用卷积神经网络对mnist数据集进行分析
使用tensorflow对mnist数据集进行建模
#1、导入需要用到的包
import tensorflow as tf
import random
import numpy as np
import matplotlib.pyplot as plt
import datetime
from tensorflow.examples.tutorials.mnist import input_data
#2、导入mnist数据集
mnist = input_data.read_data_sets("data/", one_hot=True)
#3、定义x和y，即输入x和标签y
tf.reset_default_graph()
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape = [None, 28,28,1]) #输入是28x28、通道是1的图片
y_ = tf.placeholder("float", shape = [None, 10]) #输出是一个10维的向量，表示10个分类
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1)) #第一层的卷积，大小是5x5，数量是32个
b_conv1 = tf.Variable(tf.constant(.1, shape = [32])) #第一层的偏置，大小是32
#4、建立第一层卷积层
h_conv1 = tf.nn.conv2d(input=x, filter=W_conv1, strides=[1, 1, 1, 1], padding='SAME') + b_conv1 #第一层卷积层的建立
h_conv1 = tf.nn.relu(h_conv1) #第一层卷积层的激活函数
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') #第一层卷积层上的池化
def conv2d(x, W):
return tf.nn.conv2d(input=x, filter=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')
#5、建立第二层卷积层
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(.1, shape = [64]))
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#6、第一个全连接层
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(.1, shape = [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)
#7、Dropout层
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#8、第二个全连接层
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(.1, shape = [10]))
#9、全连接层
y = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
#10、
【完整代码】
#1、导入需要用到的包
import tensorflow as tf
import random
import numpy as np
import matplotlib.pyplot as plt
import datetime
from tensorflow.examples.tutorials.mnist import input_data
#2、导入mnist数据集
mnist = input_data.read_data_sets("data/", one_hot=True)
#3、定义x和y，即输入x和标签y
tf.reset_default_graph()
sess = tf.InteractiveSession()
x = tf.placeholder("float", shape = [None, 28,28,1]) #输入是28x28、通道是1的图片
y_ = tf.placeholder("float", shape = [None, 10]) #输出是一个10维的向量，表示10个分类
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 1, 32], stddev=0.1)) #第一层的卷积，大小是5x5，数量是32个
b_conv1 = tf.Variable(tf.constant(.1, shape = [32])) #第一层的偏置，大小是32
#4、建立第一层卷积层
h_conv1 = tf.nn.conv2d(input=x, filter=W_conv1, strides=[1, 1, 1, 1], padding='SAME') + b_conv1 #第一层卷积层的建立
h_conv1 = tf.nn.relu(h_conv1) #第一层卷积层的激活函数
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') #第一层卷积层上的池化
def conv2d(x, W):
return tf.nn.conv2d(input=x, filter=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')
#5、建立第二层卷积层
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 64], stddev=0.1))
b_conv2 = tf.Variable(tf.constant(.1, shape = [64]))
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#6、第一个全连接层
W_fc1 = tf.Variable(tf.truncated_normal([7 * 7 * 64, 1024], stddev=0.1))
b_fc1 = tf.Variable(tf.constant(.1, shape = [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)
#7、Dropout层
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#8、第二个全连接层
W_fc2 = tf.Variable(tf.truncated_normal([1024, 10], stddev=0.1))
b_fc2 = tf.Variable(tf.constant(.1, shape = [10]))
#9、全连接层
y = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
crossEntropyLoss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_, logits = y))
trainStep = tf.train.AdamOptimizer().minimize(crossEntropyLoss)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.global_variables_initializer())
batchSize = 50
for i in range(1000):
batch = mnist.train.next_batch(batchSize)
trainingInputs = batch[0].reshape([batchSize,28,28,1])
trainingLabels = batch[1]
if i%100 == 0:
trainAccuracy = accuracy.eval(session=sess, feed_dict={x:trainingInputs, y_: trainingLabels, keep_prob: 1.0})
print ("step %d, training accuracy %g"%(i, trainAccuracy))
trainStep.run(session=sess, feed_dict={x: trainingInputs, y_: trainingLabels, keep_prob: 0.5})
作者：洪士
