利用卷积神经网络对mnist数据集进行分类
MNIST进阶教程
利用卷积神经网络对mnist数据集进行分类_训练模型
利用卷积神经网络对mnist数据集进行分类_利用训练好的模型进行分类
ps: 仅供自己学习使用
模型训练
"""
@date 2020/02/18
@desc 利用卷积网络对mnist数据集进行分类--模型训练
"""
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("../alexnet/data/", one_hot=True)
# 每个批次大小
batch_size = 100
n_batch = mnist.train._num_examples // batch_size
# 权重和偏置项初始化
# 权重在初始化时应该加入少量的噪声来打破对称性以及避免0梯度。
# 使用的ReLU神经元，用一个较小的正数来初始化偏置项，以避免神经元节点输出恒为0的问题（dead neurons）。
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1) # 生成一个截断的正态分布
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
# 卷积和池化
# 卷积使用1步长（stride size），0边距（padding size）的模板，保证输出和输入是同一个大小。
# 池化用简单传统的2x2大小的模板做max pooling。
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')
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
# 改变x的格式转为4D的向量[batch,in_height,in_width,in_channels]
# 因为是灰度图，所以in_channels=1
x_image = tf.reshape(x, [-1, 28, 28, 1])
## 第一层卷积
W_conv1 = weight_variable([5, 5, 1, 32]) # 5*5的采样窗口， 1代表channel数，32个卷积核从一个平面抽取特征 32个卷积核是自定义的
b_conv1 = bias_variable([32]) # 每个卷积核一个偏置值
# 把x_image和权值向量进行卷积，加上偏置项，然后应用ReLU激活函数，最后进行max pooling。
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
## 第二层卷积
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)
# 28x28的图片第一次卷积后还是28x28 第一次池化后变为14x14
# 第二次卷积后 变为14x14 第二次池化后变为7x7
## 全连接层1
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# 第一个全连接层的输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
## 全连接层2
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
# 计算输出
predication = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
#交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=predication))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(predication, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(1000):
batch_x, batch_y = mnist.train.next_batch(batch_size)
sess.run(train_step, feed_dict={x: batch_x, y: batch_y, keep_prob: 0.7})
# 每训练100次， 打印输出loss和accuracy
if i % 50 == 0 or i == 999:
l, acc = sess.run([cross_entropy, accuracy], feed_dict={x: mnist.test.images, y: mnist.test.labels, keep_prob: 0.7})
print("Step " + str(i) + ", Minibatch Loss= " + "{:.4f}".format(l)
+ ", Training Accuracy= " + "{:.3f}".format(acc))
print("Optimization Finished!")
# calculate accuracy for mnist test images
test_accuracy = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels, keep_prob: 0.7})
print("test_accuracy: " + str(test_accuracy))
## saver.save(sess, save_path='/home/xxx/logs/mnistmodel', global_step=1) # 将训练出来的权重参数保存
分类预测
#coding:utf-8
import tensorflow as tf
from PIL import Image,ImageFilter
from tensorflow.examples.tutorials.mnist import input_data
def imageprepare(argv): # 该函数读一张图片，处理后返回一个数组，进到网络中预测
"""
This function returns the pixel values.
The imput is a png file location.
"""
im = Image.open(argv).convert('L')
width = float(im.size[0])
height = float(im.size[1])
newImage = Image.new('L', (28, 28), (255)) # creates white canvas of 28x28 pixels
if width > height: # check which dimension is bigger
# Width is bigger. Width becomes 20 pixels.
nheight = int(round((20.0 / width * height), 0)) # resize height according to ratio width
if nheight == 0: # rare case but minimum is 1 pixel
nheight = 1
# resize and sharpen
img = im.resize((20, nheight), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
wtop = int(round(((28 - nheight) / 2), 0)) # caculate horizontal pozition
newImage.paste(img, (4, wtop)) # paste resized image on white canvas
else:
# Height is bigger. Heigth becomes 20 pixels.
nwidth = int(round((20.0 / height * width), 0)) # resize width according to ratio height
if (nwidth == 0): # rare case but minimum is 1 pixel
nwidth = 1
# resize and sharpen
img = im.resize((nwidth, 20), Image.ANTIALIAS).filter(ImageFilter.SHARPEN)
wleft = int(round(((28 - nwidth) / 2), 0)) # caculate vertical pozition
newImage.paste(img, (wleft, 4)) # paste resized image on white canvas
# newImage.save("sample.png")
tv = list(newImage.getdata()) # get pixel values
# normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
tva = [(255 - x) * 1.0 / 255.0 for x in tv]
return tva
def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev=0.1) #生成一个截断的正态分布
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1,shape = shape)
return tf.Variable(initial)
#卷基层
def conv2d(x,W):
return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')
#池化层
def max_pool_2x2(x):
return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')
#定义两个placeholder
x = tf.placeholder(tf.float32, [None,784])
#y = tf.placeholder(tf.float32,[None,10])
#改变x的格式转为4D的向量[batch,in_height,in_width,in_channels]
x_image = tf.reshape(x, [-1,28,28,1])
#初始化第一个卷基层的权值和偏置
W_conv1 = weight_variable([5,5,1,32]) #5*5的采样窗口 32个卷积核从一个平面抽取特征 32个卷积核是自定义的
b_conv1 = bias_variable([32]) #每个卷积核一个偏置值
#把x_image和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1 = max_pool_2x2(h_conv1) #进行max-pooling
#初始化第二个卷基层的权值和偏置
W_conv2 = weight_variable([5,5,32,64]) # 5*5的采样窗口 64个卷积核从32个平面抽取特征 由于前一层操作得到了32个特征图
b_conv2 = bias_variable([64]) #每一个卷积核一个偏置值
#把h_pool1和权值向量进行卷积 再加上偏置值 然后应用于relu激活函数
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2) #进行max-pooling
#28x28的图片第一次卷积后还是28x28 第一次池化后变为14x14
#第二次卷积后 变为14x14 第二次池化后变为7x7
#通过上面操作后得到64张7x7的平面
#初始化第一个全连接层的权值
W_fc1 = weight_variable([7*7*64,1024])#上一层有7*7*64个神经元，全连接层有1024个神经元
b_fc1 = bias_variable([1024]) #1024个节点
#把第二个池化层的输出扁平化为一维
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
#求第一个全连接层的输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)
#keep_prob用来表示神经元的输出概率
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)
#初始化第二个全连接层
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
#计算输出
gailv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess,'/home/xxx/logs/mnistmodel-1')
array = imageprepare('/home/xxx/logs/7.jpg') # 读一张包含数字的图片
prediction = tf.argmax(gailv, 1) # 预测
prediction = prediction.eval(feed_dict={x:[array],keep_prob:1.0},session=sess)
print('The digits in this image is:%d' % prediction[0])
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
