介紹
在TensorFlow的官方入門課程中叮趴，多次用到mnist數(shù)據(jù)集。mnist數(shù)據(jù)集是一個(gè)數(shù)字手寫體圖片庫权烧，但它的存儲(chǔ)格式并非常見的圖片格式眯亦，所有的圖片都集中保存在四個(gè)擴(kuò)展名為idx*-ubyte.gz的二進(jìn)制文件。
數(shù)據(jù)集
可以直接從官網(wǎng)進(jìn)行下載
http://yann.lecun.com/exdb/mnist/
數(shù)據(jù)集
如果我們想要知道大名鼎鼎的mnist手寫體數(shù)字都長什么樣子般码，就需要從mnist數(shù)據(jù)集中導(dǎo)出手寫體數(shù)字圖片妻率。了解這些手寫體的總體形狀，也有助于加深我們對TensorFlow入門課程的理解板祝。
訓(xùn)練數(shù)據(jù)集
當(dāng)我們下載了數(shù)據(jù)集后宫静，需要對數(shù)據(jù)集進(jìn)行訓(xùn)練。并保存訓(xùn)練的模型
#!/usr/bin/python3.5
# -*- coding: utf-8 -*-
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
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')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
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)
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)
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)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
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"))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
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 %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
saver.save(sess, 'WModel/model.ckpt')
print('test accuracy %g' % accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
對應(yīng)的模型文件如圖所示
模型
用畫圖手寫數(shù)字
通過電腦自帶畫圖工具券时，手寫一個(gè)數(shù)字孤里，像素為28，如圖所示
在這里插入圖片描述
識(shí)別手寫數(shù)字
把上面生成的圖片保存為bmp或png
然后通過程序調(diào)用橘洞，在使用之前需要先加載前面保存的模型
#!/usr/bin/python3.5
# -*- coding: utf-8 -*-
from PIL import Image, ImageFilter
import tensorflow as tf
import matplotlib.pyplot as plt
import time
def imageprepare():
"""
This function returns the pixel values.
The imput is a png file location.
"""
file_name='result/4.bmp'#導(dǎo)入自己的圖片地址
#in terminal 'mogrify -format png *.jpg' convert jpg to png
im = Image.open(file_name)
# plt.imshow(im)
# plt.show()
im = im.convert('L')
im.save("sample.png")
tv = list(im.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]
#print(tva)
return tva
"""
This function returns the predicted integer.
The imput is the pixel values from the imageprepare() function.
"""
# Define the model (same as when creating the model file)
result=imageprepare()
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
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')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
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)
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)
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)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
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"))
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, "./WModel/model.ckpt")#這里使用了之前保存的模型參數(shù)
print ("Model restored.")
prediction=tf.argmax(y_conv,1)
predint=prediction.eval(feed_dict={x: [result],keep_prob: 1.0}, session=sess)
print(h_conv2)
print('識(shí)別結(jié)果:')
print(predint[0])
識(shí)別結(jié)果如圖所示:
運(yùn)行結(jié)果
