介紹

在TensorFlow的官方入門課程中，多次用到mnist數(shù)據(jù)集。mnist數(shù)據(jù)集是一個數(shù)字手寫體圖片庫，但它的存儲格式并非常見的圖片格式，所有的圖片都集中保存在四個擴展名為idx*-ubyte.gz的二進制文件。

數(shù)據(jù)集

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，就需要從mnist數(shù)據(jù)集中導(dǎo)出手寫體數(shù)字圖片。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。

訓(xùn)練數(shù)據(jù)集

當(dāng)我們下載了數(shù)據(jù)集后，需要對數(shù)據(jù)集進行訓(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，手寫一個數(shù)字，像素為28，如圖所示

在這里插入圖片描述

識別手寫數(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，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('識別結(jié)果:')
    print(predint[0])

識別結(jié)果如圖所示:

運行結(jié)果