利用MNIST的数据集图片进行手写体的识别

利用MNIST数据集的图片进行手写体的识别

1，把MNIST数据集里面的图片下载到一个文件夹

# -*-coding:utf-8-*-
from tensorflow.examples.tutorials.mnist import input_data
import scipy.misc
import os

#读取MNIST数据集 。如果不存在就事先下载
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

#把原始图像保存在MNIST_data/raw/文件夹下
#如果没有这个文件夹，会自动创建
save_dir = 'MNIST_data/raw/'
if os.path.exists(save_dir) is False:
    os.makedirs(save_dir)

#保存前20张照片
for i in range(20):
    #请注意,mnist.train.images[i, ;]
    image_array = mnist.train.images[i, :]
    # Tensoflow 中的MNIST图片是一个784维的向量，我们重新把它还原为28X28维的图像
    image_array = image_array.reshape(28, 28)
    #保存文件的格式：
    filename = save_dir + 'mnist_train_%d.jpg' % i
    #先用scipy.misc.toimage转换为图像,再调用save直接保存
    scipy.misc.toimage(image_array, cmin=0.0, cmax=1.0).save(filename)

2，利用两层卷积神经网络进行训练生成训练模型

# -*-coding:utf-8-*-

from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
from skimage import io

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
img = io.imread('/media/kuka/文档/MNIST-rawimages/mnist_train_12.jpg')
np_img = np.reshape(img, (1, 784))
plt.imshow(img, 'gray')
plt.show()

x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])


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])
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(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

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)

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuray = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver = tf.train.Saver()  # 定义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 = accuray.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, '/media/kuka/文档/MNIST-Model/model.ckpt')  # 模型储存位置
    print("test accuracy %g" % accuray.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

3，利用生成的模型进行手写体的识别

# -*-coding:utf-8-*-

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from PIL import Image
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)


def imageprepare():
    #进行识别的图片
    im = Image.open('/media/kuka/文档/MNIST-rawimages/mnist_train_1.jpg') 
    plt.imshow(im)
    plt.show()
    #把图像转换成784维的向量
    tv = list(im.getdata())
    # print(tv)
    return tv


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(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

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)

correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuray = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver = tf.train.Saver()  # 定义saver
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    saver.restore(sess, "/media/kuka/文档/MNIST-Model/model.ckpt")  # 使用模型，参数和之前的代码保持一致
    prediction = tf.argmax(y_conv, 1)
    predint = prediction.eval(feed_dict={x: [result], keep_prob: 1.0}, session=sess)

one_hot_label = mnist.train.labels[1, :]  #识别图片的标签
label = np.argmax(one_hot_label)
if label == predint[0]:
    print('best match !')
else:
    print('error !')
print('图片原始标签： %d' % label)
print('识别结果: %d' % predint[0])

运行结果如下