TensorFlow实时识别手写数字（数字通过鼠标输入）

最新推荐文章于 2023-07-30 22:36:43 发布

佛缘Song

最新推荐文章于 2023-07-30 22:36:43 发布

阅读量1.7k

点赞数 5

文章标签： TensorFlow mnist 手写数字识别

本文链接：https://blog.csdn.net/Nichalos_Song/article/details/72228977

版权

在学习TensorFlow教程的的手写数字识别时，感觉受益匪浅，但是教程上的例子对于我这种刚入门的人来说不够直接，冲击力也不足。于是自己加上了用鼠标绘画数字，并用训练好的网络模型来识别的功能。下面给出程序与说明：

程序：

import numpy as np
import cv2
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

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

sess = tf.InteractiveSession()

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')

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

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.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
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, tf.float32))

tf.global_variables_initializer().run()

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})

print("test accuracy %g"%accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
## the above is the standard tutorial

## follow is edited myself
drawing = False
ix, iy = -1, -1

def draw_digit(event, x, y, flags, param):
    global ix, iy, drawing
    
    if event == cv2.EVENT_LBUTTONDOWN:
        drawing = True
        ix, iy = x, y
    elif event == cv2.EVENT_MOUSEMOVE:
        if drawing == True:
            cv2.circle(img, (x, y), 1, (255), -1)
    elif event == cv2.EVENT_LBUTTONUP:
        drawing = False

img = np.zeros((28,28), np.uint8)
cv2.namedWindow('Image')
cv2.setMouseCallback('Image', draw_digit)

while(1):
    img = np.zeros((28,28), np.uint8)
    while(1):
        cv2.imshow('Image', img)
        k = cv2.waitKey(1) & 0xFF
        if k == 10: #Enter key
            cv2.imwrite('1.png', img)
            break

    flatten = img.flatten()/255.0

    y_input = np.zeros((1,10))
    input_image = np.zeros((1,784))
    input_image[0] = flatten

    prediction = tf.argmax(y_conv, 1)
    print sess.run(prediction, feed_dict = {x:input_image, y_:y_input,keep_prob: 1.0})

    j = cv2.waitKey(1) & 0xFF
    if j == 17: #Enter key
        break

将程序保存为 xxx.py文件，在Linux终端运行python xxx.py，等待网络训练完毕之后，在桌面上回出现如下的窗口（该窗口很小）