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)
用鼠标在窗口内画数字,示例如下:
等等(每次输入一个数字)
这时按下Enter键,在终端就会出现网络预测之后的数字,只要画的不是太不像,准确度还是很高的。
如果已经按过了Enter键,再按下Esc键就会退出程序。
程序说明:
1、网络训练与教程一模一样
2、鼠标画数字是调用opencv的库实现的,这里将窗口大小定义为28 * 28,绘画的图定义为单通道的灰度图,来适应MNISIT的数据格式。
3、关于程序中的一些解释:
1) 当网络训练时,是run Ada这个优化的来执行训练的,此优化器在训练过程中会优化权重W和偏置b的值,loss决定什么时候停止训练
2) 当识别自己用鼠标画出的数字时,是run prediction这个节点,因为TensorFlow会自动的推算prediction这个节点运行的依赖节点,这些依赖节点明显不包括优化器。所以在识别过程中用得到的W和b是训练完毕之后的值,所以可以正确识别。
3) prediction中的y_input的值是可以随便取值的,只要其类型是[None, 10]即可,因为要给节点中的 y_conv feed值,否则执行时会报错
注:此程序未来改进地方
1、 扩大窗口的大小,在程序中使用图片压缩功能,将大图片压缩到28 * 28
2、 增加保存训练好的网络模型功能,这样就可以减少训练网络需要的时间了