记得在当前工程中新建一个MNIST_data文件夹和model文件夹
终端cd到当前工程路径
train.py代码
import tensorflow as tf #导入数据 from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True) #去除加速sse的warning import os os.environ['TF_CPP_MIN_LOG_LEVEL']='2' #x为训练图像,y_为训练图像标签 x = tf.placeholder(tf.float32, shape=[None, 784]) y_ = tf.placeholder(tf.float32, shape=[None, 10]) #权重偏置初始化 W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) #权重在初始化时应该加入少量的噪声来打破对称性以及避免0梯度,避免神经元节点输出恒为0的问题(dead neurons) 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') #第一层卷积层,32个卷积核去分别关注32个特征 W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) x_image = tf.reshape(x, [-1,28,28,1])#将单张图片从784维向量重新还原为28x28的矩阵图片,-1表示取出所有的数据 h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) #第二层卷积层 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) #全连接层 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) #使用Dropout,训练时为0.5,测试时为1,keep_prob表示保留不关闭的神经元的比例 keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #把1024维的向量转换成10维,对应10个类别 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2 #交叉熵 cross_entropy = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)) #定义train_step train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) #定义测试准确率 correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) #存储训练的模型 saver = tf.train.Saver() #创建Session和变量初始化 sess = tf.InteractiveSession() sess.run(tf.global_variables_initializer()) #标准训练是20000步,这里为节约时间训练1000步 for i in range(1000): batch = mnist.train.next_batch(50) if i%100 == 0:#每100步输出一次在验证集上的准确度 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, '/home/xy/highschool_myOwn614/model/model.ckpt') #模型存储的文件夹 #输出在测试集上的准确度 print("test accuracy %g"%accuracy.eval(feed_dict={ x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
训练结果
test_number文件夹中的内容为
test.py文件
from PIL import Image, ImageFilter import tensorflow as tf import cv2 #去除加速sse的warning import os os.environ['TF_CPP_MIN_LOG_LEVEL']='2' #语音播报预测结果 import pyttsx3 def imageprepare(): #导入自己的图片地址 file_name='/home/xy/highschool_myOwn614/test_number/1_1.png' #in terminal 'mogrify -format png *.jpg' convert jpg to png im = Image.open(file_name).convert('L') tv = list(im.getdata()) #get pixel values #normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.我们写的是白底黑字,标准训练的是黑底白字,需要转换 tva = [ (255-x)*1.0/255.0 for x in tv] return tva result=imageprepare() #详细解释见train.py x = tf.placeholder(tf.float32, [None, 784]) W = tf.Variable(tf.zeros([784, 10])) b = tf.Variable(tf.zeros([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.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) init_op = tf.global_variables_initializer() saver = tf.train.Saver() with tf.Session() as sess: sess.run(init_op) #使用之前保存的模型参数 saver.restore(sess, "/home/xy/highschool_myOwn614/model/model.ckpt") prediction=tf.argmax(y_conv,1) predint=prediction.eval(feed_dict={x: [result],keep_prob: 1.0}, session=sess) #将预测结果写在predictNumber.txt文件里 fi_xu=open('/home/xy/highschool_myOwn614/predictNumber.txt','w') fi_xu.write(str(predint[0])) fi_xu.close() print('recognize result:') print(predint[0]) #语音播报 engine = pyttsx3.init() engine.say("hello,you predict number is"+str(predint[0])) engine.runAndWait()
结果