tensorflow利用标准mnist训练的模型测试自己写的单张数字图片（5）

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