手写数字识别的神经网络实践

作者: shaneZhang 分类: 机器学习的实践 发布时间: 2019-01-26 13:52

本示例代码为基于mnist数据集的手写数字识别的神经网络实践。示例用使用的手写数字板的识别图片可以参考https://code.5288z.com/zhangyuqing/AIPractice fc2目录下的pic文件夹下的相关图片。 整个内容包括4个文件,fc2_mnist_forward.py fc2_mnist_backward.py fc2_minist_test.py fc2_minist_app.py 其中前三个分别为该神经网络的执行和测试文件,在进行训练完毕后可以看到输出准确率可以达到98%以上,在重新运行fc2_mnist_app.py即可对响应的文件进行识别。下面分别是这四个文件的代码。

#coding=utf-8
#fc2_mnist_forward.py
#本文件是前向传播过程的代码

import  tensorflow as tf

INPUT_NODE= 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

def get_weight(shape,regularizer):
    w = tf.Variable(tf.truncated_normal(shape,stddev=0.1))
    if regularizer != None:
        tf.add_to_collection('losses',tf.contrib.layers.l2_regularizer(regularizer)(w))
    return w


def get_bias(shape):
    b = tf.Variable(tf.zeros(shape))
    return  b


def forward(x,regularizer):
    print regularizer
    w1 = get_weight([INPUT_NODE,LAYER1_NODE],regularizer)
    b1 = get_bias([LAYER1_NODE])
    y1 = tf.nn.relu(tf.matmul(x,w1) + b1)
    w2 = get_weight([LAYER1_NODE,OUTPUT_NODE],regularizer)
    b2 = get_bias([OUTPUT_NODE])
    y = tf.matmul(y1,w2) + b2
    return y
#coding=utf-8
#fc2_mnist_backward.py
#本文件是反向传播过程的代码

import  tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import fc2_mnist_forward
import  os

BATCH_SIZE = 200
LEANRING_RATE_BASE = 0.1
LEANRING_RATE_DECAY = 0.99
REGULAERIZER = 0.0001
STEPS = 50000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "./model/"
MODEL_NAME = "mnist_model"

def backward(mnist):
    x = tf.placeholder(tf.float32, [None, fc2_mnist_forward.INPUT_NODE])
    y_ = tf.placeholder(tf.float32, [None, fc2_mnist_forward.OUTPUT_NODE])
    y = fc2_mnist_forward.forward(x, REGULAERIZER)
    global_step = tf.Variable(0,trainable=False)

    ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y,labels=tf.argmax(y_,1))
    cem = tf.reduce_mean(ce)
    loss = cem + tf.add_n(tf.get_collection('losses'))

    learning_rate = tf.train.exponential_decay(
        LEANRING_RATE_BASE,
        global_step,
        mnist.train.num_examples / BATCH_SIZE,
        LEANRING_RATE_DECAY,
        staircase=True
    )

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss,global_step=global_step)

    ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY,global_step)
    ema_op = ema.apply(tf.trainable_variables())

    with tf.control_dependencies([train_step,ema_op]):
        train_op = tf.no_op(name = 'train')

    saver = tf.train.Saver()

    with tf.Session() as sess:
        init_op = tf.global_variables_initializer()
        sess.run(init_op)
        ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
        if ckpt and ckpt.model_checkpoint_path:
            saver.restore(sess,ckpt.model_checkpoint_path)

        for i in range(STEPS):
            xs,ys = mnist.train.next_batch(BATCH_SIZE)
            _,loss_value,step = sess.run([train_op,loss,global_step],feed_dict={x:xs,y_:ys})
            if i % 1000 == 0:
                print "After %d training steps, loss on training batch is %g." % (step,loss_value)
                saver.save(sess,os.path.join(MODEL_SAVE_PATH,MODEL_NAME),global_step=global_step)



def main():
    mnist = input_data.read_data_sets("../data/",one_hot=True)
    backward(mnist)


if __name__ == "__main__":
    main()
#coding=utf-8
#fc2_mnist_test.py
#本文件为训练模型的数据集训练文件

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import fc2_mnist_forward
import fc2_mnist_backward

TEST_INTERVAL_SECS = 5


def test(mnist):
    with tf.Graph().as_default() as g:
        x = tf.placeholder(tf.float32,[None,fc2_mnist_forward.INPUT_NODE])
        y_ = tf.placeholder(tf.float32,[None,fc2_mnist_forward.OUTPUT_NODE])
        y = fc2_mnist_forward.forward(x,None)

        ema = tf.train.ExponentialMovingAverage(fc2_mnist_backward.MOVING_AVERAGE_DECAY)
        ema_restore = ema.variables_to_restore()
        saver = tf.train.Saver(ema_restore)

        correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

        while True:
            with tf.Session() as sess:
                ckpt = tf.train.get_checkpoint_state(fc2_mnist_backward.MODEL_SAVE_PATH)
                if ckpt and ckpt.model_checkpoint_path:
                    saver.restore(sess,ckpt.model_checkpoint_path)
                    global_step = ckpt.model_checkpoint_path.split("/")[-1].split("-")[-1]
                    accuracy_score = sess.run(accuracy,feed_dict={x:mnist.test.images,y_:mnist.test.labels})
                    print "after %s training steps ,test accuracy = %g"%(global_step,accuracy_score)
                else:
                    print "NO checkpoint file found"
            time.sleep(TEST_INTERVAL_SECS)



def main():
    mnist = input_data.read_data_sets("../data/",one_hot=True)
    test(mnist)


if __name__ == "__main__":
    main()
#coding=utf8
#fc2_minist_app.py
#本文件为最终生成的数据应用程序模型,下图中所运行的示例演示结果文件。
import tensorflow as tf
import numpy as np
from PIL import  Image
import fc2_mnist_backward
import fc2_mnist_forward

def resotre_model(testPicArray):
    with tf.Graph().as_default() as tg:
        x = tf.placeholder(tf.float32,[None,fc2_mnist_forward.INPUT_NODE])
        y = fc2_mnist_forward.forward(x,None)
        preValue = tf.argmax(y,1)

        variable_averages = tf.train.ExponentialMovingAverage(fc2_mnist_backward.MOVING_AVERAGE_DECAY)
        variables_to_resotore = variable_averages.variables_to_restore()
        saver = tf.train.Saver(variables_to_resotore)

        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(fc2_mnist_backward.MODEL_SAVE_PATH)
            if ckpt and ckpt.model_checkpoint_path:
                saver.restore(sess,ckpt.model_checkpoint_path)
                preValue = sess.run(preValue,feed_dict={x:testPicArray})
                return preValue
            else:
                print "No checkpoint file found"
                return -1

def pre_pic(picName):
    img = Image.open(picName)
    reIm = img.resize((28,28),Image.ANTIALIAS)
    im_arr = np.array(reIm.convert('L'))
    thredshold = 50
    for i in range(28):
        for j in range(28):
            im_arr[i][j] = 255 - im_arr[i][j]
            if im_arr[i][j] < thredshold:
                im_arr[i][j] = 0
            else:
                im_arr[i][j] = 255
    nm_arr = im_arr.reshape([1,784])
    nm_arr = nm_arr.astype(np.float32)
    img_ready = np.multiply(nm_arr,1.0/255.0)

    return img_ready




def application():
    testNum = input("input the number of test pictures:")
    for i in range(testNum):
        testPicPath = raw_input("the path of test picture:")
        testPicArr = pre_pic(testPicPath)
        preValue = resotre_model(testPicArr)
        print "the prediction number is:",preValue


def main():
    application()


if __name__ == '__main__':
    main()

本页面支持繁体中文友好显示:手写数字识别的神经网络实践

如果觉得我的文章对您有用,请随意打赏。如果有其他问题请联系博主QQ(909491009)或者下方留言!

发表回复