利用mnist数据集进行的数字识别和数字图片存储操作

主体内容就是题目所示的那样，利用mnist数据集进行的数字识别和数字图片存储操作

下面附上代码：

1.mnist，py文件(书里面用到，但没有找到的文件）

# coding: utf-8
try:
    import urllib.request
except ImportError:
    raise ImportError('You should use Python 3.x')
import os.path
import gzip
import pickle
import os
import numpy as np


url_base = 'http://yann.lecun.com/exdb/mnist/'
key_file = {
    'train_img':'train-images-idx3-ubyte.gz',
    'train_label':'train-labels-idx1-ubyte.gz',
    'test_img':'t10k-images-idx3-ubyte.gz',
    'test_label':'t10k-labels-idx1-ubyte.gz'
}

dataset_dir = os.path.dirname(os.path.abspath(__file__))
save_file = dataset_dir + "/mnist.pkl"

train_num = 60000
test_num = 10000
img_dim = (1, 28, 28)
img_size = 784


def _download(file_name):
    file_path = dataset_dir + "/" + file_name
    
    if os.path.exists(file_path):
        return

    print("Downloading " + file_name + " ... ")
    urllib.request.urlretrieve(url_base + file_name, file_path)
    print("Done")
    
def download_mnist():
    for v in key_file.values():
       _download(v)
        
def _load_label(file_name):
    file_path = dataset_dir + "/" + file_name
    
    print("Converting " + file_name + " to NumPy Array ...")
    with gzip.open(file_path, 'rb') as f:
            labels = np.frombuffer(f.read(), np.uint8, offset=24)
    print("Done")
    
    return labels

def _load_img(file_name):
    file_path = dataset_dir + "/" + file_name
    
    print("Converting " + file_name + " to NumPy Array ...")    
    with gzip.open(file_path, 'rb') as f:
            data = np.frombuffer(f.read(), np.uint8, offset=16)
    data = data.reshape(-1, img_size)
    print("Done")
    
    return data
    
def _convert_numpy():
    dataset = {}
    dataset['train_img'] =  _load_img(key_file['train_img'])
    dataset['train_label'] = _load_label(key_file['train_label'])    
    dataset['test_img'] = _load_img(key_file['test_img'])
    dataset['test_label'] = _load_label(key_file['test_label'])
    
    return dataset

def init_mnist():
    download_mnist()
    dataset = _convert_numpy()
    print("Creating pickle file ...")
    with open(save_file, 'wb') as f:
        pickle.dump(dataset, f, -1)
    print("Done!")

def _change_one_hot_label(X):
    T = np.zeros((X.size, 10))
    for idx, row in enumerate(T):
        row[X[idx]] = 1
        
    return T
    

def load_mnist(normalize=True, flatten=True, one_hot_label=False):
    """读入MNIST数据集
    
    Parameters
    ----------
    normalize : 将图像的像素值正规化为0.0~1.0
    one_hot_label : 
        one_hot_label为True的情况下，标签作为one-hot数组返回
        one-hot数组是指[0,0,1,0,0,0,0,0,0,0]这样的数组
    flatten : 是否将图像展开为一维数组
    
    Returns
    -------
    (训练图像, 训练标签), (测试图像, 测试标签)
    """
    if not os.path.exists(save_file):
        init_mnist()
        
    with open(save_file, 'rb') as f:
        dataset = pickle.load(f)
    
    if normalize:
        for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].astype(np.float32)
            dataset[key] /= 255.0
            
    if one_hot_label:
        dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
        dataset['test_label'] = _change_one_hot_label(dataset['test_label'])
    
    if not flatten:
         for key in ('train_img', 'test_img'):
            dataset[key] = dataset[key].reshape(-1, 1, 28, 28)

    return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label']) 


if __name__ == '__main__':
    init_mnist()

2.mnist_show.py文件(同样是书上代码，但自己进行修改，目前可以输出十个识别出来的数字，同时将数字图片保存在test文件夹中)

# coding: utf-8
import sys, os
import cv2
sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import numpy as np
from dataest.mnist import load_mnist
from PIL import Image
import struct
import shutil


def img_show(img):
    pil_img = Image.fromarray(np.uint8(img))
    pil_img.show()

def setDir():
    if  not os.path.exists('./test'):
        os.makedirs('./test')
    else:
        shutil.rmtree('./test')
        os.mkdir('./test')



(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True, normalize=False)
setDir()
for i in range(0,10):
	img = x_train[i]
	label = t_train[i]
	img = img.reshape(28, 28)
	#Image.save('mnistpicture/'+img+'.png')
	
	fileName="./test/"+str(i)+"-"+str(t_train[i])+".bmp"
	cv2.imwrite(fileName, img)
	print(label)  # 5
	#img.show()

print(img.shape)  # (784,)
img = img.reshape(28, 28)  # 把图像的形状变为原来的尺寸
print(img.shape)  # (28, 28)

#img_show(img)

这个里面需要配置相应的环境，就请读者朋友们自己去配吧。毕竟我不熟悉你们的环境。

我的代码是MAC版本的，windows的需要修改一下文件格式。

利用mnist数据集进行的数字识别和数字图片存储操作

猜你喜欢