MNIST数据集手写数字识别（一）

# 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=8)

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)#二维，和flatten一维有区别

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()

一键获取完整项目代码

python

————————————————

原文链接：https://blog.csdn.net/weixin_41896770/article/details/119576575

(x_train,t_train),(x_test,t_test)=load_mnist(flatten=True,normalize=False)

x_train.shape,t_train.shape,x_test.shape,t_test.shape

结果：((60000, 784), (60000,), (10000, 784), (10000,))

训练集图像是60000张，784(28*28)个像素/张，测试集图片是10000张，图片也是784(28*28)个像素/张

如果flatten为False，也就是不展开输入的图像（一维数组），那么图像就是1*28*28的三维数组

(x_train,t_train),(x_test,t_test)=load_mnist(flatten=False,normalize=False)

结果：((60000, 1, 28, 28), (60000,), (10000, 1, 28, 28), (10000,))

一键获取完整项目代码

python

————————————————

原文链接：https://blog.csdn.net/weixin_41896770/article/details/119576575

import sys,os

import numpy as np

from PIL import Image

os.chdir('D:\Anaconda3\TONYTEST')

sys.path.append('D:\Anaconda3\TONYTEST')

from dataset.mnist import load_mnist

def img_show(img):

pil_img=Image.fromarray(np.uint8(img))

pil_img.show()

(x_train,t_train),(x_test,t_test)=load_mnist(flatten=True,normalize=False)

img=x_train[4]#9

label=t_train[4]#9

print(label)

print(img.shape)#(784,)

img=img.reshape(28,28)

img_show(img)

将出现一个28*28像素的手写数字为9的图片

一键获取完整项目代码

————————————————

原文链接：https://blog.csdn.net/weixin_41896770/article/details/119576575

加载中~

分享到各大网站