python MNIST手写识别数据调用API的方法
作者:caichao08 时间:2021-05-13 19:20:45
MNIST数据集比较小,一般入门机器学习都会采用这个数据集来训练
下载地址:yann.lecun.com/exdb/mnist/
有4个有用的文件:
train-images-idx3-ubyte: training set images
train-labels-idx1-ubyte: training set labels
t10k-images-idx3-ubyte: test set images
t10k-labels-idx1-ubyte: test set labels
The training set contains 60000 examples, and the test set 10000 examples. 数据集存储是用binary file存储的,黑白图片。
下面给出load数据集的代码:
import os
import struct
import numpy as np
import matplotlib.pyplot as plt
def load_mnist():
'''
Load mnist data
http://yann.lecun.com/exdb/mnist/
60000 training examples
10000 test sets
Arguments:
kind: 'train' or 'test', string charater input with a default value 'train'
Return:
xxx_images: n*m array, n is the sample count, m is the feature number which is 28*28
xxx_labels: class labels for each image, (0-9)
'''
root_path = '/home/cc/deep_learning/data_sets/mnist'
train_labels_path = os.path.join(root_path, 'train-labels.idx1-ubyte')
train_images_path = os.path.join(root_path, 'train-images.idx3-ubyte')
test_labels_path = os.path.join(root_path, 't10k-labels.idx1-ubyte')
test_images_path = os.path.join(root_path, 't10k-images.idx3-ubyte')
with open(train_labels_path, 'rb') as lpath:
# '>' denotes bigedian
# 'I' denotes unsigned char
magic, n = struct.unpack('>II', lpath.read(8))
#loaded = np.fromfile(lpath, dtype = np.uint8)
train_labels = np.fromfile(lpath, dtype = np.uint8).astype(np.float)
with open(train_images_path, 'rb') as ipath:
magic, num, rows, cols = struct.unpack('>IIII', ipath.read(16))
loaded = np.fromfile(train_images_path, dtype = np.uint8)
# images start from the 16th bytes
train_images = loaded[16:].reshape(len(train_labels), 784).astype(np.float)
with open(test_labels_path, 'rb') as lpath:
# '>' denotes bigedian
# 'I' denotes unsigned char
magic, n = struct.unpack('>II', lpath.read(8))
#loaded = np.fromfile(lpath, dtype = np.uint8)
test_labels = np.fromfile(lpath, dtype = np.uint8).astype(np.float)
with open(test_images_path, 'rb') as ipath:
magic, num, rows, cols = struct.unpack('>IIII', ipath.read(16))
loaded = np.fromfile(test_images_path, dtype = np.uint8)
# images start from the 16th bytes
test_images = loaded[16:].reshape(len(test_labels), 784)
return train_images, train_labels, test_images, test_labels
再看看图片集是什么样的:
def test_mnist_data():
'''
Just to check the data
Argument:
none
Return:
none
'''
train_images, train_labels, test_images, test_labels = load_mnist()
fig, ax = plt.subplots(nrows = 2, ncols = 5, sharex = True, sharey = True)
ax =ax.flatten()
for i in range(10):
img = train_images[i][:].reshape(28, 28)
ax[i].imshow(img, cmap = 'Greys', interpolation = 'nearest')
print('corresponding labels = %d' %train_labels[i])
if __name__ == '__main__':
test_mnist_data()
跑出的结果如下:
来源:https://blog.csdn.net/caichao08/article/details/78988389
标签:python,MNIST,手写识别
![](/images/zang.png)
![](/images/jiucuo.png)
猜你喜欢
python日志记录模块实例及改进
2021-03-14 12:49:09
不要跳转或刷新 实现网页区域选择显示
2010-07-02 16:25:00
PHP中让json_encode不自动转义斜杠“/”的方法
2023-07-12 22:44:58
精美漂亮的php分页类代码
2023-11-22 08:28:09
VBScript WeekdayName 函数语法
2008-01-25 19:25:00
Python根据当前日期取去年同星期日期
2021-09-14 15:01:48
浅谈js数组和splice的用法
2023-08-23 00:19:42
SQL Server中如何优化磁带备份设备性能
2009-01-07 14:23:00
使用Python的SymPy库解决数学运算问题的方法
2021-04-19 19:36:35
Django实现文件上传下载功能
2023-06-13 20:09:46
![](https://img.aspxhome.com/file/2023/9/85009_0s.gif)
python实现简单俄罗斯方块游戏
2023-04-13 03:28:05
![](https://img.aspxhome.com/file/2023/4/85044_0s.jpg)
python MultipartEncoder传输zip文件实例
2022-04-20 07:22:57
python 列表递归求和、计数、求最大元素的实例
2023-01-07 13:28:07
asp检测文件编码方法
2007-10-03 14:27:00
SQL SERVER 2005中的同步复制技术
2009-01-05 13:44:00
简单了解python 邮件模块的使用方法
2021-07-11 00:08:14
php浅析反序列化结构
2023-11-17 17:34:37
运行SQL Server的计算机间移动数据库
2009-01-20 13:07:00
Python Opencv使用ann神经网络识别手写数字功能
2023-11-03 02:44:52
![](https://img.aspxhome.com/file/2023/8/63268_0s.png)
ASP 3.0中的新特性
2008-02-27 13:28:00
![](https://img.aspxhome.com/file/UploadPic/20082/27/2008227134234597s.jpg)