只用numpy读取MNIST（不用到struct）

MNIST

MNIST是一个包含60000个训练样本和10000个测试样本的手写数字数据集，每个灰度图为28*28，MNIST中包含4个文件：

train-images-idx3-ubyte
train-labels-idx1-ubyte
t10k-images-idx3-ubyte
t10k-labels-idx1-ubyte

IDX3文件格式

IDX1文件格式

代码

import numpy as np

def read_idx3(filename):
    with open(filename, 'rb') as fo:
        buf = fo.read()
        
        index = 0
        header = np.frombuffer(buf, '>i', 4, index)
        
        index += header.size * header.itemsize
        data = np.frombuffer(buf, '>B', header[1] * header[2] * header[3], index).reshape(header[1], -1)
        
        return data
    
def read_idx1(filename):
    with open(filename, 'rb') as fo:
        buf = fo.read()
        
        index = 0
        header = np.frombuffer(buf, '>i', 2, index)
        
        index += header.size * header.itemsize
        data = np.frombuffer(buf, '>B', header[1], index)
        
        return data

结果