mnist_loader.py

最新推荐文章于 2025-03-12 21:49:27 发布

唯相遇

最新推荐文章于 2025-03-12 21:49:27 发布

阅读量4k

点赞数 1

分类专栏： Python3.5手写字体识别文章标签：基于Python3.5的手写字体识别

Python3.5手写字体识别专栏收录该内容

3 篇文章

订阅专栏

这是一个用于加载 MNIST 图像数据的库，详细介绍了数据结构及其返回的数据格式。通常调用 `load_data_wrapper` 函数来获取经过预处理的训练、验证及测试数据。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

"""
mnist_loader
~~~~~~~~~~~~

A library to load the MNIST image data.  For details of the data
structures that are returned, see the doc strings for ``load_data``
and ``load_data_wrapper``.  In practice, ``load_data_wrapper`` is the
function usually called by our neural network code.
"""

#### Libraries
# Standard library
import pickle
import gzip

import numpy as np
def load_data():
    f = gzip.open('mnist.pkl.gz', 'rb')
    training_data, validation_data, test_data = pickle.load(f,encoding = 'bytes')
    f.close()
    return (training_data, validation_data, test_data)

def load_data_wrapper():
    tr_d, va_d, te_d = load_data()
    training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
    training_results = [vectorized_result(y) for y in tr_d[1]]
    training_data = zip(training_inputs, training_results)
    validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
    validation_data = zip(validation_inputs, va_d[1])
    test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
    test_data = zip(test_inputs, te_d[1])
    return (training_data, validation_data, test_data)

def vectorized_result(j):
    e = np.zeros((10, 1))
    e[j] = 1.0
    return e