Dataset之Fashion-MNIST：Fashion-MNIST数据集简介、下载、使用方法之详细攻略

Fashion-MNIST数据集简介

https://imgconvert.csdnimg.cn/aHR0cHM6Ly9pbWcyMDE4LmNuYmxvZ3MuY29tL2Jsb2cvMTMxMzQ3NS8yMDE5MDcvMTMxMzQ3NS0yMDE5MDczMDE3MjYyNzExNy0xMzUyNTM3OTc1LmdpZg

、

     Fashion-MNIST数据集是德国Zalando公司提供的衣物图像数据集，包含60,000个样本的训练 集和10,000个样本的测试集。每个样本都是 28x28灰度图像，与10个类别的标签相关联。Fashion-MNIST数据集旨在作为原始MNIST数据集的直接替代品，用于对机器学习算法进行基准测试。

Name Content Examples Size Link MD5 Checksum

train-images-idx3-ubyte.gz training set images 60,000 26 MBytes Download 8d4fb7e6c68d591d4c3dfef9ec88bf0d

train-labels-idx1-ubyte.gz training set labels 60,000 29 KBytes Download 25c81989df183df01b3e8a0aad5dffbe

t10k-images-idx3-ubyte.gz test set images 10,000 4.3 MBytes Download bef4ecab320f06d8554ea6380940ec79

t10k-labels-idx1-ubyte.gz test set labels 10,000 5.1 KBytes Download bb300cfdad3c16e7a12a480ee83cd310

论文：https://arxiv.org/pdf/1708.07747.pdf

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

GitHub：https://github.com/zalandoresearch/fashion-mnist

其他介绍：http://www.worldlink.com.cn/zh_tw/osdir/fashion-mnist.html

     论文介绍了Fashion-MNIST，一种时尚产品图像数据集，旨在代替mnist，同时为基准机器学习算法提供一种更具挑战性的替代方法。Fashion-MNIST中的图像被转换为与mnist数据集相匹配的格式，使其立即与任何能够与原始mnist数据集一起工作的机器学习包兼容。

1、Why we made Fashion-MNIST

   The original MNIST dataset contains a lot of handwritten digits. Members of the AI/ML/Data Science community love this dataset and use it as a benchmark to validate their algorithms. In fact, MNIST is often the first dataset researchers try. "If it doesn't work on MNIST, it won't work at all", they said. "Well, if it does work on MNIST, it may still fail on others."

Fashion-MNIST数据集下载

0、数据集及代码下载

git clone git@github.com:zalandoresearch/fashion-mnist.git

1、基于python语言下载

'Use utils/mnist_reader in this repo'

import mnist_reader

X_train, y_train = mnist_reader.load_mnist('data/fashion', kind='train')

X_test, y_test = mnist_reader.load_mnist('data/fashion', kind='t10k')

2、基于Tensorflow下载

from tensorflow.examples.tutorials.mnist import input_data

data = input_data.read_data_sets('data/fashion')

data.train.next_batch(BATCH_SIZE)

ata = input_data.read_data_sets('data/fashion', source_url='http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/')

Fashion-MNIST数据集使用方法

TF之GD：基于tensorflow框架搭建GD算法利用Fashion-MNIST数据集实现多分类预测(92%)

https://blog.csdn.net/qq_41185868/article/details/97802399