在新选项卡中打开链接
  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 alg… 展开

    Github
    Get the Data

    Many ML libraries already include Fashion-MNIST data/API, give it a try!
    You … 展开

    Github
    Usage

    Loading data with Python (requires NumPy)
    Use utils/mnist_reader in this repo:
    Loading data with Tensorflow
    Make sure you have downloaded the data and placed it in d… 展开

    Github
    Contributing

    Thanks for your interest in contributing! There are many ways to get involved; start with our contributor guidelines and then check these open issues for specific tasks. 展开

    Github
     
  1. 1

    Fashion-MNIST is a dataset created by Zalando, consisting of 60,000 training examples and 10,000 test examples. Each example is a 28x28 grayscale image of a fashion product, associated with a label from one of 10 classes. The dataset is designed to serve as a direct drop-in replacement for the original MNIST dataset, which contains handwritten digits1.

    Why Fashion-MNIST?

    The original MNIST dataset is widely used in the AI/ML community for benchmarking algorithms. However, it has become too easy for modern algorithms, with convolutional neural networks achieving 99.7% accuracy1. Fashion-MNIST addresses this by providing a more challenging dataset that better represents modern computer vision tasks1.

    Loading the Dataset

    Using Python and NumPy

    You can load the dataset using the mnist_reader utility provided in the repository:

    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')
    这是否有帮助?

    查看以下来源的结果:

  2. fashion_mnist | TensorFlow Datasets

    2024年6月1日 · fashion_mnist is a dataset of Zalando's article images for image classification. It contains 60,000 training and 10,000 test examples, each with a label from 10 classes.

  3. Fashion MNIST数据集介绍及下载 - CSDN博客

    2020年1月6日 · 本文介绍了Fashion MNIST数据集的特点和用途,以及如何下载和加载该数据集。Fashion MNIST是一组包含70000张灰度图像的服饰分类数据集,与经典的MNIST手写数字数据集有相似的格式和大小,但更具挑战性。

  4. Fashion-MNIST:替代MNIST手写数字集的图像数据集

    Fashion-MNIST是由Zalando旗下的研究部门提供的一个包含10种类别的7万个时尚商品图片的数据集,与MNIST数据集的大小、格式和划分一致。本文介绍了Fashion-MNIST的目的、获取方式、评测结果和可视化,并提供了论文引用信 …

  5. Fashion MNIST - Kaggle

    An MNIST-like dataset of 70,000 28x28 labeled fashion images Kaggle uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more

  6. Dataset之Fashion-MNIST:Fashion-MNIST数据集简介 …

    2019年5月22日 · Fashion-MNIST是一种时尚产品图像数据集,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。本文详细介绍了Fashion-MNIST数据集的特点、下载方式和使用方法,并提供了相关的代码和 …

  7. fashion-mnist/README.zh-CN.md at master - GitHub

    A MNIST-like fashion product database. Benchmark :point_down: - zalandoresearch/fashion-mnist

  8. GitHub - primaryobjects/fashion: The Fashion-MNIST dataset and …

  9. zalando-datasets/fashion_mnist · Datasets at Hugging …

    Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes.

  10. [1708.07747] Fashion-MNIST: a Novel Image Dataset for …