CIFAR-100 图像分类数据集

CIFAR-100 Dataset 是用于机器视觉领域的图像分类数据集，拥有 20 个大类，共计 100 个小类，其中每个小类包含 600 张图像（500 张训练图像和 100 张测试图像）并且每张图像均有一个小标签和一个大标签。该数据集由多伦多大学计算机科学系（Computer Science of University of Toronto）的 Alex Krizhevsky、Vinod Nair 和 Geoffrey Hinton 于 2009 年发布，相关论文有《Learning Multiple Layers of Features from Tiny Images》。

The CIFAR-100 Dataset is an image classification dataset for machine vision. It comprises 20 superclasses and a total of 100 subclasses. Each subclass contains 600 images, including 500 training images and 100 test images, and each image is assigned both a subclass label and a superclass label. This dataset was released in 2009 by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton from the Department of Computer Science, University of Toronto, with its associated paper titled *Learning Multiple Layers of Features from Tiny Images*.

搜集汇总

背景与挑战

背景概述

CIFAR-100 是一个经典的图像分类数据集，包含20个大类和100个小类，总计60,000张图像，每张图像均标注有小标签和大标签，适用于机器视觉任务。该数据集由多伦多大学的研究团队于2009年发布，常用于训练和评估深度学习模型，具有结构清晰、规模适中的特点。