CIFAR-100
收藏魔搭社区2026-05-23 更新2024-08-31 收录
下载链接:
https://modelscope.cn/datasets/OpenDataLab/CIFAR-100
下载链接
链接失效反馈官方服务:
资源简介:
displayName: CIFAR-100
labelTypes:
- Classification
license:
- Unknown
mediaTypes:
- Image
paperUrl: https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf
publishDate: "2009-04-08"
publishUrl: http://www.cs.toronto.edu/~kriz/cifar.html
publisher:
- Massachusetts Institute of Technology
- New York University
tags: []
taskTypes:
- Image Classification
---
# 数据集介绍
## 简介
这个数据集就像 CIFAR-10,除了它有 100 个类,每个类包含 600 张图像。每个类别有 500 个训练图像和 100 个测试图像。 CIFAR-100 中的 100 个类被分为 20 个超类。每个图像都带有一个“精细”标签(它所属的类)和一个“粗糙”标签(它所属的超类)。
## 类定义
```
aquatic mammals: beaver, dolphin, otter, seal, whale
fish: aquarium fish, flatfish, ray, shark, trout
flowers: orchids, poppies, roses, sunflowers, tulips
food containers: bottles, bowls, cans, cups, plates
fruit and vegetables: apples, mushrooms, oranges, pears, sweet peppers
household electrical devices: clock, computer keyboard, lamp, telephone, television
household furniture: bed, chair, couch, table, wardrobe
insects: bee, beetle, butterfly, caterpillar, cockroach
large carnivores: bear, leopard, lion, tiger, wolf
large man-made outdoor things: bridge, castle, house, road, skyscraper
large natural outdoor scenes: cloud, forest, mountain, plain, sea
large omnivores and herbivores: camel, cattle, chimpanzee, elephant, kangaroo
medium-sized mammals: fox, porcupine, possum, raccoon, skunk
non-insect invertebrates: crab, lobster, snail, spider, worm
people: baby, boy, girl, man, woman
reptiles: crocodile, dinosaur, lizard, snake, turtle
small mammals: hamster, mouse, rabbit, shrew, squirrel
trees: maple, oak, palm, pine, willow
vehicles 1: bicycle, bus, motorcycle, pickup truck, train
vehicles 2: lawn-mower, rocket, streetcar, tank, tractor
```
## 引文
```
@article{krizhevsky2009learning,
title={Learning multiple layers of features from tiny images},
author={Krizhevsky, Alex and Hinton, Geoffrey and others},
year={2009},
publisher={Citeseer}
}
```
## Download dataset
:modelscope-code[]{type="git"}
显示名称:CIFAR-100
标签类型:
- 分类
许可协议:
- 未知
媒体类型:
- 图像
论文链接:https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf
发布日期:"2009-04-08"
发布平台链接:http://www.cs.toronto.edu/~kriz/cifar.html
发布机构:
- 麻省理工学院(Massachusetts Institute of Technology, MIT)
- 纽约大学(New York University, NYU)
标签:[]
任务类型:
- 图像分类
---
# 数据集简介
## 概况
本数据集与CIFAR-10高度相似,但其包含100个类别,每类共计600张图像。其中每类包含500张训练图像与100张测试图像。CIFAR-100的100个类别被划分为20个超类别,每张图像同时附带「精细标签」(对应其所属的具体类别)与「粗糙标签」(对应其所属的超类别)。
## 类别定义
水生哺乳动物(aquatic mammals):海狸、海豚、水獭、海豹、鲸
鱼类(fish):观赏鱼、比目鱼、鳐鱼、鲨鱼、鳟鱼
花卉(flowers):兰花、罂粟花、玫瑰、向日葵、郁金香
食品容器(food containers):瓶子、碗、金属罐、杯子、盘子
果蔬类(fruit and vegetables):苹果、蘑菇、橙子、梨、甜椒
家用电气设备(household electrical devices):时钟、电脑键盘、灯具、电话、电视机
家用家具(household furniture):床、椅子、长沙发、桌子、衣柜
昆虫类(insects):蜜蜂、甲虫、蝴蝶、毛毛虫、蟑螂
大型食肉动物(large carnivores):熊、豹、狮子、老虎、狼
大型人工户外设施(large man-made outdoor things):桥梁、城堡、房屋、道路、摩天大楼
大型自然户外场景(large natural outdoor scenes):云、森林、山脉、平原、海洋
大型杂食与草食动物(large omnivores and herbivores):骆驼、牛、黑猩猩、大象、袋鼠
中型哺乳动物(medium-sized mammals):狐狸、豪猪、负鼠、浣熊、臭鼬
非昆虫无脊椎动物(non-insect invertebrates):螃蟹、龙虾、蜗牛、蜘蛛、蠕虫
人类(people):婴儿、男孩、女孩、男性、女性
爬行动物(reptiles):鳄鱼、恐龙、蜥蜴、蛇、乌龟
小型哺乳动物(small mammals):仓鼠、小鼠、兔子、鼩鼱、松鼠
树木(trees):枫树、橡树、棕榈树、松树、柳树
交通工具1(vehicles 1):自行车、公共汽车、摩托车、皮卡、火车
交通工具2(vehicles 2):割草机、火箭、有轨电车、坦克、拖拉机
## 引用文献
@article{krizhevsky2009learning,
title={从微型图像中学习多层特征},
author={Alex Krizhevsky、Geoffrey Hinton 等},
year={2009},
publisher={Citeseer}
}
## 数据集下载
:modelscope-code[]{type="git"}
提供机构:
maas
创建时间:
2024-07-05



