# CIFAR-100

## Summary
* [Introduction](#introduction)
* [Dataset Structure](#dataset_structure)
* [Reference](#reference)
* [License](#license)
* [Citation](#citation)

## Introduction

The CIFAR-100 dataset consists of 60000 32x32 colour images in 100 classes, with 600 images per class. There are 500 training images and 100 testing images per class. There are 50000 training images and 10000 test images. The 100 classes are grouped into 20 superclasses. There are two labels per image - fine label (actual class) and coarse label (superclass).

## Dataset Structure
### Data Instances
A sample from the training set is provided below:

{
  'img': <PIL.PngImagePlugin.PngImageFile image mode=RGB size=32x32 at 0x2767F58E080>,
  'fine_label': 19,
  'coarse_label': 11
}

### Data Fields
- **img**: An image in the form of a PIL.Image.Image object with dimensions of 32x32 pixels. It's worth noting that when accessing the image column using dataset[0]["image"], the image file is automatically decoded. Decoding a large number of image files can be time-consuming. Therefore, it is recommended to first query the sample index before the "image" column. In other words, dataset[0]["image"] should always be prioritized over dataset["image"][0].
- **fine_label**: An integer classification label with the following mapping: apple(0), aquarium_fish(1), baby(2),... , worm (99).
- **coarse_label**: An integer coarse classification label with the following mapping: aquatic_mammals(0), fish(1), flowers(2),... , vehicles_2 (19).


## Reference
We would like to acknowledge Alex Krizhevsky for creating and maintaining the CIFAR-100 dataset as a valuable resource for the computer vision and machine learning research community. For more information about the CIFAR-100 dataset and its creator, please visit [the CIFAR-100 dataset website](https://www.cs.toronto.edu/~kriz/cifar.html).

## License
The dataset has been released under MIT license.

## Citation

@TECHREPORT{Krizhevsky09learningmultiple,
    author = {Alex Krizhevsky},
    title = {Learning multiple layers of features from tiny images},
    institution = {},
    year = {2009}
}