v2.5.0
Datasets ⭐
EXAMPLE CODE
CIFAR 100 Dataset
Load the CIFAR 100 dataset with one line of code in Python. Stream CIFAR 100 while training models in PyTorch & TensorFlow. Visualize the CIFAR 100 dataset.
Visualization of the CIFAR-100 Train Dataset on the Activeloop Platform

CIFAR 100 dataset

What is CIFAR 100 Dataset?

The CIFAR100 (Canadian Institute For Advanced Research) dataset consists of 100 classes with 600 color images of 32x32 resolution for each class. It is divided into 500 training and 100 testing images per class. In CIFAR100, there are 20 superclasses sub-grouped into 100 classes. The dataset comes with two labels for each image such as a "fine" label (class) and a "coarse" label (superclass).

Download CIFAR 100 Dataset in Python

Instead of downloading the CIFAR-100 dataset in Python, you can effortlessly load it in Python via our open-source package Hub with just one line of code.

Load CIFAR 100 Dataset Training Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/cifar100-train")
Copied!

Load CIFAR 100 Dataset Testing Subset in Python

1
import hub
2
ds = hub.load("hub://activeloop/cifar100-test")
Copied!

CIFAR 100 Dataset Structure

CIFAR 100 Data Fields

  • images: tensor containing images of the dataset
  • labels: tensor containing labels for their respective image
  • coarse_labels: tensor containing superclass for their respective image

CIFAR 100 Data Splits

How to use CIFAR 100 Dataset with PyTorch and TensorFlow in Python

Train a model on CIFAR 100 dataset with PyTorch in Python

Let's use Hub's built-in PyTorch one-line dataloader to connect the data to the compute:
1
dataloader = ds.pytorch(num_workers=0, batch_size=4, shuffle=False)
Copied!

Train a model on CIFAR 100 dataset with TensorFlow in Python

1
dataloader = ds.tensorflow()
Copied!

Additional Information about CIFAR 100 Dataset

CIFAR 100 Dataset Description

CIFAR 100 Dataset Curators

Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton

CIFAR 100 Dataset Licensing Information

Hub users may have access to a variety of publicly available datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have a license to use the datasets. It is your responsibility to determine whether you have permission to use the datasets under their license.
If you're a dataset owner and do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thank you for your contribution to the ML community!

CIFAR 100 Dataset Citation Information

1
@article{krizhevsky2009learning,
2
title={Learning multiple layers of features from tiny images},
3
author={Krizhevsky, Alex and Hinton, Geoffrey and others},
4
year={2009},
5
publisher={Citeseer}
6
}
Copied!

CIFAR 100 Dataset FAQs

What is the CIFAR 100 dataset for Python?

CIFAR 100 is similar to the CIFAR 10 dataset; however, it contains 100 classes of 600 images. Each image comes with a "fine" label (class it belongs to) and a "coarse" label (superclass it belongs to). Classes are grouped into 20 superclasses. Each class consists of 500 training images and 100 testing images.

What is the CIFAR 100 dataset used for?

The CIFAR 100 dataset is commonly used for image classification and recognition. It is also commonly used as a benchmark dataset for computer vision algorithms.

How to use and download the CIFAR 100 dataset in Python?

Using the open-source package Activeloop Hub, the CIFAR 100 dataset can quickly be loaded with just one line of code. See detailed instructions on how to load the CIFAR 100 dataset training subset and how to load the testing subset in Python.

What is the difference between CIFAR 100 dataset and CIFAR 10 dataset?

The main difference between the CIFAR 10 dataset and the CIFAR 100 dataset is the number of images and classes. The CIFAR 10 dataset has 10 classes with 6000 images per class. While the CIFAR 100 dataset has 100 classes containing 600 images per class.

How to use CIFAR 100 dataset?

You can stream the CIFAR 100 dataset while training a model in TensorFlow or PyTorch in seconds using the Activeloop Hub open-source package. See detailed instructions on how to train a model on the CIFAR 100 dataset with PyTorch and how to train a model on the CIFAR 100 dataset with TensorFlow in Python.