The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

To use this dataset:

import tensorflow_datasets as tfds

ds = tfds.load('cifar10', split='train')
for ex in ds.take(4):
 print(ex)

See the guide for more informations on tensorflow_datasets.

https://storage.googleapis.com/tfds-data/visualization/fig/cifar10-3.0.2.png" alt="Visualization" width="500px">

Dataset Specifications

Contains the entire CIFAR10 dataset, downloaded via PyTorch, then split and saved as .png files representing 32x32 images. There a three splits, perfectly balanced class-wise:

train: 49,000 out of the original 50,000 samples from the training set of CIFAR10; calibration: 1,000 left-out samples from the training set; test: 10,000 samples, the entire original test set.

  File Structure

Files are archives

Dataset Card for cifar10_augmented

This dataset contains augmented versions of CIFAR-10 to benchmark the impact of classical and synthetic augmentation techniques on deep image classification models. Provided as a .zip file, the dataset must be unzipped before use. It follows a standard ImageFolder structure for compatibility with PyTorch and TensorFlow pipelines.

  Dataset Details





  Dataset Sources

Repository:… See the full description on the dataset page: https://huggingface.co/datasets/ianisdev/cifar10_augmented.

This folder contains the neuromorphic vision dataset named as 'CIFAR10-DVS' obtained by displaying the moving images of the CIFAR-10 dataset (http://www.cs.toronto.edu/~kriz/cifar.html) on a LCD monitor. The dataset is used for event-driven scene classification and pattern recognition. These recordings can be displayed using the jAER software (http://sourceforge.net/p/jaer/wiki/Home) using filters DVS128.The files "dat2mat.m" and "mat2dat.m" in (http://www2.imse-cnm.csic.es/caviar/MNIST_DVS/) can be used to transfer lists of events between jAER format (.dat or .aedat) and matlab.Please cite it if you intend to use this dataset. Li H, Liu H, Ji X, Li G and Shi L (2017) CIFAR10-DVS: An Event-Stream Dataset for Object Classification. Front. Neurosci. 11:309. doi: 10.3389/fnins.2017.00309The high-sensitivity DVS used in the recording reported in:P. Lichtsteiner, C. Posch, and T. Delbruck, “A 128×128 120 dB 15 μs latency asynchronous temporal contrast vision sensor,” IEEE J. Solid-State Circuits, vol. 43, no. 2, pp. 566–576, Feb. 2008A single 128x128 pixel DVS sensor was placed in front of a 24" LCD monitor. Images of CIFAR-10 were upscaled to 512 * 512 through bicubic interpolation, and displayed on the LCD monitor with circulating smooth movement. A total of 10,000 event-stream recordings in 10 classes(airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck) with 1000 recordings per classes were obtained.

This dataset is just like the CIFAR-10, except it has 100 classes containing 600 images each. There are 500 training images and 100 testing images per class. The 100 classes in the CIFAR-100 are grouped into 20 superclasses. Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs).

To use this dataset:

import tensorflow_datasets as tfds

ds = tfds.load('cifar100', split='train')
for ex in ds.take(4):
 print(ex)

See the guide for more informations on tensorflow_datasets.

https://storage.googleapis.com/tfds-data/visualization/fig/cifar100-3.0.2.png" alt="Visualization" width="500px">