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. The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.

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.