CIFAR_10_small

Author: Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton Source: [University of Toronto](https://www.cs.toronto.edu/~kriz/cifar.html) - 2009 Please cite: Alex Krizhevsky (2009) Learning Multiple Layers of Features from Tiny Images, Tech Report. CIFAR-10 small This is a 20,000 instance sample of the original CIFAR-10 dataset. Sampled randomly and stratified, with 2000 examples per class. Training and test set are merged. Find the corresponding task for the original train-test splits. CIFAR-10 is a labeled subset of the [80 million tiny images dataset](http://groups.csail.mit.edu/vision/TinyImages/). It (originally) consists 32x32 color images representing 10 classes of objects: 0. airplane 1. automobile 2. bird 3. cat 4. deer 5. dog 6. frog 7. horse 8. ship 9. truck The classes are completely mutually exclusive. There is no overlap between automobiles and trucks. "Automobile" includes sedans, SUVs, things of that sort. "Truck" includes only big trucks. Neither includes pickup trucks. The original CIFAR-10 dataset contains 6000 images per class. The original train-test split randomly divided these into 5000 train and 1000 test images per class. ### Attribute description Each instance represents a 32x32 colour image as a 3072-value array. The first 1024 entries contain the red channel values, the next 1024 the green, and the final 1024 the blue. The image is stored in row-major order, so that the first 32 entries of the array are the red channel values of the first row of the image. The labels are encoded as integers in the range 0-9, corresponding to the numbered classes listed above