observations.cifar10

cifar10(path)

Load the CIFAR-10 data set (Krizhevsky & Hinton, 2009). It consists of 32x32 RGB images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

Args:

  • path: str. Path to directory which either stores file or otherwise file will be downloaded and extracted there. Filename is cifar-10-batches-py/.

Returns:

Tuple of np.ndarray's (x_train, y_train), (x_test, y_test).

Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images.