This is classic MNIST dataset and pickled (in npz format). To load this dataset in your code use following function def load_data(path): with np.load(path) as f: x_train, y_train = f['x_train'], f['y_train'] x_test, y_test = f['x_test'], f['y_test'] return (x_train, y_train), (x_test, y_test) (x_train, y_train), (x_test, y_test) = load_data('../input/mnist.npz') Dataset source: https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz