# scale the raw pixel intensities to the range [0, 1]
data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)
print("[INFO] data matrix: {:.2f}MB".format(
	data.nbytes / (1024 * 1000.0)))

# binarize the labels
lb = LabelBinarizer()
labels = lb.fit_transform(labels)

# partition the data into training and testing splits using 80% of
# the data for training and the remaining 20% for testing
(trainX, testX, trainY, testY) = train_test_split(data,
	labels, test_size=0.2, random_state=42)