if __name__ == "__main__":
sigma, alpha = 4, 32
train = load_data()
multiplier = 4
original_size = train[0].shape[0]
final_size = multiplier * original_size
print("Creating dataset of size {}".format(final_size))
x = []
y = numpy.array([])
for run in range(multiplier):
for i in range(original_size):
image = train[0][i]
label = train[1][i]
image = transform.elastic(image, sigma, alpha)
rotation = random.randint(-30, 30)
if label in (1, 7):
rotation /= 2
image = transform.rotate(image, rotation)
image = transform.sigmoid(image, 12)
x.append(image)
y = numpy.append(y, label)
if len(x) % 1000 == 0:
print("Image {}".format(len(x)))
ds = (numpy.vstack(x), y)
prefix = "mnist_elastic_{}_{}".format(sigma, alpha)
suffix = "{}k".format(int(final_size / 1000))
numpy.save("{}_x_{}".format(prefix, suffix), ds[0])
# Load the dataset
# train_set, valid_set, test_set format: tuple(input, target)
# input is an numpy.ndarray of 2 dimensions (a matrix)
# witch row's correspond to an example. target is a
# numpy.ndarray of 1 dimensions (vector)) that have the same length as
# the number of rows in the input. It should give the target
# target to the example with the same index in the input.
dataset = '../data/mnist.pkl.gz'
f = gzip.open(dataset, 'rb')
train_set, valid_set, test_set = cPickle.load(f)
f.close()
return train_set
if __name__ == "__main__":
ds = load_images()
images = ds[0]
labels = ds[1]
w = 16
for n in range(15):
image = images[n]
label = int(labels[n])
image = transform.elastic(image, 4, 32)
rotation = random.randint(-30, 30)
if label in (1, 7):
rotation /= 2
image = transform.rotate(image, rotation)
image = transform.sigmoid(image, 12)
show_image(images[n], image)
