def run_n_aug(x, y, n_aug, num_classes): # data augmentation
# x = augmentation.horizontal_flip(x)
# x = augmentation.vertical_flip(x)
# x = augmentation.random_crop(x)
# x = augmentation.random_transfer(x)
# x = augmentation.random_rotation(x)
# x, y = augmentation.mixup(image=x, label=y, num_classes=num_classes)
# x = augmentation.cutout(x)
# x = augmentation.random_erasing(x)
# x, y = augmentation.ricap(image_batch=x, label_batch=y, num_classes=num_classes)
if n_aug == 1:
x = augmentation.horizontal_flip(x)
# x = augmentation.vertical_flip(x)
elif n_aug == 2:
x = augmentation.random_crop(x)
elif n_aug == 3:
x = augmentation.random_transfer(x)
elif n_aug == 4:
x = augmentation.random_rotation(x)
elif n_aug == 5:
x, y = augmentation.mixup(image=x, label=y, num_classes=num_classes)
elif n_aug == 6:
x = augmentation.cutout(x)
elif n_aug == 7:
x = augmentation.random_erasing(x)
elif n_aug == 8:
x, y = augmentation.ricap(image_batch=x,
label_batch=y,
num_classes=num_classes)
x = to_var(x)
y = to_var(y)
elif n_aug == 12:
x = augmentation.horizontal_flip(x)
x = augmentation.random_crop(x)
elif n_aug == 17:
x = augmentation.horizontal_flip(x)
x = augmentation.random_erasing(x)
elif n_aug == 34:
x = augmentation.random_transfer(x)
x = augmentation.random_rotation(x)
return x, y
def augmentation(self, X, Y):
print('Augmentation model...')
total = len(X)
x_train, y_train = [], []
for i in xrange(total):
x, y = X[i], Y[i]
#standart
x_train.append(x)
y_train.append(y)
# for _ in xrange(1):
# _x, _y = elastic_transform(x[0], y[0], 100, 20)
# x_train.append(_x.reshape((1,) + _x.shape))
# y_train.append(_y.reshape((1,) + _y.shape))
#flip x
x_train.append(flip_axis(x, 2))
y_train.append(flip_axis(y, 2))
#flip y
x_train.append(flip_axis(x, 1))
y_train.append(flip_axis(y, 1))
#continue
#zoom
for _ in xrange(1):
_x, _y = random_zoom(x, y, (0.9, 1.1))
x_train.append(_x)
y_train.append(_y)
for _ in xrange(0):
_x, _y = random_rotation(x, y, 5)
x_train.append(_x)
y_train.append(_y)
#intentsity
for _ in xrange(1):
_x = random_channel_shift(x, 5.0)
x_train.append(_x)
y_train.append(y)
x_train = np.array(x_train)
y_train = np.array(y_train)
print('x_trian: ', x_train.shape)
return x_train, y_train
def aug_train(split_dir, mode):
train_dir = split_dir + os.sep + "train"
for subdir, dirs, files in os.walk(train_dir):
for f in files:
file_path = subdir + os.sep + f
if (is_image(f)):
print(file_path)
name, ext = os.path.splitext(f)
img = cv2.imread(file_path)
for i in range(1, 4):
rot_dir = (subdir + os.sep + name + "_aug_" + str(i + 1) +
ext)
if (mode == 'random'):
cv2.imwrite(rot_dir, aug.random_rotation(img))
elif (mode == 'strict'):
cv2.imwrite(rot_dir, aug.strict_rotation(img, i))
else:
print("The mode should be either random | strict")
sys.exit(1)
