def augment(self, n_augm, out_fname, update=False):
# Define augmenter
sometimes = lambda aug: iaa.Sometimes(0.5, aug)
seq = iaa.Sequential(
[
# apply the following augmenters to most images
iaa.Fliplr(0.5), # horizontally flip 50% of all images
#iaa.Flipud(0.2), # vertically flip 20% of all images
sometimes(iaa.Crop(percent=(0, 0.1))), # crop images by 0-10% of their height/width
sometimes(iaa.Affine(
scale={"x": (0.9, 1.1), "y": (0.9, 1.1)}, # scale images to 80-120% of their size, individually per axis
translate_percent={"x": (-0.1, 0.1), "y": (-0.1, 0.1)}, # translate by -20 to +20 percent (per axis)
rotate=(-20, 20), # rotate by -45 to +45 degrees
shear=(-16, 16), # shear by -16 to +16 degrees
order=[0, 1], # use nearest neighbour or bilinear interpolation (fast)
cval=(0, 255), # if mode is constant, use a cval between 0 and 255
mode=ia.ALL # use any of scikit-image's warping modes (see 2nd image from the top for examples)
)),
sometimes(
iaa.AdditiveGaussianNoise(loc=0, scale=(0.0, 0.05*255), per_channel=0.5) # add gaussian noise to images
),
],
random_order=True
)
with h5py.File(self.path+out_fname, 'r+') as hf:
for subject_k,subject_v in hf['train/pose6/'].items():
if subject_k.split('_')[1] in ['F017', 'F018', 'F019','F020']:
for segment_k,segment_v in subject_v.items():
labels = np.asarray(segment_v['aus'])
idxs = self.balance(labels)
labels = labels[idxs]
for i in range(n_augm):
node = 'train/pose6/'+subject_k+'/'+segment_k+'_'+str(i)
_ = hf.create_group(node)
for tp in ['faces', 'leye', 'reye', 'beye', 'nose', 'mouth', 'lmouth', 'rmouth']:
print '{}/{}/{}'.format(subject_k, segment_k, tp)
images = np.asarray(segment_v[tp])
if np.max(idxs)<images.shape[0]:
images = images[idxs]
else:
print ('-------An index error-------')
labels = np.asarray(segment_v['aus'])
for i in range(n_augm):
augm_images = seq.augment_images(images)
node = 'train/pose6/'+subject_k+'/'+segment_k+'_'+str(i)
print ' Writing node {} with data of shape {}'.format(node, augm_images.shape)
segment = hf[node]
segment.create_dataset(tp, data=augm_images)
if tp=='faces':
segment.create_dataset('aus', data=labels)
def color_space_argumentation(self, image):
seq = iaa.Sequential([
iaa.OneOf([
iaa.GaussianBlur((0, 3.0)),
iaa.AverageBlur(k=(2, 7)),
iaa.MedianBlur(k=(3, 7)),
]),
iaa.Sharpen(alpha=(0, 1.0), lightness=(0.75, 1.5)),
iaa.Add((-2, 21), per_channel=0.5),
iaa.Multiply((0.75, 1.25), per_channel=0.5),
iaa.ContrastNormalization((0.5, 1.50), per_channel=0.5),
iaa.Grayscale(alpha=(0.0, 0.50)),
],
random_order=False)
return seq.augment_image(image)
def get_basic_imgaug_seq(seed):
determinist = {
"deterministic": True,
"random_state": seed
}
train_seq = iaa.Sequential([
iaa.Affine(translate_px=(-25, 25),
scale=(0.85, 1.15),
rotate=(-65, 65),
mode='reflect',
**determinist),
],
random_order=True,
**determinist
)
return train_seq
def get_high_zoom_imgaug_seq(seed):
determinist = {
"deterministic": True,
"random_state": seed
}
train_seq = iaa.Sequential([
# iaa.Sometimes(0.45, iaa.Sharpen(alpha=0.9, lightness=(0.5, 1.15), **determinist), **determinist),
iaa.Sometimes(0.45, iaa.ContrastNormalization(alpha=(0.75, 1.15), **determinist), **determinist),
# iaa.Sometimes(0.5, iaa.AdditiveGaussianNoise(scale=(0, 0.01 * 255),
# per_channel=True, **determinist), **determinist),
iaa.Affine(translate_px=(-5, 5),
scale=(1.0, 1.75),
rotate=(-65, 65),
mode='reflect',
**determinist),
# iaa.Add(value=(-35, 35), per_channel=True), # Probably, can change nature of label
],
random_order=True,
**determinist
)
return train_seq
def augment(img_data, augment=True):
assert 'filepath' in img_data
assert 'bboxes' in img_data
assert 'width' in img_data
assert 'height' in img_data
img_data_aug = copy.deepcopy(img_data)
img = cv2.imread(img_data_aug['filepath'])
# add dimension to keep imgaug tutorial code unchanged
images = np.expand_dims(img, axis=0)
if augment:
# The augmenters expect a list of imgaug.KeypointsOnImage.
keypoints_on_images = []
for image in images:
keypoints = []
for bbox in img_data_aug['bboxes']:
# for every bbox x1, y1, x2, y2 in pairs
x1 = bbox['x1']
y1 = bbox['y1']
keypoints.append(ia.Keypoint(x=x1, y=y1))
x2 = bbox['x2']
y2 = bbox['y2']
keypoints.append(ia.Keypoint(x=x2, y=y2))
keypoints_on_images.append(
ia.KeypointsOnImage(keypoints, shape=image.shape))
# Define our sequence of augmentation steps that will be applied to every image
# All augmenters with per_channel=0.5 will sample one value _per image_
# in 50% of all cases. In all other cases they will sample new values
# _per channel_.
# CHANGE PARAMETERS IN DATA_AUGMENT_V2_PARAMETERS FILE
seq = iaa.Sequential(augment_parameters.get_augment_parameters(),
random_order=True)
# maybe show image transformation sample in grid
if SHOW_AUGMENTED_IMAGE_SAMPLES:
seq.show_grid(images, cols=8, rows=8)
seq_det = seq.to_deterministic(
) # call this for each batch again, NOT only once at the start
# augment keypoints and images
images_aug = seq_det.augment_images(images)
keypoints_aug = seq_det.augment_keypoints(keypoints_on_images)
# maybe show keypoints
if SHOW_KEYPOINTS:
for img_idx, (image_before, image_after, keypoints_before,
keypoints_after) in enumerate(
zip(images, images_aug, keypoints_on_images,
keypoints_aug)):
image_before = keypoints_before.draw_on_image(image_before)
image_after = keypoints_after.draw_on_image(image_after)
misc.imshow(np.concatenate((image_before, image_after),
axis=1)) # before and after
for kp_idx, keypoint in enumerate(keypoints_after.keypoints):
keypoint_old = keypoints_on_images[img_idx].keypoints[
kp_idx]
x_old, y_old = keypoint_old.x, keypoint_old.y
x_new, y_new = keypoint.x, keypoint.y
print(
"[Keypoints for image #%d] before aug: x=%d y=%d | after aug: x=%d y=%d"
% (img_idx, x_old, y_old, x_new, y_new))
# update bboxes coordinates after augmentation
keypoints = keypoints_aug[0].get_coords_array()
for i, bbox in enumerate(img_data_aug['bboxes']):
bbox['x1'] = keypoints[2 * i][0]
bbox['y1'] = keypoints[2 * i][1]
bbox['x2'] = keypoints[2 * i + 1][0]
bbox['y2'] = keypoints[2 * i + 1][1]
img = images_aug[0]
img_data_aug['width'] = img.shape[1]
img_data_aug['height'] = img.shape[0]
return img_data_aug, img
def get_id_imgaug_seq():
return iaa.Sequential()