def __call__(self, sample):
img, annot = sample.image, sample.annotation
unique_labels = np.unique(
annot[:, 4].astype('int').astype('str')).tolist()
rotate_degree = random.uniform(-1 * self.degree, self.degree)
bbs = BoundingBoxesOnImage([
BoundingBox(x1=ann[0],
y1=ann[1],
x2=ann[2],
y2=ann[3],
label=str(int(ann[4]))) for ann in annot
],
shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(
labels=unique_labels,
foreground=iaa.geometric.TranslateY(percent=0.1))
img_aug, bbs_aug = aug(image=img, bounding_boxes=bbs)
# drawn_img = bbs_aug.draw_on_image(img_aug * 255, size=2, color=[0, 255., 0])
# import skimage
# skimage.io.imsave('draw.png', drawn_img)
# img = img.rotate(rotate_degree, Image.BILINEAR)
# mask = mask.rotate(rotate_degree, Image.NEAREST)
sample.image = img_aug
sample.annotation = bbs_aug
def __call__(self, sample):
img, annot = sample.image, sample.annotation
unique_labels = np.unique(
annot[:, 4].astype('int').astype('str')).tolist()
bbs = BoundingBoxesOnImage([
BoundingBox(x1=ann[0],
y1=ann[1],
x2=ann[2],
y2=ann[3],
label=str(int(ann[4]))) for ann in annot
],
shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(labels=unique_labels,
foreground=iaa.Cutout(
nb_iterations=int(round(self.v)),
size=0.05,
fill_mode="gaussian"))
img_aug, bbs_aug = aug(image=img, bounding_boxes=bbs)
annot_aug = np.array(
[[bb.x1, bb.y1, bb.x2, bb.y2,
np.float32(bb.label)] for bb in bbs_aug])
# the shape has to be at least (0,5)
if len(annot_aug) == 0:
annot_aug = np.zeros((0, 5))
sample.image = img_aug
sample.annotation = annot_aug
def __call__(self, sample):
img, annot = sample.image, sample.annotation
unique_labels = np.unique(
annot[:, 4].astype('int').astype('str')).tolist()
bbs = BoundingBoxesOnImage([
BoundingBox(x1=ann[0],
y1=ann[1],
x2=ann[2],
y2=ann[3],
label=str(int(ann[4]))) for ann in annot
],
shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(labels=unique_labels,
foreground=iaa.pillike.EnhanceColor(
self.v))
img_aug, bbs_aug = aug(image=(img * 255.).astype('uint8'),
bounding_boxes=bbs)
img_aug = img_aug.astype('float32') / 255.
annot_aug = np.array(
[[bb.x1, bb.y1, bb.x2, bb.y2,
np.float32(bb.label)] for bb in bbs_aug])
# the shape has to be at least (0,5)
if len(annot_aug) == 0:
annot_aug = np.zeros((0, 5))
sample.image = img_aug
sample.annotation = annot_aug
def __call__(self, sample):
img, annot = sample['img'], sample['annot']
unique_labels = np.unique(
annot[:, 4].astype('int').astype('str')).tolist()
bbs = BoundingBoxesOnImage([
BoundingBox(x1=ann[0],
y1=ann[1],
x2=ann[2],
y2=ann[3],
label=str(int(ann[4]))) for ann in annot
],
shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(
labels=unique_labels,
foreground=iaa.pillike.Solarize(threshold=0.))
img_aug, bbs_aug = aug(image=(img * 2. - 1.), bounding_boxes=bbs)
img_aug = (img_aug + 1.) / 2
annot_aug = np.array(
[[bb.x1, bb.y1, bb.x2, bb.y2,
np.float32(bb.label)] for bb in bbs_aug])
# the shape has to be at least (0,5)
if len(annot_aug) == 0:
annot_aug = np.zeros((0, 5))
return {'img': img_aug, 'annot': annot_aug}
def __call__(self, sample):
img, annot = sample['img'], sample['annot']
unique_labels = np.unique(
annot[:, 4].astype('int').astype('str')).tolist()
bbs = BoundingBoxesOnImage([
BoundingBox(x1=ann[0],
y1=ann[1],
x2=ann[2],
y2=ann[3],
label=str(int(ann[4]))) for ann in annot
],
shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(
labels=unique_labels,
foreground=iaa.AllChannelsHistogramEqualization())
img_aug, bbs_aug = aug(image=(img * 255.).astype('uint8'),
bounding_boxes=bbs)
img_aug = img_aug.astype('float32') / 255.
annot_aug = np.array(
[[bb.x1, bb.y1, bb.x2, bb.y2,
np.float32(bb.label)] for bb in bbs_aug])
# the shape has to be at least (0,5)
if len(annot_aug) == 0:
annot_aug = np.zeros((0, 5))
return {'img': img_aug, 'annot': annot_aug}
def cutout_bbox(magnitude: int, **kwargs) -> iaa.BlendAlphaBoundingBoxes:
"""
Only apply cutout to the bounding box area. Passing the
height and width of the image as integers and as keywords
will scale the bounding box according to the policy. Note, the
cutout location is chosen randomly and will only appear if it
falls within the bounding box.
:type magnitude: int
:param magnitude: magnitude of cutout
:param kwargs:
height: height of the image as int
width: width of the image as int
:rtype: iaa.BlendAlphaBoundingBoxes
:return: Method to apply cutout only to bounding boxes
"""
level = int((magnitude / _MAX_MAGNITUDE) * CUTOUT_BBOX)
cutout_args = {}
if 'height' in kwargs and 'width' in kwargs:
size = tuple(
np.clip([level / kwargs['height'], level / kwargs['width']], 0.0,
1.0))
cutout_args['size'] = size
return iaa.BlendAlphaBoundingBoxes(None,
foreground=iaa.Cutout(**cutout_args))
def chapter_augmenters_blendalphaboundingboxes():
fn_start = "blend/blendalphaboundingboxes"
aug = iaa.BlendAlphaBoundingBoxes(None, background=iaa.Multiply(0.0))
batch = ia.Batch(
images=[ia.quokka(size=(128, 128))] * (4 * 1),
bounding_boxes=[ia.quokka_bounding_boxes(size=(128, 128))] * (4 * 1))
run_and_save_augseq_batch(fn_start + "_multiply_background.jpg",
aug,
batch,
cols=4,
rows=1)
def __call__(self, sample):
img, annot = sample['img'], sample['annot']
unique_labels = np.unique(annot[:, 4].astype('int').astype('str')).tolist()
bbs = BoundingBoxesOnImage([BoundingBox(x1=ann[0], y1=ann[1], x2=ann[2], y2=ann[3], label=str(int(ann[4]))) for ann in annot], shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(labels=unique_labels, foreground=iaa.geometric.TranslateY(percent=0.1))
img_aug, bbs_aug = aug(image=img, bounding_boxes=bbs)
annot_aug = np.array([[bb.x1, bb.y1, bb.x2, bb.y2, np.float32(bb.label)] for bb in bbs_aug])
# drawn_img = bbs_aug.draw_on_image(img_aug * 255, size=2, color=[0, 255., 0])
# import skimage
# skimage.io.imsave('draw.png', drawn_img)
return {'image': img_aug, 'annot': annot_aug}
def fliplr_boxes(_: int) -> iaa.BlendAlphaBoundingBoxes:
"""
Flip only the bounding boxes horizontally
Tensorflow Policy Equivalent: flip_only_bboxes
:type _: int
:param _: Unused, kept to fit within the ecosystem
:rtype: iaa.AllChannelsHistogramEqualization
:return: Method to flip bounding boxes horizontally
"""
return iaa.BlendAlphaBoundingBoxes(None, foreground=iaa.Fliplr(1.0))
def translate_y_bbox(magnitude: int) -> iaa.BlendAlphaBoundingBoxes:
"""
Translate bounding boxes only on the y-axis
Tensorflow Policy Equivalent: translate_y
:type magnitude: int
:param magnitude: magnitude of translation
:rtype: iaa.BlendAlphaBoundingBoxes
:return: Method to apply y translation to bounding boxes
"""
level = _translate_mag_to_arg(magnitude, bbox=True)
return iaa.BlendAlphaBoundingBoxes(
None, foreground=iaa.geometric.TranslateY(px=level))
def shear_y_bbox(magnitude: int) -> iaa.BlendAlphaBoundingBoxes:
"""
Apply y shear only to bboxes
Tensorflow Policy Equivalent: shear_y_only_bboxes
:type magnitude: int
:param magnitude: magnitude of y shear
:rtype: iaa.BlendAlphaBoundingBoxes
:return: Method to y shear bounding boxes
"""
level = _shear_mag_to_arg(magnitude)
return iaa.BlendAlphaBoundingBoxes(
None,
foreground=iaa.ShearY(level),
)
def __call__(self, sample):
img, annot = sample.image, sample.annotation
unique_labels = np.unique(
annot[:, 4].astype('int').astype('str')).tolist()
bbs = BoundingBoxesOnImage([
BoundingBox(x1=ann[0],
y1=ann[1],
x2=ann[2],
y2=ann[3],
label=str(int(ann[4]))) for ann in annot
],
shape=img.shape)
aug = iaa.BlendAlphaBoundingBoxes(
labels=unique_labels,
foreground=iaa.geometric.TranslateX(percent=self.v))
img_aug, bbs_aug = aug(image=img, bounding_boxes=bbs)
annot_aug = np.array(
[[bb.x1, bb.y1, bb.x2, bb.y2,
np.float32(bb.label)] for bb in bbs_aug])
masks = []
if sample.masks_and_category is not None:
for index in sample.masks_and_category:
masks.append(index[0])
mask_aug = []
if masks is not None:
for mask in masks:
mask = SegmentationMapsOnImage(mask, shape=img.shape).arr
segmap, _ = aug(image=mask, bounding_boxes=bbs)
mask_aug.append(segmap)
# back to 2D array
mask_result = []
for mask in mask_aug:
mask_result.append(mask[:, :, 0])
for i, index in enumerate(sample.masks_and_category):
index[0] = mask_result[i]
# the shape has to be at least (0,5)
if len(annot_aug) == 0:
annot_aug = np.zeros((0, 5))
sample.image = img_aug
sample.annotation = annot_aug
