def __init__(self, background=(123, 117, 104), labels_format={'class_id': 0, 'xmin': 1, 'ymin': 2, 'xmax': 3, 'ymax': 4}):
'''
Arguments:
background (list/tuple, optional): A 3-tuple specifying the RGB color value of the
background pixels of the translated images.
labels_format (dict, optional): A dictionary that defines which index in the last axis of the labels
of an image contains which bounding box coordinate. The dictionary maps at least the keywords
'xmin', 'ymin', 'xmax', and 'ymax' to their respective indices within last axis of the labels array.
'''
self.labels_format = labels_format
# Generate coordinates for patches that are between 1.0 and 4.0 times
# the size of the input image in both spatial dimensions.
self.patch_coord_generator = PatchCoordinateGenerator(must_match='h_w',
min_scale=1.0,
max_scale=4.0,
scale_uniformly=True)
# With probability 0.5, place the input image randomly on a canvas filled with
# mean color values according to the parameters set above. With probability 0.5,
# return the input image unaltered.
self.expand = RandomPatch(patch_coord_generator=self.patch_coord_generator,
box_filter=None,
image_validator=None,
n_trials_max=1,
clip_boxes=False,
prob=0.5,
background=background,
labels_format=self.labels_format)
def __init__(self,
background=(123, 117, 104),
labels_format={
'class_id': 0,
'xmin': 1,
'ymin': 2,
'xmax': 3,
'ymax': 4
}):
self.labels_format = labels_format
# Generate coordinates for patches that are between 1.0 and 4.0 times
# the size of the input image in both spatial dimensions.
self.patch_coord_generator = PatchCoordinateGenerator(
must_match='h_w',
min_scale=1.0,
max_scale=4.0,
scale_uniformly=True)
# With probability 0.5, place the input image randomly on a canvas filled with
# mean color values according to the parameters set above. With probability 0.5,
# return the input image unaltered.
self.expand = RandomPatch(
patch_coord_generator=self.patch_coord_generator,
box_filter=None,
image_validator=None,
n_trials_max=1,
clip_boxes=False,
prob=0.5,
background=background,
labels_format=self.labels_format)
def __init__(self,
resize_height,
resize_width,
random_brightness=(-48, 48, 0.5),
random_contrast=(0.5, 1.8, 0.5),
random_saturation=(0.5, 1.8, 0.5),
random_hue=(18, 0.5),
random_flip=0.5,
min_scale=0.3,
max_scale=2.0,
min_aspect_ratio=0.5,
max_aspect_ratio=2.0,
n_trials_max=3,
clip_boxes=True,
overlap_criterion='area',
bounds_box_filter=(0.3, 1.0),
bounds_validator=(0.5, 1.0),
n_boxes_min=1,
background=(0, 0, 0),
labels_format={'class_id': 0, 'xmin': 1, 'ymin': 2, 'xmax': 3, 'ymax': 4}):
self.n_trials_max = n_trials_max
self.clip_boxes = clip_boxes
self.overlap_criterion = overlap_criterion
self.bounds_box_filter = bounds_box_filter
self.bounds_validator = bounds_validator
self.n_boxes_min = n_boxes_min
self.background = background
self.labels_format = labels_format
# Determines which boxes are kept in an image after the transformations have been applied.
self.box_filter_patch = BoxFilter(check_overlap=True,
check_min_area=False,
check_degenerate=False,
overlap_criterion=self.overlap_criterion,
overlap_bounds=self.bounds_box_filter,
labels_format=self.labels_format)
self.box_filter_resize = BoxFilter(check_overlap=False,
check_min_area=True,
check_degenerate=True,
min_area=16,
labels_format=self.labels_format)
# Determines whether the result of the transformations is a valid training image.
self.image_validator = ImageValidator(overlap_criterion=self.overlap_criterion,
bounds=self.bounds_validator,
n_boxes_min=self.n_boxes_min,
labels_format=self.labels_format)
# Utility transformations
self.convert_to_3_channels = ConvertTo3Channels() # Make sure all images end up having 3 channels.
self.convert_RGB_to_HSV = ConvertColor(current='RGB', to='HSV')
self.convert_HSV_to_RGB = ConvertColor(current='HSV', to='RGB')
self.convert_to_float32 = ConvertDataType(to='float32')
self.convert_to_uint8 = ConvertDataType(to='uint8')
self.resize = Resize(height=resize_height,
width=resize_width,
box_filter=self.box_filter_resize,
labels_format=self.labels_format)
# Photometric transformations
self.random_brightness = RandomBrightness(lower=random_brightness[0], upper=random_brightness[1],
prob=random_brightness[2])
self.random_contrast = RandomContrast(lower=random_contrast[0], upper=random_contrast[1],
prob=random_contrast[2])
self.random_saturation = RandomSaturation(lower=random_saturation[0], upper=random_saturation[1],
prob=random_saturation[2])
self.random_hue = RandomHue(max_delta=random_hue[0], prob=random_hue[1])
# Geometric transformations
self.random_flip = RandomFlip(dim='horizontal', prob=random_flip, labels_format=self.labels_format)
self.patch_coord_generator = PatchCoordinateGenerator(must_match='w_ar',
min_scale=min_scale,
max_scale=max_scale,
scale_uniformly=False,
min_aspect_ratio=min_aspect_ratio,
max_aspect_ratio=max_aspect_ratio)
self.random_patch = RandomPatch(patch_coord_generator=self.patch_coord_generator,
box_filter=self.box_filter_patch,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max,
clip_boxes=self.clip_boxes,
prob=1.0,
can_fail=False,
labels_format=self.labels_format)
# Define the processing chain
self.transformations = [self.convert_to_3_channels,
self.convert_to_float32,
self.random_brightness,
self.random_contrast,
self.convert_to_uint8,
self.convert_RGB_to_HSV,
self.convert_to_float32,
self.random_saturation,
self.random_hue,
self.convert_to_uint8,
self.convert_HSV_to_RGB,
self.random_patch,
self.random_flip,
self.resize]
def __init__(self,
resize_height,
resize_width,
random_brightness=(-20, 20, 0.5),
random_contrast=(0.8, 1.0, 0.5),
random_saturation=(0.8, 1.8, 0.5),
random_hue=(10, 0.5),
random_flip=0.5,
random_rotate_small=([np.pi / 40, np.pi / 30], 0.5),
random_rotate_big=([np.pi / 2, np.pi, 3 * np.pi / 2], 0.5),
min_scale=0.8,
max_scale=1.05,
min_aspect_ratio=0.8,
max_aspect_ratio=1.2,
n_trials_max=3,
overlap_criterion='center_point',
bounds_box_filter=(0.3, 1.0),
bounds_validator=(0.5, 1.0),
n_boxes_min=1,
random_translate=((0.03, 0.05), (0.03, 0.05), 0.5),
random_scale=(0.9, 1.1, 0.5),
proba_no_aug=1 / 3):
self.n_trials_max = n_trials_max
self.overlap_criterion = overlap_criterion
self.bounds_box_filter = bounds_box_filter
self.bounds_validator = bounds_validator
self.n_boxes_min = n_boxes_min
self.proba_no_aug = proba_no_aug # the probability of not performing any transformations
# Determines which boxes are kept in an image after the transformations have been applied.
self.box_filter = BoxFilter(check_overlap=True,
check_min_area=False,
check_degenerate=False,
overlap_criterion=self.overlap_criterion,
overlap_bounds=self.bounds_box_filter)
self.box_filter_resize = BoxFilter(check_overlap=False,
check_min_area=True,
check_degenerate=True,
min_area=16)
# Determines whether the result of the transformations is a valid training image.
self.image_validator = ImageValidator(
overlap_criterion=self.overlap_criterion,
bounds=self.bounds_validator,
n_boxes_min=self.n_boxes_min)
# Utility transformations
self.convert_to_3_channels = ConvertTo3Channels(
) # Make sure all images end up having 3 channels.
self.convert_RGB_to_HSV = ConvertColor(current='RGB', to='HSV')
self.convert_HSV_to_RGB = ConvertColor(current='HSV', to='RGB')
self.convert_to_float32 = ConvertDataType(to='float32')
self.convert_to_uint8 = ConvertDataType(to='uint8')
self.resize = Resize(height=resize_height,
width=resize_width,
box_filter=self.box_filter_resize)
# Photometric transformations
self.random_brightness = RandomBrightness(lower=random_brightness[0],
upper=random_brightness[1],
prob=random_brightness[2])
self.random_contrast = RandomContrast(lower=random_contrast[0],
upper=random_contrast[1],
prob=random_contrast[2])
self.random_saturation = RandomSaturation(lower=random_saturation[0],
upper=random_saturation[1],
prob=random_saturation[2])
self.random_hue = RandomHue(max_delta=random_hue[0],
prob=random_hue[1])
# Geometric transformations
self.random_horizontal_flip = RandomFlip(dim='horizontal',
prob=random_flip)
self.random_vertical_flip = RandomFlip(dim='vertical',
prob=random_flip)
self.random_translate = RandomTranslate(
dy_minmax=random_translate[0],
dx_minmax=random_translate[1],
prob=random_translate[2],
box_filter=self.box_filter,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max)
self.random_rotate_small = RandomRotate(
angles=random_rotate_small[0],
prob=random_rotate_small[1],
box_filter=self.box_filter,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max)
self.random_rotate_big = RandomRotate(
angles=random_rotate_big[0],
prob=random_rotate_big[1],
box_filter=self.box_filter,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max)
self.random_zoom_in = RandomScale(min_factor=1.0,
max_factor=random_scale[1],
prob=random_scale[2],
box_filter=self.box_filter,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max)
self.random_zoom_out = RandomScale(
min_factor=random_scale[0],
max_factor=random_scale[0],
prob=random_scale[2],
box_filter=self.box_filter,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max)
# random patch generator is not used for the moment but it could be useful in your project
self.patch_coord_generator = PatchCoordinateGenerator(
must_match='h_w',
min_scale=min_scale,
max_scale=max_scale,
scale_uniformly=False,
min_aspect_ratio=min_aspect_ratio,
max_aspect_ratio=max_aspect_ratio)
self.random_patch = RandomPatch(
patch_coord_generator=self.patch_coord_generator,
box_filter=self.box_filter,
image_validator=self.image_validator,
n_trials_max=self.n_trials_max,
prob=0.5,
can_fail=False)
# If we zoom in, do translation before scaling.
self.sequence1 = [
self.convert_to_3_channels, self.convert_to_float32,
self.random_brightness, self.random_contrast,
self.convert_to_uint8, self.convert_RGB_to_HSV,
self.convert_to_float32, self.random_saturation, self.random_hue,
self.convert_to_uint8, self.convert_HSV_to_RGB,
self.random_horizontal_flip, self.random_vertical_flip,
self.random_translate, self.random_rotate_big,
self.random_rotate_small, self.random_zoom_in, self.random_patch,
self.resize
]
# If we zoom out, do translation after scaling.
self.sequence2 = [
self.convert_to_3_channels, self.convert_to_float32,
self.random_brightness, self.random_contrast,
self.convert_to_uint8, self.convert_RGB_to_HSV,
self.convert_to_float32, self.random_saturation, self.random_hue,
self.convert_to_uint8, self.convert_HSV_to_RGB,
self.random_horizontal_flip, self.random_vertical_flip,
self.random_zoom_out, self.random_translate,
self.random_rotate_big, self.random_rotate_small,
self.random_patch, self.resize
]
self.sequence3 = [
self.convert_to_3_channels, self.convert_to_uint8,
self.random_horizontal_flip, self.random_vertical_flip,
self.random_translate, self.random_rotate_big,
self.random_rotate_small, self.resize
]