imgaug.augmenters.flip

Augmenters that apply mirroring/flipping operations to images.

List of augmenters:

• Fliplr

• Flipud

class imgaug.augmenters.flip.Fliplr(p=1, seed=None, name=None, random_state='deprecated', deterministic='deprecated')

Bases: Augmenter

Flip/mirror input images horizontally.

Note

The default value for the probability is 0.0. So, to flip all input images use Fliplr(1.0) and not just Fliplr().

Supported dtypes:

See fliplr().

Parameters:

• p (number or imgaug.parameters.StochasticParameter, optional) – Probability of each image to get flipped.

• seed (None or int or imgaug.random.RNG or numpy.random.Generator or numpy.random.BitGenerator or numpy.random.SeedSequence or numpy.random.RandomState, optional) – See __init__().

• name (None or str, optional) – See __init__().

• random_state (None or int or imgaug.random.RNG or numpy.random.Generator or numpy.random.BitGenerator or numpy.random.SeedSequence or numpy.random.RandomState, optional) – Old name for parameter seed. Its usage will not yet cause a deprecation warning, but it is still recommended to use seed now. Outdated since 0.4.0.

• deterministic (bool, optional) – Deprecated since 0.4.0. See method to_deterministic() for an alternative and for details about what the “deterministic mode” actually does.

Examples

>>> import imgaug.augmenters as iaa
>>> aug = iaa.Fliplr(0.5)

Flip 50 percent of all images horizontally.

>>> aug = iaa.Fliplr(1.0)

Flip all images horizontally.

Methods

__call__(*args, **kwargs)	Alias for augment().
augment([return_batch, hooks])	Augment a batch.
augment_batch(batch[, hooks])	Deprecated.
augment_batch_(batch[, parents, hooks])	Augment a single batch in-place.
augment_batches(batches[, hooks, background])	Augment multiple batches.
augment_bounding_boxes(bounding_boxes_on_images)	Augment a batch of bounding boxes.
augment_heatmaps(heatmaps[, parents, hooks])	Augment a batch of heatmaps.
augment_image(image[, hooks])	Augment a single image.
augment_images(images[, parents, hooks])	Augment a batch of images.
augment_keypoints(keypoints_on_images[, ...])	Augment a batch of keypoints/landmarks.
augment_line_strings(line_strings_on_images)	Augment a batch of line strings.
augment_polygons(polygons_on_images[, ...])	Augment a batch of polygons.
augment_segmentation_maps(segmaps[, ...])	Augment a batch of segmentation maps.
copy()	Create a shallow copy of this Augmenter instance.
copy_random_state(source[, recursive, ...])	Copy the RNGs from a source augmenter sequence.
copy_random_state_(source[, recursive, ...])	Copy the RNGs from a source augmenter sequence (in-place).
deepcopy()	Create a deep copy of this Augmenter instance.
draw_grid(images, rows, cols)	Augment images and draw the results as a single grid-like image.
find_augmenters(func[, parents, flat])	Find augmenters that match a condition.
find_augmenters_by_name(name[, regex, flat])	Find augmenter(s) by name.
find_augmenters_by_names(names[, regex, flat])	Find augmenter(s) by names.
get_all_children([flat])	Get all children of this augmenter as a list.
get_children_lists()	Get a list of lists of children of this augmenter.
get_parameters()	See get_parameters().
localize_random_state([recursive])	Assign augmenter-specific RNGs to this augmenter and its children.
localize_random_state_([recursive])	Assign augmenter-specific RNGs to this augmenter and its children.
pool([processes, maxtasksperchild, seed])	Create a pool used for multicore augmentation.
remove_augmenters(func[, copy, ...])	Remove this augmenter or children that match a condition.
remove_augmenters_(func[, parents])	Remove in-place children of this augmenter that match a condition.
remove_augmenters_inplace(func[, parents])	Deprecated.
reseed([random_state, deterministic_too])	Deprecated.
seed_([entropy, deterministic_too])	Seed this augmenter and all of its children.
show_grid(images, rows, cols)	Augment images and plot the results as a single grid-like image.
to_deterministic([n])	Convert this augmenter from a stochastic to a deterministic one.

get_parameters()

See get_parameters().

class imgaug.augmenters.flip.Flipud(p=1, seed=None, name=None, random_state='deprecated', deterministic='deprecated')

Bases: Augmenter

Flip/mirror input images vertically.

Note

The default value for the probability is 0.0. So, to flip all input images use Flipud(1.0) and not just Flipud().

Supported dtypes:

See flipud().

Parameters:

• p (number or imgaug.parameters.StochasticParameter, optional) – Probability of each image to get flipped.

• seed (None or int or imgaug.random.RNG or numpy.random.Generator or numpy.random.BitGenerator or numpy.random.SeedSequence or numpy.random.RandomState, optional) – See __init__().

• name (None or str, optional) – See __init__().

• random_state (None or int or imgaug.random.RNG or numpy.random.Generator or numpy.random.BitGenerator or numpy.random.SeedSequence or numpy.random.RandomState, optional) – Old name for parameter seed. Its usage will not yet cause a deprecation warning, but it is still recommended to use seed now. Outdated since 0.4.0.

• deterministic (bool, optional) – Deprecated since 0.4.0. See method to_deterministic() for an alternative and for details about what the “deterministic mode” actually does.

Examples

>>> import imgaug.augmenters as iaa
>>> aug = iaa.Flipud(0.5)

Flip 50 percent of all images vertically.

>>> aug = iaa.Flipud(1.0)

Flip all images vertically.

Methods

__call__(*args, **kwargs)	Alias for augment().
augment([return_batch, hooks])	Augment a batch.
augment_batch(batch[, hooks])	Deprecated.
augment_batch_(batch[, parents, hooks])	Augment a single batch in-place.
augment_batches(batches[, hooks, background])	Augment multiple batches.
augment_bounding_boxes(bounding_boxes_on_images)	Augment a batch of bounding boxes.
augment_heatmaps(heatmaps[, parents, hooks])	Augment a batch of heatmaps.
augment_image(image[, hooks])	Augment a single image.
augment_images(images[, parents, hooks])	Augment a batch of images.
augment_keypoints(keypoints_on_images[, ...])	Augment a batch of keypoints/landmarks.
augment_line_strings(line_strings_on_images)	Augment a batch of line strings.
augment_polygons(polygons_on_images[, ...])	Augment a batch of polygons.
augment_segmentation_maps(segmaps[, ...])	Augment a batch of segmentation maps.
copy()	Create a shallow copy of this Augmenter instance.
copy_random_state(source[, recursive, ...])	Copy the RNGs from a source augmenter sequence.
copy_random_state_(source[, recursive, ...])	Copy the RNGs from a source augmenter sequence (in-place).
deepcopy()	Create a deep copy of this Augmenter instance.
draw_grid(images, rows, cols)	Augment images and draw the results as a single grid-like image.
find_augmenters(func[, parents, flat])	Find augmenters that match a condition.
find_augmenters_by_name(name[, regex, flat])	Find augmenter(s) by name.
find_augmenters_by_names(names[, regex, flat])	Find augmenter(s) by names.
get_all_children([flat])	Get all children of this augmenter as a list.
get_children_lists()	Get a list of lists of children of this augmenter.
get_parameters()	See get_parameters().
localize_random_state([recursive])	Assign augmenter-specific RNGs to this augmenter and its children.
localize_random_state_([recursive])	Assign augmenter-specific RNGs to this augmenter and its children.
pool([processes, maxtasksperchild, seed])	Create a pool used for multicore augmentation.
remove_augmenters(func[, copy, ...])	Remove this augmenter or children that match a condition.
remove_augmenters_(func[, parents])	Remove in-place children of this augmenter that match a condition.
remove_augmenters_inplace(func[, parents])	Deprecated.
reseed([random_state, deterministic_too])	Deprecated.
seed_([entropy, deterministic_too])	Seed this augmenter and all of its children.
show_grid(images, rows, cols)	Augment images and plot the results as a single grid-like image.
to_deterministic([n])	Convert this augmenter from a stochastic to a deterministic one.

get_parameters()

See get_parameters().

imgaug.augmenters.flip.HorizontalFlip(*args, **kwargs)

Alias for Fliplr.

imgaug.augmenters.flip.VerticalFlip(*args, **kwargs)

Alias for Flipud.

imgaug.augmenters.flip.fliplr(arr)

Flip an image-like array horizontally.

Supported dtypes:

• uint8: yes; fully tested

• uint16: yes; fully tested

• uint32: yes; fully tested

• uint64: yes; fully tested

• int8: yes; fully tested

• int16: yes; fully tested

• int32: yes; fully tested

• int64: yes; fully tested

• float16: yes; fully tested

• float32: yes; fully tested

• float64: yes; fully tested

• float128: yes; fully tested

• bool: yes; fully tested

Parameters:

arr (ndarray) – A 2D/3D (H, W, [C]) image array.

Returns:

Horizontally flipped array.

Return type:

ndarray

Examples

>>> import numpy as np
>>> import imgaug.augmenters.flip as flip
>>> arr = np.arange(16).reshape((4, 4))
>>> arr_flipped = flip.fliplr(arr)

Create a 4x4 array and flip it horizontally.

imgaug.augmenters.flip.flipud(arr)

Flip an image-like array vertically.

Supported dtypes:

• uint8: yes; fully tested

• uint16: yes; fully tested

• uint32: yes; fully tested

• uint64: yes; fully tested

• int8: yes; fully tested

• int16: yes; fully tested

• int32: yes; fully tested

• int64: yes; fully tested

• float16: yes; fully tested

• float32: yes; fully tested

• float64: yes; fully tested

• float128: yes; fully tested

• bool: yes; fully tested

Parameters:

arr (ndarray) – A 2D/3D (H, W, [C]) image array.

Returns:

Vertically flipped array.

Return type:

ndarray

Examples

>>> import numpy as np
>>> import imgaug.augmenters.flip as flip
>>> arr = np.arange(16).reshape((4, 4))
>>> arr_flipped = flip.flipud(arr)

Create a 4x4 array and flip it vertically.