ElasticTransformation#

class deeptrack.augmentations.ElasticTransformation(alpha: float | Callable[[...], float] = 20, sigma: float | Callable[[...], float] = 2, ignore_last_dim: bool | Callable[[...], bool] = True, order: int | Callable[[...], int] = 3, cval: float | Callable[[...], float] = 0, mode: str | Callable[[...], str] = 'constant', **kwargs)#

Bases: Augmentation

Transform images by moving pixels locally around using displacement fields.

The augmenter creates a random distortion field using alpha and sigma, which define the strength and smoothness of the field respectively. These are used to transform the input locally.

For a detailed explanation, see

Simard, Steinkraus and Platt
Best Practices for Convolutional Neural Networks applied to Visual
Document Analysis
in Proc. of the International Conference on Document Analysis and
Recognition, 2003

Parameters#

alphanumber

Strength of the distortion field. Common values are in the range (10, 100)

sigmanumber

Standard deviation of the gaussian kernel used to smooth the distortion fields. Common values are in the range (1, 10)

ignore_last_dimbool

Whether to skip creating a distortion field for the last dimension. This is often desired if the last dimension is a channel dimension (such as a color image.) In that case, the three channels are transformed identically and do not bleed into eachother.

orderint

Interpolation order to use. Takes integers from 0 to 5

  • 0: Nearest-neighbor

  • 1: Bi-linear (default)

  • 2: Bi-quadratic (not recommended by skimage)

  • 3: Bi-cubic

  • 4: Bi-quartic

  • 5: Bi-quintic

cvalnumber

The constant intensity value used to fill in new pixels. This value is only used if mode is set to constant.

modestr

Parameter that defines newly created pixels. May take the same values as in scipy.ndimage.map_coordinates(), i.e. constant, nearest, reflect or wrap.

Methods Summary

get(image, sigma, alpha, ignore_last_dim, ...)

Transform an image [abstract method].

Methods Documentation

get(image, sigma, alpha, ignore_last_dim, **kwargs)#

Transform an image [abstract method].

Abstract method that defines how the feature transforms the input. The current value of all properties will be passed as keyword arguments.

Parameters#

image‘Image’ or List[‘Image’]

The Image or list of images to transform.

**kwargsDict[str, Any]

The current value of all properties in properties as well as any global arguments.

Returns#

‘Image’ or List[‘Image’]

The transformed image or list of images.

Raises#

NotImplementedError

Must be overridden by subclasses.