AsType

class deeptrack.features.AsType(dtype: Any | Callable[[...], Any] = 'float64', **kwargs: dict[str, Any])

Bases: Feature

Convert the data type of images.

This feature changes the data type (dtype) of input images to a specified type. The accepted types are the same as those used by NumPy arrays, such as float64, int32, uint16, int16, uint8, and int8.

Parameters

dtype: PropertyLike[Any], optional

The desired data type for the image. Defaults to “float64”.

**kwargs:: dict of str to Any

Additional keyword arguments passed to the parent Feature class.

Methods

get(image: np.ndarray, dtype: str, **kwargs: dict[str, Any]) -> np.ndarray

Convert the data type of the input image.

Examples

>>> import numpy as np
>>> from deeptrack.features import AsType

Create an input array: >>> input_image = np.array([1.5, 2.5, 3.5])

Apply an AsType feature to convert to int32: >>> astype_feature = AsType(dtype=”int32”) >>> output_image = astype_feature.get(input_image, dtype=”int32”) >>> print(output_image) [1 2 3]

Verify the data type: >>> print(output_image.dtype) int32

Methods Summary

get(image, dtype, **kwargs)

Convert the data type of the input image.

Methods Documentation

get(image: ndarray, dtype: str, **kwargs: dict[str, Any]) → ndarray

Convert the data type of the input image.

Parameters

image: np.ndarray

The input image to process.

dtype: str

The desired data type for the image.

**kwargs: Any

Additional keyword arguments (unused here).

Returns

np.ndarray

The input image converted to the specified data type.