← Back to API reference

neuralset.extractors.image.RFFT2D

pydantic model neuralset.extractors.image.RFFT2D

(Cropped) 2D Fourier spectrum of an image of real values.

Parameters:

• n_components_to_keep – Number of components of the FFT to keep, starting from low frequencies and moving towards higher frequencies. If None, use all components.

• average_channels – If True, average RGB channels before taking the FFT (to reduce dimensionality).

• return_log_psd – If True, return the flattened log PSD instead of the “viewed-as-real” complex FFT.

• return_angle – If True, return the flattened angle. Can be combined with the log PSD.

Fields:

• average_channels (bool)

• n_components_to_keep (int | None)

• return_angle (bool)

• return_log_psd (bool)

requirements: ClassVar[tuple[str, ...]] = ('torchvision>=0.15.2', 'pillow>=9.2.0')

field n_components_to_keep: int | None = None

field average_channels: bool = True

field return_log_psd: bool = False

field return_angle: bool = False

← Back to API reference