neuralset.extractors.image.RFFT2D¶

class neuralset.extractors.image.RFFT2D(*, event_types: Literal['Image'] = 'Image', aggregation: Literal['single', 'sum', 'mean', 'first', 'middle', 'last', 'cat', 'stack', 'trigger'] = 'single', allow_missing: bool = False, frequency: float = 0.0, imsize: int | None = None, infra: MapInfra = MapInfra(folder=None, cluster=None, logs='{folder}/logs/{user}/%j', job_name=None, timeout_min=25, nodes=1, tasks_per_node=1, cpus_per_task=8, gpus_per_node=1, mem_gb=None, max_pickle_size_gb=None, slurm_constraint=None, slurm_partition=None, slurm_account=None, slurm_qos=None, slurm_use_srun=False, slurm_additional_parameters=None, conda_env=None, workdir=None, permissions=511, version='v5', keep_in_ram=True, max_jobs=128, min_samples_per_job=4096, forbid_single_item_computation=False, mode='cached'), n_components_to_keep: int | None = None, average_channels: bool = True, return_log_psd: bool = False, return_angle: bool = False)[source][source]¶

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

Parameters:

n_components_to_keep (int | None) – Number of components of the FFT to keep, starting from low frequencies and moving towards higher frequencies. If None, use all components.
average_channels (bool) – If True, average RGB channels before taking the FFT (to reduce dimensionality).
return_log_psd (bool) – If True, return the flattened log PSD instead of the “viewed-as-real” complex FFT.
return_angle (bool) – If True, return the flattened angle. Can be combined with the log PSD.