sage.data.psd.read_psds

Filename : read_psds.py Description : Short description of the file

Created on 2026-03-02 20:46:58

__author__ = Narenraju Nagarajan __copyright__ = Copyright 2026, ProjectName __license__ = MIT Licence __version__ = 0.0.1 __maintainer__ = Narenraju Nagarajan __affiliation__ = N/A __email__ = N/A __status__ = [‘inProgress’, ‘Archived’, ‘inUsage’, ‘Debugging’]

GitHub Repository: NULL

Documentation: NULL

Functions

get_fiducial_psds()

Load the pre-computed fiducial per-detector PSDs from disk.

Module Contents

get_fiducial_psds()[source]

Load the pre-computed fiducial per-detector PSDs from disk.

Reads binary float32 files written during the data-preparation stage from {export_dir}/fiducial_psds/ and returns them as a single stacked tensor on the configured device.

The fiducial PSDs are used by OptimalSNREstimator to compute matched-filter SNR for SNR rescaling during signal injection.

Returns:: Per-detector one-sided PSDs on cfg.device, where D is the number of detectors and F is the number of frequency bins.
Return type:: torch.Tensor, shape (D, F)