deepextractor.generation.glitch_functions

Synthetic glitch signal generators.

The CDVGAN and gengli generators require optional dependencies:

pip install deepextractor[generative]

Module Contents

deepextractor.generation.glitch_functions.SRATE = 4096[source]
deepextractor.generation.glitch_functions.NYQUIST_FREQ = 2048[source]
deepextractor.generation.glitch_functions.generate_chirp(duration, sample_rate=4096, f0_min=1, f0_max=NYQUIST_FREQ, f1_min=1, f1_max=NYQUIST_FREQ)[source]
deepextractor.generation.glitch_functions.generate_sine(duration, sample_rate=4096, freq_min=1, freq_max=NYQUIST_FREQ)[source]
deepextractor.generation.glitch_functions.generate_sine_gaussian(duration, sample_rate=4096, freq_min=1, freq_max=NYQUIST_FREQ)[source]
deepextractor.generation.glitch_functions.generate_gaussian_pulse(duration, sample_rate=4096, fc_min=1, fc_max=NYQUIST_FREQ, bw_min=0.1, bw_max=1.0, bwr_min=-10, bwr_max=0, tpr_min=0.5, tpr_max=2.0)[source]

Generate a Gaussian pulse with random parameters.

Parameters:

  • duration (float) – Duration in seconds.

  • sample_rate (int) – Sampling rate in Hz.

  • fc_min (float) – Range for the center frequency (Hz).

  • fc_max (float) – Range for the center frequency (Hz).

  • bw_min (float) – Range for the fractional bandwidth.

  • bw_max (float) – Range for the fractional bandwidth.

  • bwr_min (float) – Range for the bandwidth reference level (dB).

  • bwr_max (float) – Range for the bandwidth reference level (dB).

  • tpr_min (float) – Range for the taper reference level (dB).

  • tpr_max (float) – Range for the taper reference level (dB).

deepextractor.generation.glitch_functions.ringdown(duration, sample_rate=4096, n_signals=1)[source]
deepextractor.generation.glitch_functions.generate_gengli_glitch(ifo)[source]

Generate a glitch sample using the gengli library.

Requires the [generative] optional dependencies: pip install deepextractor[generative]

deepextractor.generation.glitch_functions.generate_cdvgan_glitch(gtype, cdvgan_generator)[source]

Generate a glitch sample using a pretrained CDVGAN TensorFlow model.

Parameters:

  • gtype (str) – Glitch type: one of 'blip', 'tomte', 'bbh', 'simplex', 'uniform'.

  • cdvgan_generator (tf.keras.Model) – The loaded CDVGAN generator model.