Package documentation

Generator class

class Generator.Generator

Bases: object

Transient noise artifacts generator from ‘“Generating transient noise artefacts in gravitational-wave detector data with generative adversarial networks by Powell et. al. “ <https://arxiv.org/abs/2207.00207>’

clear_queue()

Clears the current queue of artifacts.

generate(glitch, n_images_to_generate)

Generates images for the given glitch in the form of numpy arrays, and adds it to the ‘queue’.

Parameters:

• glitch (String) – Name of the glitch to be generated.

• n_images_to_generate – Number of images to be generated.

Returns:

a (n_images_to_generate x 140 x 170) numpy array of the images generated and a (n_images_to_generate) list of corresponding glitch labels.

Return type:

Returns a tuple

generate_all(n_images_to_generate)

Generates images for all the glitches, in the form of numpy arrays.

Parameters:

n_images_to_generate – Number of images to be generated, for each glitch

Returns:

a ((n_images_to_generate * num_of_glitches) x 140 x 170) numpy array of the images generated and a (n_images_to_generate * num_of_glitches) list of corresponding glitch labels.

The array can be accessed through ‘generator.curr_array’ and the glitch labels through ‘generator.curr_glitch’

Return type:

Returns a tuple

save_as_hdf5(path, name='timeseries', clear_queue=False)

Saves the queue of artifacts in a h5 file. The snippets are 2 seconds long.

Parameters:

• path – Folder where the h5 file should be created.

• name (String) – Name for the h5 file (Default: “timeseries”)

• clear_queue – Boolean value for if the queue will be cleared after the images are saved. (Default: False)

save_as_png(path, clear_queue=False)

Saves the queue of artifacts, which are in the form of a spectrogram, as png files.

Parameters:

• path – Folder where the images will be saved.

• clear_queue – Boolean value for if the queue will be cleared after the images are saved. (Default: False)