def test_high_polyphony():
pol_dir = osp.join(absolute_dir_path, "generated", "polyphony")
if osp.exists(pol_dir):
shutil.rmtree(pol_dir)
shutil.copytree(osp.join(absolute_dir_path, "material", "post_processing"),
pol_dir)
ll = glob.glob(osp.join(pol_dir, "*.jams"))
assert len(ll) == 2
save_name = os.path.join(absolute_dir_path, "generated", "final.tsv")
rm_high_polyphony(pol_dir, 1, save_name)
ll = glob.glob(osp.join(pol_dir, "*.jams"))
assert len(ll) == 1, f"Problem rm_high_polyphony {len(ll)} != 1"
events_start=(
event_time_dist,
event_time_mean,
event_time_std,
event_time_min,
event_time_max,
),
events_duration=(event_duration_dist, event_duration_min,
event_duration_max),
snrs=(snr_dist, snr_min, snr_max),
pitch_shifts=(pitch_dist, pitch_min, pitch_max),
time_stretches=(time_stretch_dist, time_stretch_min, time_stretch_max),
txt_file=True,
)
rm_high_polyphony(out_folder_500, 2)
out_tsv = osp.join(out_tsv_folder, "500ms.tsv")
post_process_txt_labels(out_folder_500,
output_folder=out_folder_500,
output_tsv=out_tsv)
# Generate 2 variants of this dataset
jams_to_modify = glob.glob(osp.join(out_folder_500, "*.jams"))
# Be careful, if changing the values of the added onset value,
# you maybe want to rerun the post_processing_annotations to be sure there is no inconsistency
# 5.5s onset files
out_folder_5500 = osp.join(base_out_folder, "5500ms")
add_onset = 5.0
modif_onset_5s = functools.partial(modify_fg_onset,
slice_seconds=add_onset)
pitch_max = 3.0
time_stretch_dist = 'uniform'
time_stretch_min = 1
time_stretch_max = 1
out_folder_ls_30 = osp.join(out_folder, "ls_30dB")
create_folder(out_folder_ls_30)
sg.generate(n_soundscapes, out_folder_ls_30, min_events, max_events, labels=('choose', []),
source_files=('choose', []), sources_time=(source_time_dist, source_time),
events_start=(evt_time_dist, evt_time_mean, evt_time_std, evt_time_min, evt_time_max),
events_duration=(event_duration_dist, event_duration_min, event_duration_max),
snrs=('const', 30), pitch_shifts=('uniform', -3.0, 3.0), time_stretches=('uniform', 1, 1),
txt_file=True)
rm_high_polyphony(out_folder_ls_30, 3)
post_process_txt_labels(out_folder_ls_30, output_folder=out_folder_ls_30, output_tsv=args.out_tsv,
background_label=True)
list_jams = glob.glob(osp.join(out_folder_ls_30, "*.jams"))
# We create the same dataset with different background SNR
# Be careful, 15 means the background SNR is 15,
# so the foreground background snr ratio is between -9dB and 15dB
out_folder_ls_15 = osp.join(out_folder, "ls_15dB")
modify_jams(list_jams, change_snr, out_folder_ls_15, db_change=-15)
# Same for 0dB FBSNR, from original fbsnr [6;30]dB, we go to [-24;0]dB FBSNR
out_folder_ls_0 = osp.join(out_folder, "ls_0dB")
modify_jams(list_jams, change_snr, out_folder_ls_15, db_change=-30)
sg = SoundscapesGenerator(duration, fg_folder, bg_folder, ref_db=ref_db)
sg.generate_by_label_occurence(params,
n_soundscapes,
outfolder,
min_events=1,
max_events=1,
pitch_shift=('uniform', -3, 3))
if __name__ == '__main__':
base_soundbank = osp.join("..", "..", "synthetic")
for subset in ["train", "eval"]:
soundbank_path = osp.join(base_soundbank, "audio", subset, "soundbank")
fg_folder = osp.join(soundbank_path, "foreground/")
bg_folder = osp.join(soundbank_path, "background")
dataset_path = osp.join("..", "..", "dataset")
param_file = osp.join(dataset_path, "metadata", subset,
f"event_occurences_{subset}.json")
outfolder = osp.join(dataset_path, "audio", subset,
"one_event_generated")
out_tsv = osp.join(dataset_path, "audio", subset,
"one_event_generated.tsv")
generate_training(15, fg_folder, bg_folder, param_file, outfolder)
rm_high_polyphony(outfolder, 3)
post_process_txt_labels(outfolder,
output_folder=outfolder,
output_tsv=out_tsv)
if random_state is None:
random_states = [None for i in range(nproc)]
else:
random_states = [random_state + i for i in range(nproc)]
print(random_states)
with multiprocessing.Pool(nproc) as p:
p.starmap(generate_multiproc,
zip(list_start, numbers, random_states))
# Single process
else:
sg = SoundscapesGenerator(duration=clip_duration,
fg_folder=fg_folder,
bg_folder=bg_folder,
ref_db=ref_db,
samplerate=sample_rate,
random_state=random_state)
sg.generate_by_label_occurence(label_occurences=co_occur_dict,
number=n_soundscapes,
out_folder=full_out_folder,
save_isolated_events=True,
pitch_shift=pitch_shift)
# ##
# Post processing
rm_high_polyphony(full_out_folder, max_polyphony=2)
# concat same labels overlapping
post_process_txt_labels(full_out_folder,
output_folder=full_out_folder,
output_tsv=out_tsv,
rm_nOn_nOff=True)