def calculate_piano_solo_prob(args):
"""Calculate the piano solo probability of all downloaded mp3s, and append
the probability to the meta csv file.
"""
# Arguments & parameters
workspace = args.workspace
mp3s_dir = args.mp3s_dir
mini_data = args.mini_data
sample_rate = piano_detection_model.SR
if mini_data:
prefix = 'minidata_'
else:
prefix = ''
# Paths
similarity_csv_path = os.path.join(workspace,
'{}full_music_pieces_youtube_similarity.csv'.format(prefix))
piano_prediction_path = os.path.join(workspace,
'{}full_music_pieces_youtube_similarity_pianosoloprob.csv'.format(prefix))
# Meta info
meta_dict = read_csv_to_meta_dict(similarity_csv_path)
meta_dict['piano_solo_prob'] = []
meta_dict['audio_name'] = []
meta_dict['audio_duration'] = []
count = 0
piano_solo_detector = piano_detection_model.PianoSoloDetector()
for n in range(len(meta_dict['surname'])):
mp3_path = os.path.join(mp3s_dir, '{}, {}, {}, {}.mp3'.format(
meta_dict['surname'][n], meta_dict['firstname'][n],
meta_dict['music'][n], meta_dict['youtube_id'][n]).replace('/', '_'))
if os.path.exists(mp3_path):
(audio, _) = librosa.core.load(mp3_path, sr=sample_rate, mono=True)
try:
probs = piano_solo_detector.predict(audio)
prob = np.mean(probs)
except:
prob = 0
print(n, mp3_path, prob)
meta_dict['audio_name'].append(get_filename(mp3_path))
meta_dict['piano_solo_prob'].append(prob)
meta_dict['audio_duration'].append(len(audio) / sample_rate)
else:
meta_dict['piano_solo_prob'].append('')
meta_dict['audio_name'].append('')
meta_dict['audio_duration'].append('')
write_meta_dict_to_csv(meta_dict, piano_prediction_path)
print('Write out to {}'.format(piano_prediction_path))
def create_subset200_piano_solo_eval_csv(args):
r"""Select 200 pieces from GiantMIDI-Piano to evaluate the music piece accuracy.
Args:
workspace: str
Returns:
None
"""
# arguments & parameters
workspace = args.workspace
eval_num = 200
# paths
csv_path = os.path.join(
workspace,
'full_music_pieces_youtube_similarity_pianosoloprob_split.csv')
output_path = os.path.join('subset_csvs_for_evaluation',
'subset200_piano_solo_eval.csv')
os.makedirs(os.path.dirname(output_path), exist_ok=True)
meta_dict = read_csv_to_meta_dict(csv_path)
audios_num = len(meta_dict['surname'])
indexes = []
for n in range(audios_num):
if meta_dict['giant_midi_piano'][n] != '' and int(
meta_dict['giant_midi_piano'][n]) == 1:
indexes.append(n)
skip_num = len(indexes) // eval_num
eval_indexes = indexes[0::skip_num][0:eval_num]
new_meta_dict = {key: [] for key in meta_dict.keys()}
new_meta_dict['index_in_csv'] = []
for index in eval_indexes:
for key in meta_dict.keys():
new_meta_dict[key].append(meta_dict[key][index])
new_meta_dict['index_in_csv'].append(index)
new_meta_dict['meta_correct'] = [''] * eval_num
new_meta_dict['sequenced'] = [''] * eval_num
write_meta_dict_to_csv(new_meta_dict, output_path)
print('Write out to {}'.format(output_path))
def create_subset200_eval_csv(args):
r"""Select 200 files from 60,724 downloaded files to evaluate the precision,
recall of piano solo detection.
Args:
workspace: str
Returns:
None
"""
workspace = args.workspace
eval_num = 200
csv_path = os.path.join(
workspace,
'full_music_pieces_youtube_similarity_pianosoloprob_split.csv')
output_path = os.path.join('subset_csvs_for_evaluation',
'subset200_eval.csv')
os.makedirs(os.path.dirname(output_path), exist_ok=True)
meta_dict = read_csv_to_meta_dict(csv_path)
audios_num = len(meta_dict['surname'])
indexes = []
for n in range(audios_num):
if float(meta_dict['similarity'][n]) > 0.6:
indexes.append(n)
skip_num = len(indexes) // eval_num
eval_indexes = indexes[0::skip_num][0:eval_num]
new_meta_dict = {key: [] for key in meta_dict.keys()}
new_meta_dict['index_in_csv'] = []
for index in eval_indexes:
for key in meta_dict.keys():
new_meta_dict[key].append(meta_dict[key][index])
new_meta_dict['index_in_csv'].append(index)
new_meta_dict['piano_solo'] = [''] * eval_num
new_meta_dict['electronic_piano'] = [''] * eval_num
new_meta_dict['sequenced'] = [''] * eval_num
write_meta_dict_to_csv(new_meta_dict, output_path)
print('Write out to {}'.format(output_path))
def create_piano_split(args):
"""Validation, test, train: 1:1:8
"""
# Arguments & parameters
workspace = args.workspace
# Paths
piano_prediction_path = os.path.join(
workspace, 'full_music_pieces_youtube_similarity_pianosoloprob.csv')
split_path = os.path.join(
workspace,
'full_music_pieces_youtube_similarity_pianosoloprob_split.csv')
# Meta info to be downloaded
meta_dict = read_csv_to_meta_dict(piano_prediction_path)
splits = []
i = 0
for n in range(len(meta_dict['surname'])):
if float(meta_dict['piano_solo_prob'][n]) >= 0.5:
if i == 0:
splits.append('validation')
elif i == 1:
splits.append('test')
else:
splits.append('train')
i += 1
else:
splits.append('none')
# Reset i if moved to next composer
if n > 0:
previous_name = '{}, {}'.format(meta_dict['surname'][n - 1],
meta_dict['surname'][n - 1])
current_name = '{}, {}'.format(meta_dict['surname'][n],
meta_dict['surname'][n])
if previous_name != current_name:
i = 0
if i == 10:
i = 0
meta_dict['split'] = splits
write_meta_dict_to_csv(meta_dict, split_path)
print('Write csv to {}'.format(split_path))
def create_piano_split(args):
"""Add 'giant_midi_piano', 'split', and 'surname_in_youtube_title' flags
to csv file and write out the csv file. The ratio of validation, test, train
subsets are 1:1:8.
Args:
workspace: str
Returns:
NoReturn
"""
# arguments & parameters
workspace = args.workspace
# Paths
piano_prediction_path = os.path.join(
workspace, 'full_music_pieces_youtube_similarity_pianosoloprob.csv')
split_path = os.path.join(
workspace,
'full_music_pieces_youtube_similarity_pianosoloprob_split.csv')
# Meta info to be downloaded
meta_dict = read_csv_to_meta_dict(piano_prediction_path)
giant_midi_pianos = []
splits = []
surname_in_youtube_titles = []
i = 0
# Add 'giant_midi_piano', 'split', and 'surname_in_youtube_title' flags to .csv file.
for n in range(len(meta_dict['surname'])):
if meta_dict['piano_solo_prob'][n] == "":
giant_midi_pianos.append("")
splits.append("")
surname_in_youtube_titles.append("")
else:
if float(meta_dict['piano_solo_prob'][n]) >= 0.5:
giant_midi_pianos.append(1)
if i == 0:
splits.append('validation')
elif i == 1:
splits.append('test')
else:
splits.append('train')
i += 1
else:
giant_midi_pianos.append(0)
splits.append("")
if meta_dict['surname'][n] in meta_dict['youtube_title'][n]:
surname_in_youtube_titles.append(1)
else:
surname_in_youtube_titles.append(0)
# Reset i if moved to next composer
if n > 0:
previous_name = '{}, {}'.format(meta_dict['surname'][n - 1],
meta_dict['surname'][n - 1])
current_name = '{}, {}'.format(meta_dict['surname'][n],
meta_dict['surname'][n])
if previous_name != current_name:
i = 0
if i == 10:
i = 0
meta_dict['giant_midi_piano'] = giant_midi_pianos
meta_dict['split'] = splits
meta_dict['surname_in_youtube_title'] = surname_in_youtube_titles
write_meta_dict_to_csv(meta_dict, split_path)
print('Write csv to {}'.format(split_path))