def save_example_to_tfrecord(df,
output_path,
audio_format,
root_dir,
tag_path,
sample_rate=16000,
num_mels=96,
multitag=False,
verbose=False):
''' Creates and saves a TFRecord file.
Parameters
----------
df: DataFrame
A pandas DataFrame containing the following columns: "track_id", "mp3_path", "npz_path".
output_path: str
The path or filename to save TFRecord file as.
If not a path, the current folder will be used with output_path as filename.
audio_format: {'waveform', 'log-mel-spectrogram'}
If 'log-mel-spectrogram', audio will be converted to that format; otherwise, it will default to raw waveform.
root_dir: str
The root directory to where the .npz files (or the .mp3 files) are stored.
tag_path: str
The path to the lastfm_clean.db database.
sample_rate: int
The sample rate to use when serializing the audio.
num_mels: int
The number of mels in the mel-spectrogram.
multitag: list
If True, encode multiple tags at the same time (provide as list of filenames; feature names will be 'tags-0', 'tags-1' etc.)
verbose: bool
If True, print progress.
'''
with tf.io.TFRecordWriter(output_path) as writer:
if not multitag:
fm = LastFm(tag_path)
n_tags = len(fm.get_tag_nums())
else:
fm = [LastFm(os.path.join(tag_path, path)) for path in multitag]
n_tags = [len(fm.get_tag_nums()) for fm in fm]
assert all(
x == n_tags[0] for x in
n_tags), 'all databases need to have the same number of tags'
n_tags = n_tags[0] # cast back to int
# initialize
exceptions = []
df.reset_index(drop=True, inplace=True)
if verbose:
progbar = Progbar(
len(df)) # create an instance of the progress bar
for i, cols in df.iterrows():
if verbose:
progbar.add(1) # update progress bar
# unpack cols
tid, path = cols
# encode tags
if not multitag:
encoded_tags = get_encoded_tags(fm, tid, n_tags)
else:
encoded_tags = np.array(
[get_encoded_tags(fm, tid, n_tags) for fm in fm]
) # convert to ndarray to ensure consistency with one-dimensional case
# skip tracks which dont have any "clean" tags
if encoded_tags.size == 0:
if verbose:
print("{} has no tags. Skipping...".format(tid))
continue
path = os.path.join(root_dir, path)
if set(df.columns) == {'track_id', 'npz_path'}:
# get the unsampled array from the .npz file
unsampled_audio = np.load(path)
else:
# get the unsampled array from the original .mp3 file
try:
array, sr = librosa.core.load(path, sr=None)
except:
exceptions.append({
'path': path,
'tid': tid,
'encoded_tags': encoded_tags
})
continue
unsampled_audio = {'array': array, 'sr': sr}
# resample audio array into 'sample_rate' and convert into 'audio_format'
processed_array = process_array(unsampled_audio['array'],
audio_format,
sr_in=unsampled_audio['sr'],
sr_out=sample_rate,
num_mels=num_mels)
# load the tf.Example
example = get_example(processed_array, tid, encoded_tags)
# save the tf.Example into a .tfrecord file
writer.write(example.SerializeToString())
# print exceptions
if set(df.columns) == {'track_id', 'npz_path'}:
return
else:
if exceptions:
print('Could not process the following tracks:')
for i, exception in enumerate(exceptions):
print(" {:3d}. {} {}".format(
i, exception["tid"] + exception["path"]))
return
