def _ExampleToInputs(self,
ex,
truncated_length=0,
crop_training_sequence_to_notes=False):
hparams = copy.deepcopy(constants.DEFAULT_HPARAMS)
hparams.crop_training_sequence_to_notes = crop_training_sequence_to_notes
filename = ex.features.feature['id'].bytes_list.value[0]
sequence, crop_beginning_seconds = data.preprocess_sequence(
ex.features.feature['sequence'].bytes_list.value[0], hparams)
wav_data = ex.features.feature['audio'].bytes_list.value[0]
if crop_training_sequence_to_notes:
wav_data = audio_io.crop_wav_data(wav_data, hparams.sample_rate,
crop_beginning_seconds,
sequence.total_time)
spec = data.wav_to_spec(wav_data, hparams=hparams)
roll = sequences_lib.sequence_to_pianoroll(
sequence,
frames_per_second=data.hparams_frames_per_second(hparams),
min_pitch=constants.MIN_MIDI_PITCH,
max_pitch=constants.MAX_MIDI_PITCH,
min_frame_occupancy_for_label=0.0,
onset_mode='length_ms',
onset_length_ms=32.,
onset_delay_ms=0.)
length = data.wav_to_num_frames(
wav_data, frames_per_second=data.hparams_frames_per_second(hparams))
return self._DataToInputs(spec, roll.active, roll.weights, length, filename,
truncated_length)
def _ExampleToInputs(self,
ex,
truncated_length=0):
hparams = copy.deepcopy(constants.DEFAULT_HPARAMS)
filename = ex.features.feature['id'].bytes_list.value[0]
sequence = data.preprocess_sequence(
ex.features.feature['sequence'].bytes_list.value[0])
wav_data = ex.features.feature['audio'].bytes_list.value[0]
spec = data.wav_to_spec(wav_data, hparams=hparams)
roll = sequences_lib.sequence_to_pianoroll(
sequence,
frames_per_second=data.hparams_frames_per_second(hparams),
min_pitch=constants.MIN_MIDI_PITCH,
max_pitch=constants.MAX_MIDI_PITCH,
min_frame_occupancy_for_label=0.0,
onset_mode='length_ms',
onset_length_ms=32.,
onset_delay_ms=0.)
length = data.wav_to_num_frames(
wav_data, frames_per_second=data.hparams_frames_per_second(hparams))
return self._DataToInputs(spec, roll.active, roll.weights, length, filename,
truncated_length)
def _ExampleToInputs(self,
ex,
truncated_length=0,
crop_training_sequence_to_notes=False):
hparams = copy.deepcopy(constants.DEFAULT_HPARAMS)
hparams.crop_training_sequence_to_notes = crop_training_sequence_to_notes
filename = ex.features.feature['id'].bytes_list.value[0]
sequence, crop_beginning_seconds = data.preprocess_sequence(
ex.features.feature['sequence'].bytes_list.value[0], hparams)
wav_data = ex.features.feature['audio'].bytes_list.value[0]
if crop_training_sequence_to_notes:
wav_data = audio_io.crop_wav_data(wav_data, hparams.sample_rate,
crop_beginning_seconds,
sequence.total_time)
spec = data.wav_to_spec(wav_data, hparams=hparams)
roll = sequences_lib.sequence_to_pianoroll(
sequence,
frames_per_second=data.hparams_frames_per_second(hparams),
min_pitch=constants.MIN_MIDI_PITCH,
max_pitch=constants.MAX_MIDI_PITCH,
min_frame_occupancy_for_label=0.0,
onset_mode='length_ms',
onset_length_ms=32.,
onset_delay_ms=0.)
length = data.wav_to_num_frames(
wav_data,
frames_per_second=data.hparams_frames_per_second(hparams))
return self._DataToInputs(spec, roll.active, roll.weights, length,
filename, truncated_length)
def _ExampleToInputs(self,
ex,
truncated_length=0):
hparams = copy.deepcopy(constants.DEFAULT_HPARAMS)
filename = ex.features.feature['id'].bytes_list.value[0]
sequence = data.preprocess_sequence(
ex.features.feature['sequence'].bytes_list.value[0])
wav_data = ex.features.feature['audio'].bytes_list.value[0]
spec = data.wav_to_spec(wav_data, hparams=hparams)
roll = sequences_lib.sequence_to_pianoroll(
sequence,
frames_per_second=data.hparams_frames_per_second(hparams),
min_pitch=constants.MIN_MIDI_PITCH,
max_pitch=constants.MAX_MIDI_PITCH,
min_frame_occupancy_for_label=0.0,
onset_mode='length_ms',
onset_length_ms=32.,
onset_delay_ms=0.)
length = data.wav_to_num_frames(
wav_data, frames_per_second=data.hparams_frames_per_second(hparams))
return self._DataToInputs(spec, roll.active, roll.weights, length, filename,
truncated_length)