def get_pipeline(melody_encoder_decoder):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
melody_encoder_decoder: A melodies_lib.MelodyEncoderDecoder object.
Returns:
A pipeline.Pipeline instance.
"""
quantizer = pipelines_common.Quantizer(steps_per_beat=4)
melody_extractor = pipelines_common.MonophonicMelodyExtractor(
min_bars=7,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False)
encoder_pipeline = EncoderPipeline(melody_encoder_decoder)
partitioner = pipelines_common.RandomPartition(
tf.train.SequenceExample, ['eval_melodies', 'training_melodies'],
[FLAGS.eval_ratio])
dag = {
quantizer: dag_pipeline.Input(music_pb2.NoteSequence),
melody_extractor: quantizer,
encoder_pipeline: melody_extractor,
partitioner: encoder_pipeline,
dag_pipeline.Output(): partitioner
}
return dag_pipeline.DAGPipeline(dag)
def testMelodyRNNPipeline(self):
FLAGS.eval_ratio = 0.0
note_sequence = testing_lib.parse_test_proto(
music_pb2.NoteSequence, """
time_signatures: {
numerator: 4
denominator: 4}
tempos: {
qpm: 120}""")
testing_lib.add_track(note_sequence, 0, [(12, 100, 0.00, 2.0),
(11, 55, 2.1, 5.0),
(40, 45, 5.1, 8.0),
(55, 120, 8.1, 11.0),
(53, 99, 11.1, 14.1)])
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
melody_extractor = pipelines_common.MonophonicMelodyExtractor(
min_bars=7,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False)
one_hot_encoder = melodies_lib.OneHotEncoderDecoder(0, 127, 0)
quantized = quantizer.transform(note_sequence)[0]
print quantized.tracks
melody = melody_extractor.transform(quantized)[0]
one_hot = one_hot_encoder.encode(melody)
print one_hot
expected_result = {'training_melodies': [one_hot], 'eval_melodies': []}
pipeline_inst = melody_rnn_create_dataset.get_pipeline(one_hot_encoder)
result = pipeline_inst.transform(note_sequence)
self.assertEqual(expected_result, result)
def testDrumsRNNPipeline(self):
note_sequence = magenta.common.testing_lib.parse_test_proto(
music_pb2.NoteSequence, """
time_signatures: {
numerator: 4
denominator: 4}
tempos: {
qpm: 120}""")
magenta.music.testing_lib.add_track_to_sequence(
note_sequence,
0, [(36, 100, 0.00, 2.0), (40, 55, 2.1, 5.0), (44, 80, 3.6, 5.0),
(41, 45, 5.1, 8.0), (64, 100, 6.6, 10.0), (55, 120, 8.1, 11.0),
(39, 110, 9.6, 9.7), (53, 99, 11.1, 14.1),
(51, 40, 12.6, 13.0), (55, 100, 14.1, 15.0),
(54, 90, 15.6, 17.0), (60, 100, 17.1, 18.0)],
is_drum=True)
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
drums_extractor = drum_pipelines.DrumsExtractor(min_bars=7,
gap_bars=1.0)
one_hot_encoding = magenta.music.OneHotEventSequenceEncoderDecoder(
magenta.music.MultiDrumOneHotEncoding())
quantized = quantizer.transform(note_sequence)[0]
drums = drums_extractor.transform(quantized)[0]
one_hot = one_hot_encoding.encode(drums)
expected_result = {
'training_drum_tracks': [one_hot],
'eval_drum_tracks': []
}
pipeline_inst = drums_rnn_create_dataset.get_pipeline(self.config,
eval_ratio=0.0)
result = pipeline_inst.transform(note_sequence)
self.assertEqual(expected_result, result)
def get_pipeline(config, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: A DrumsRnnConfig object.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence,
['eval_drum_tracks', 'training_drum_tracks'],
[eval_ratio])
dag = {partitioner: dag_pipeline.DagInput(music_pb2.NoteSequence)}
for mode in ['eval', 'training']:
time_change_splitter = pipelines_common.TimeChangeSplitter(
name='TimeChangeSplitter_' + mode)
quantizer = pipelines_common.Quantizer(
steps_per_quarter=config.steps_per_quarter, name='Quantizer_' + mode)
drums_extractor = drum_pipelines.DrumsExtractor(
min_bars=7, max_steps=512, gap_bars=1.0, name='DrumsExtractor_' + mode)
encoder_pipeline = encoder_decoder.EncoderPipeline(
magenta.music.DrumTrack, config.encoder_decoder,
name='EncoderPipeline_' + mode)
dag[time_change_splitter] = partitioner[mode + '_drum_tracks']
dag[quantizer] = time_change_splitter
dag[drums_extractor] = quantizer
dag[encoder_pipeline] = drums_extractor
dag[dag_pipeline.DagOutput(mode + '_drum_tracks')] = encoder_pipeline
return dag_pipeline.DAGPipeline(dag)
def testQuantizer(self):
steps_per_quarter = 4
note_sequence = common_testing_lib.parse_test_proto(
music_pb2.NoteSequence, """
time_signatures: {
numerator: 4
denominator: 4}
tempos: {
qpm: 60}""")
testing_lib.add_track_to_sequence(note_sequence, 0,
[(12, 100, 0.01, 10.0),
(11, 55, 0.22, 0.50),
(40, 45, 2.50, 3.50),
(55, 120, 4.0, 4.01),
(52, 99, 4.75, 5.0)])
expected_quantized_sequence = sequences_lib.QuantizedSequence()
expected_quantized_sequence.qpm = 60.0
expected_quantized_sequence.steps_per_quarter = steps_per_quarter
testing_lib.add_quantized_track_to_sequence(
expected_quantized_sequence, 0,
[(12, 100, 0, 40), (11, 55, 1, 2), (40, 45, 10, 14),
(55, 120, 16, 17), (52, 99, 19, 20)])
unit = pipelines_common.Quantizer(steps_per_quarter)
self._unit_transform_test(unit, note_sequence,
[expected_quantized_sequence])
def testMelodyRNNPipeline(self):
note_sequence = magenta.common.testing_lib.parse_test_proto(
music_pb2.NoteSequence,
"""
time_signatures: {
numerator: 4
denominator: 4}
tempos: {
qpm: 120}""")
magenta.music.testing_lib.add_track_to_sequence(
note_sequence, 0,
[(12, 100, 0.00, 2.0), (11, 55, 2.1, 5.0), (40, 45, 5.1, 8.0),
(55, 120, 8.1, 11.0), (53, 99, 11.1, 14.1)])
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
melody_extractor = melody_pipelines.MelodyExtractor(
min_bars=7, min_unique_pitches=5, gap_bars=1.0,
ignore_polyphonic_notes=False)
one_hot_encoding = magenta.music.OneHotEventSequenceEncoderDecoder(
magenta.music.MelodyOneHotEncoding(
self.config.min_note, self.config.max_note))
quantized = quantizer.transform(note_sequence)[0]
melody = melody_extractor.transform(quantized)[0]
melody.squash(
self.config.min_note,
self.config.max_note,
self.config.transpose_to_key)
one_hot = one_hot_encoding.encode(melody)
expected_result = {'training_melodies': [one_hot], 'eval_melodies': []}
pipeline_inst = melody_rnn_create_dataset.get_pipeline(self.config,
eval_ratio=0.0)
result = pipeline_inst.transform(note_sequence)
self.assertEqual(expected_result, result)
def testMelodyRNNPipeline(self):
note_sequence = testing_lib.parse_test_proto(
music_pb2.NoteSequence,
"""
time_signatures: {
numerator: 4
denominator: 4}
tempos: {
bpm: 120}""")
testing_lib.add_track(
note_sequence, 0,
[(12, 100, 0.01, 10.0), (11, 55, 0.22, 0.50), (40, 45, 2.50, 3.50),
(55, 120, 4.0, 4.01), (52, 99, 4.75, 5.0)])
quantizer = pipelines_common.Quantizer(steps_per_beat=4)
melody_extractor = pipelines_common.MonophonicMelodyExtractor(
min_bars=7, min_unique_pitches=5,
gap_bars=1.0)
one_hot_encoder = melody_rnn_create_dataset.OneHotEncoder()
quantized = quantizer.transform(note_sequence)[0]
melody = melody_extractor.transform(quantized)[0]
one_hot = one_hot_encoder.transform(melody)[0]
expected_result = {'melody_rnn_train': [one_hot], 'melody_rnn_eval': []}
pipeline_inst = melody_rnn_create_dataset.MelodyRNNPipeline(eval_ratio=0)
result = pipeline_inst.transform(note_sequence)
self.assertEqual(expected_result, result)
def get_pipeline(config, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: A DrumsRnnConfig object.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
drums_extractor_train = drum_pipelines.DrumsExtractor(
min_bars=7, max_steps=512, gap_bars=1.0, name='DrumsExtractorTrain')
drums_extractor_eval = drum_pipelines.DrumsExtractor(
min_bars=7, max_steps=512, gap_bars=1.0, name='DrumsExtractorEval')
encoder_pipeline_train = EncoderPipeline(config,
name='EncoderPipelineTrain')
encoder_pipeline_eval = EncoderPipeline(config, name='EncoderPipelineEval')
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence, ['eval_drum_tracks', 'training_drum_tracks'],
[eval_ratio])
dag = {
quantizer: dag_pipeline.Input(music_pb2.NoteSequence),
partitioner: quantizer,
drums_extractor_train: partitioner['training_drum_tracks'],
drums_extractor_eval: partitioner['eval_drum_tracks'],
encoder_pipeline_train: drums_extractor_train,
encoder_pipeline_eval: drums_extractor_eval,
dag_pipeline.Output('training_drum_tracks'): encoder_pipeline_train,
dag_pipeline.Output('eval_drum_tracks'): encoder_pipeline_eval
}
return dag_pipeline.DAGPipeline(dag)
def get_pipeline(config, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: A MelodyRnnConfig object.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
A id_pipeline.IDPipeline instance.
"""
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
melody_extractor = melody_pipelines.MelodyExtractor(
min_bars=7,
max_steps=512,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False)
id_pipeline = pipelines_common.IDPipeline()
encoder_pipeline = EncoderPipeline(config)
partitioner = pipelines_common.RandomPartition(
tf.train.SequenceExample, ['eval_melodies', 'training_melodies'],
[eval_ratio])
dag = {
quantizer: dag_pipeline.DagInput(music_pb2.NoteSequence),
melody_extractor: quantizer,
id_pipeline: melody_extractor,
encoder_pipeline: id_pipeline,
partitioner: encoder_pipeline,
dag_pipeline.DagOutput(): partitioner
}
return dag_pipeline.DAGPipeline(dag), id_pipeline
def midi_files_to_sequence_proto(midi_files, batch_size, input_size):
all_sequences = filter(lambda x: x != None, [
midi_file_to_sequence_proto(midi_file, batch_size, input_size)
for midi_file in midi_files
])
examples = []
#print("All our events are: ", all_events)
unit = melody_pipelines.MelodyExtractor(min_bars=1,
min_unique_pitches=1,
gap_bars=1)
melody_extractor = melody_pipelines.MelodyExtractor(
min_bars=7,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False)
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
one_hot_encoding = magenta.music.OneHotEventSequenceEncoderDecoder(
magenta.music.MelodyOneHotEncoding(0, 128))
for note_sequence in all_sequences:
#quantized_sequence = quantize_note_sequence(
# note_sequence, steps_per_quarter=1)
#quantized_sequence = mm.quantize_note_sequence(note_sequence, steps_per_quarter=1)
#outputs = unit.transform(quantized_sequence)
#single_quant = quantizer.transform(note_sequence)
#print("single quant seq is: ", single_quant)
# quantized = quantizer.transform(note_sequence)
#print("single quant is: ", single_quant)
single_quant = note_sequence
melody = melody_extractor.transform(single_quant)
print("outputs/melody is ", outputs)
#melody = outputs
# self.config.min_note,
# self.config.max_note,
# self.config.transpose_to_key)
melody.squash(0, 128, 0)
one_hot = one_hot_encoding.encode(melody)
examples.append(one_hot)
#seq_example =
#seq_example = make_sequence_example(inputs, labels)
#examples.append(seq_example)
# melody = melodies_lib.Melody(events.notes)
# melody.squash(0,128,0)
# examples.append(self.med.encode(melody))
print("done with a batch!!!")
return get_padded_batch(examples, batch_size, input_size)
def get_pipeline(config, steps_per_quarter, min_steps, max_steps, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: An EventSequenceRnnConfig.
steps_per_quarter: How many steps per quarter to use when quantizing.
min_steps: Minimum number of steps for an extracted sequence.
max_steps: Maximum number of steps for an extracted sequence.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
quantizer = pipelines_common.Quantizer(steps_per_quarter=steps_per_quarter)
# Transpose up to a major third in either direction.
# Because our current dataset is Bach chorales, transposing more than a major
# third in either direction probably doesn't makes sense (e.g., because it is
# likely to exceed normal singing range).
transposition_range = range(-4, 5)
transposition_pipeline_train = sequences_lib.TranspositionPipeline(
transposition_range, name='TranspositionPipelineTrain')
transposition_pipeline_eval = sequences_lib.TranspositionPipeline(
transposition_range, name='TranspositionPipelineEval')
poly_extractor_train = PolyphonicSequenceExtractor(
min_steps=min_steps, max_steps=max_steps, name='PolyExtractorTrain')
poly_extractor_eval = PolyphonicSequenceExtractor(min_steps=min_steps,
max_steps=max_steps,
name='PolyExtractorEval')
encoder_pipeline_train = encoder_decoder.EncoderPipeline(
polyphony_lib.PolyphonicSequence,
config.encoder_decoder,
name='EncoderPipelineTrain')
encoder_pipeline_eval = encoder_decoder.EncoderPipeline(
polyphony_lib.PolyphonicSequence,
config.encoder_decoder,
name='EncoderPipelineEval')
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence, ['eval_poly_tracks', 'training_poly_tracks'],
[eval_ratio])
dag = {
quantizer: dag_pipeline.DagInput(music_pb2.NoteSequence),
partitioner: quantizer,
transposition_pipeline_train: partitioner['training_poly_tracks'],
transposition_pipeline_eval: partitioner['eval_poly_tracks'],
poly_extractor_train: transposition_pipeline_train,
poly_extractor_eval: transposition_pipeline_eval,
encoder_pipeline_train: poly_extractor_train,
encoder_pipeline_eval: poly_extractor_eval,
dag_pipeline.DagOutput('training_poly_tracks'): encoder_pipeline_train,
dag_pipeline.DagOutput('eval_poly_tracks'): encoder_pipeline_eval
}
return dag_pipeline.DAGPipeline(dag)
def get_pipeline(config, steps_per_quarter, min_steps, max_steps, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: An EventSequenceRnnConfig.
steps_per_quarter: How many steps per quarter to use when quantizing.
min_steps: Minimum number of steps for an extracted sequence.
max_steps: Maximum number of steps for an extracted sequence.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
# Transpose up to a major third in either direction.
# Because our current dataset is Bach chorales, transposing more than a major
# third in either direction probably doesn't makes sense (e.g., because it is
# likely to exceed normal singing range).
transposition_range = range(-4, 5)
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence, ['eval_poly_tracks', 'training_poly_tracks'],
[eval_ratio])
dag = {partitioner: dag_pipeline.DagInput(music_pb2.NoteSequence)}
for mode in ['eval', 'training']:
time_change_splitter = pipelines_common.TimeChangeSplitter(
name='TimeChangeSplitter_' + mode)
quantizer = pipelines_common.Quantizer(
steps_per_quarter=steps_per_quarter, name='Quantizer_' + mode)
transposition_pipeline = sequences_lib.TranspositionPipeline(
transposition_range, name='TranspositionPipeline_' + mode)
poly_extractor = PolyphonicSequenceExtractor(min_steps=min_steps,
max_steps=max_steps,
name='PolyExtractor_' +
mode)
encoder_pipeline = encoder_decoder.EncoderPipeline(
polyphony_lib.PolyphonicSequence,
config.encoder_decoder,
name='EncoderPipeline_' + mode)
dag[time_change_splitter] = partitioner[mode + '_poly_tracks']
dag[quantizer] = time_change_splitter
dag[transposition_pipeline] = quantizer
dag[poly_extractor] = transposition_pipeline
dag[encoder_pipeline] = poly_extractor
dag[dag_pipeline.DagOutput(mode + '_poly_tracks')] = encoder_pipeline
return dag_pipeline.DAGPipeline(dag)
def get_pipeline(config, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: An ImprovRnnConfig object.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
all_transpositions = config.transpose_to_key is None
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
lead_sheet_extractor_train = lead_sheet_pipelines.LeadSheetExtractor(
min_bars=7,
max_steps=512,
min_unique_pitches=3,
gap_bars=1.0,
ignore_polyphonic_notes=False,
all_transpositions=all_transpositions,
name='LeadSheetExtractorTrain')
lead_sheet_extractor_eval = lead_sheet_pipelines.LeadSheetExtractor(
min_bars=7,
max_steps=512,
min_unique_pitches=3,
gap_bars=1.0,
ignore_polyphonic_notes=False,
all_transpositions=all_transpositions,
name='LeadSheetExtractorEval')
encoder_pipeline_train = EncoderPipeline(config,
name='EncoderPipelineTrain')
encoder_pipeline_eval = EncoderPipeline(config, name='EncoderPipelineEval')
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence, ['eval_lead_sheets', 'training_lead_sheets'],
[eval_ratio])
dag = {
quantizer: dag_pipeline.DagInput(music_pb2.NoteSequence),
partitioner: quantizer,
lead_sheet_extractor_train: partitioner['training_lead_sheets'],
lead_sheet_extractor_eval: partitioner['eval_lead_sheets'],
encoder_pipeline_train: lead_sheet_extractor_train,
encoder_pipeline_eval: lead_sheet_extractor_eval,
dag_pipeline.DagOutput('training_lead_sheets'): encoder_pipeline_train,
dag_pipeline.DagOutput('eval_lead_sheets'): encoder_pipeline_eval
}
return dag_pipeline.DAGPipeline(dag)
def testMelodyRNNPipeline(self):
note_sequence = magenta.common.testing_lib.parse_test_proto(
music_pb2.NoteSequence, """
time_signatures: {
numerator: 4
denominator: 4}
tempos: {
qpm: 120}""")
magenta.music.testing_lib.add_track_to_sequence(
note_sequence, 0, [(12, 100, 0.00, 2.0), (11, 55, 2.1, 5.0),
(40, 45, 5.1, 8.0), (55, 120, 8.1, 11.0),
(53, 99, 11.1, 14.1)])
magenta.music.testing_lib.add_chords_to_sequence(
note_sequence, [('N.C.', 0.0), ('Am9', 5.0), ('D7', 10.0)])
quantizer = pipelines_common.Quantizer(steps_per_quarter=4)
lead_sheet_extractor = lead_sheet_pipelines.LeadSheetExtractor(
min_bars=7,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False,
all_transpositions=False)
conditional_encoding = magenta.music.ConditionalEventSequenceEncoderDecoder(
magenta.music.OneHotEventSequenceEncoderDecoder(
magenta.music.MajorMinorChordOneHotEncoding()),
magenta.music.OneHotEventSequenceEncoderDecoder(
magenta.music.MelodyOneHotEncoding(self.config.min_note,
self.config.max_note)))
quantized = quantizer.transform(note_sequence)[0]
lead_sheet = lead_sheet_extractor.transform(quantized)[0]
lead_sheet.squash(self.config.min_note, self.config.max_note,
self.config.transpose_to_key)
encoded = conditional_encoding.encode(lead_sheet.chords,
lead_sheet.melody)
expected_result = {
'training_lead_sheets': [encoded],
'eval_lead_sheets': []
}
pipeline_inst = improv_rnn_create_dataset.get_pipeline(self.config,
eval_ratio=0.0)
result = pipeline_inst.transform(note_sequence)
self.assertEqual(expected_result, result)
def __init__(self, melody_encoder_decoder, eval_ratio):
self.training_set_name = 'training_melodies'
self.eval_set_name = 'eval_melodies'
super(MelodyRNNPipeline,
self).__init__(input_type=music_pb2.NoteSequence,
output_type={
self.training_set_name:
tf.train.SequenceExample,
self.eval_set_name: tf.train.SequenceExample
})
self.eval_ratio = eval_ratio
self.quantizer = pipelines_common.Quantizer(steps_per_beat=4)
self.melody_extractor = pipelines_common.MonophonicMelodyExtractor(
min_bars=7,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False)
self.encoder_unit = EncoderPipeline(melody_encoder_decoder)
self.stats_dict = {}
def get_pipeline(config, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: An ImprovRnnConfig object.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
all_transpositions = config.transpose_to_key is None
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence, ['eval_lead_sheets', 'training_lead_sheets'],
[eval_ratio])
dag = {partitioner: dag_pipeline.DagInput(music_pb2.NoteSequence)}
for mode in ['eval', 'training']:
time_change_splitter = pipelines_common.TimeChangeSplitter(
name='TimeChangeSplitter_' + mode)
quantizer = pipelines_common.Quantizer(
steps_per_quarter=config.steps_per_quarter,
name='Quantizer_' + mode)
lead_sheet_extractor = lead_sheet_pipelines.LeadSheetExtractor(
min_bars=7,
max_steps=512,
min_unique_pitches=3,
gap_bars=1.0,
ignore_polyphonic_notes=False,
all_transpositions=all_transpositions,
name='LeadSheetExtractor_' + mode)
encoder_pipeline = EncoderPipeline(config,
name='EncoderPipeline_' + mode)
dag[time_change_splitter] = partitioner[mode + '_lead_sheets']
dag[quantizer] = time_change_splitter
dag[lead_sheet_extractor] = quantizer
dag[encoder_pipeline] = lead_sheet_extractor
dag[dag_pipeline.DagOutput(mode + '_lead_sheets')] = encoder_pipeline
return dag_pipeline.DAGPipeline(dag)
def get_pipeline(config, steps_per_quarter, min_steps, max_steps, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: An EventSequenceRnnConfig.
steps_per_quarter: How many steps per quarter to use when quantizing.
min_steps: Minimum number of steps for an extracted sequence.
max_steps: Maximum number of steps for an extracted sequence.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
quantizer = pipelines_common.Quantizer(steps_per_quarter=steps_per_quarter)
poly_extractor_train = PolyphonicSequenceExtractor(
min_steps=min_steps, max_steps=max_steps, name='PolyExtractorTrain')
poly_extractor_eval = PolyphonicSequenceExtractor(
min_steps=min_steps, max_steps=max_steps, name='PolyExtractorEval')
encoder_pipeline_train = encoder_decoder.EncoderPipeline(
polyphony_lib.PolyphonicSequence, config.encoder_decoder,
name='EncoderPipelineTrain')
encoder_pipeline_eval = encoder_decoder.EncoderPipeline(
polyphony_lib.PolyphonicSequence, config.encoder_decoder,
name='EncoderPipelineEval')
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence,
['eval_poly_tracks', 'training_poly_tracks'],
[eval_ratio])
dag = {quantizer: dag_pipeline.DagInput(music_pb2.NoteSequence),
partitioner: quantizer,
poly_extractor_train: partitioner['training_poly_tracks'],
poly_extractor_eval: partitioner['eval_poly_tracks'],
encoder_pipeline_train: poly_extractor_train,
encoder_pipeline_eval: poly_extractor_eval,
dag_pipeline.DagOutput('training_poly_tracks'): encoder_pipeline_train,
dag_pipeline.DagOutput('eval_poly_tracks'): encoder_pipeline_eval}
return dag_pipeline.DAGPipeline(dag)
def get_pipeline(config, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: A MelodyRnnConfig object.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence, ['eval_melodies', 'training_melodies'],
[eval_ratio])
dag = {partitioner: dag_pipeline.DagInput(music_pb2.NoteSequence)}
for mode in ['eval', 'training']:
time_change_splitter = pipelines_common.TimeChangeSplitter(
name='TimeChangeSplitter_' + mode)
quantizer = pipelines_common.Quantizer(steps_per_quarter=4,
name='Quantizer_' + mode)
melody_extractor = melody_pipelines.MelodyExtractor(
min_bars=7,
max_steps=512,
min_unique_pitches=5,
gap_bars=1.0,
ignore_polyphonic_notes=False,
name='MelodyExtractor_' + mode)
encoder_pipeline = EncoderPipeline(config,
name='EncoderPipeline_' + mode)
dag[time_change_splitter] = partitioner[mode + '_melodies']
dag[quantizer] = time_change_splitter
dag[melody_extractor] = quantizer
dag[encoder_pipeline] = melody_extractor
dag[dag_pipeline.DagOutput(mode + '_melodies')] = encoder_pipeline
return dag_pipeline.DAGPipeline(dag)
def get_pipeline(config, min_steps, max_steps, eval_ratio):
"""Returns the Pipeline instance which creates the RNN dataset.
Args:
config: An EventSequenceRnnConfig.
min_steps: Minimum number of steps for an extracted sequence.
max_steps: Maximum number of steps for an extracted sequence.
eval_ratio: Fraction of input to set aside for evaluation set.
Returns:
A pipeline.Pipeline instance.
"""
partitioner = pipelines_common.RandomPartition(
music_pb2.NoteSequence,
['eval_pianoroll_tracks', 'training_pianoroll_tracks'],
[eval_ratio])
dag = {partitioner: dag_pipeline.DagInput(music_pb2.NoteSequence)}
for mode in ['eval', 'training']:
time_change_splitter = pipelines_common.TimeChangeSplitter(
name='TimeChangeSplitter_' + mode)
quantizer = pipelines_common.Quantizer(
steps_per_quarter=config.steps_per_quarter, name='Quantizer_' + mode)
pianoroll_extractor = PianorollSequenceExtractor(
min_steps=min_steps, max_steps=max_steps,
name='PianorollExtractor_' + mode)
encoder_pipeline = mm.EncoderPipeline(
mm.PianorollSequence, config.encoder_decoder,
name='EncoderPipeline_' + mode)
dag[time_change_splitter] = partitioner[mode + '_pianoroll_tracks']
dag[quantizer] = time_change_splitter
dag[pianoroll_extractor] = quantizer
dag[encoder_pipeline] = pianoroll_extractor
dag[dag_pipeline.DagOutput(mode + '_pianoroll_tracks')] = encoder_pipeline
return dag_pipeline.DAGPipeline(dag)
