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 = note_sequence_pipelines.TimeChangeSplitter( name='TimeChangeSplitter_' + mode) quantizer = note_sequence_pipelines.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 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 = note_sequence_pipelines.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_pipeline.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 = note_sequence_pipelines.TimeChangeSplitter( name='TimeChangeSplitter_' + mode) quantizer = note_sequence_pipelines.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 = event_sequence_pipeline.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 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 = note_sequence_pipelines.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_pipeline.get_pipeline(self.config, eval_ratio=0.0) result = pipeline_inst.transform(note_sequence) self.assertEqual(expected_result, result)
def get_pipeline(config, min_events, max_events, eval_ratio): """Returns the Pipeline instance which creates the RNN dataset. Args: config: A PerformanceRnnConfig. min_events: Minimum number of events for an extracted sequence. max_events: Maximum number of events for an extracted sequence. eval_ratio: Fraction of input to set aside for evaluation set. Returns: A pipeline.Pipeline instance. """ # Stretch by -5%, -2.5%, 0%, 2.5%, and 5%. stretch_factors = [0.95, 0.975, 1.0, 1.025, 1.05] # Transpose no more than a major third. transposition_range = range(-3, 4) partitioner = pipelines_common.RandomPartition( music_pb2.NoteSequence, ['eval_performances', 'training_performances'], [eval_ratio]) dag = {partitioner: dag_pipeline.DagInput(music_pb2.NoteSequence)} for mode in ['eval', 'training']: sustain_pipeline = note_sequence_pipelines.SustainPipeline( name='SustainPipeline_' + mode) stretch_pipeline = note_sequence_pipelines.StretchPipeline( stretch_factors, name='StretchPipeline_' + mode) splitter = note_sequence_pipelines.Splitter(hop_size_seconds=30.0, name='Splitter_' + mode) quantizer = note_sequence_pipelines.Quantizer( steps_per_second=config.steps_per_second, name='Quantizer_' + mode) transposition_pipeline = note_sequence_pipelines.TranspositionPipeline( transposition_range, name='TranspositionPipeline_' + mode) perf_extractor = PerformanceExtractor( min_events=min_events, max_events=max_events, num_velocity_bins=config.num_velocity_bins, name='PerformanceExtractor_' + mode) encoder_pipeline = EncoderPipeline(config, name='EncoderPipeline_' + mode) dag[sustain_pipeline] = partitioner[mode + '_performances'] if mode == 'eval': # No stretching in eval. dag[splitter] = sustain_pipeline else: dag[stretch_pipeline] = sustain_pipeline dag[splitter] = stretch_pipeline dag[quantizer] = splitter if mode == 'eval': # No transposition in eval. dag[perf_extractor] = quantizer else: dag[transposition_pipeline] = quantizer dag[perf_extractor] = transposition_pipeline dag[encoder_pipeline] = perf_extractor dag[dag_pipeline.DagOutput(mode + '_performances')] = encoder_pipeline 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 = note_sequence_pipelines.TimeChangeSplitter( name='TimeChangeSplitter_' + mode) quantizer = note_sequence_pipelines.Quantizer( steps_per_quarter=config.steps_per_quarter, 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=True, 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, eval_ratio=0.0): 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 = note_sequence_pipelines.TimeChangeSplitter( name='TimeChangeSplitter_' + mode) repeat_sequence = RepeatSequence(min_duration=16, name='RepeatSequence_' + mode) transposition_pipeline = note_sequence_pipelines.TranspositionPipeline( (0, ), name='TranspositionPipeline_' + mode) quantizer = note_sequence_pipelines.Quantizer( steps_per_quarter=config.steps_per_quarter, 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=True, name='MelodyExtractor_' + mode) encoder_pipeline = EncoderPipeline(config, name='EncoderPipeline_' + mode) dag[time_change_splitter] = partitioner[mode + '_melodies'] dag[repeat_sequence] = time_change_splitter dag[quantizer] = repeat_sequence dag[transposition_pipeline] = quantizer dag[melody_extractor] = transposition_pipeline 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. """ # 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 = note_sequence_pipelines.TimeChangeSplitter( name='TimeChangeSplitter_' + mode) quantizer = note_sequence_pipelines.Quantizer( steps_per_quarter=config.steps_per_quarter, name='Quantizer_' + mode) transposition_pipeline = note_sequence_pipelines.TranspositionPipeline( transposition_range, name='TranspositionPipeline_' + mode) poly_extractor = PolyphonicSequenceExtractor(min_steps=min_steps, max_steps=max_steps, name='PolyExtractor_' + mode) encoder_pipeline = event_sequence_pipeline.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 testMelodyRNNPipeline(self): note_sequence = magenta.common.testing_lib.parse_test_proto( note_seq.NoteSequence, """ time_signatures: { numerator: 4 denominator: 4} tempos: { qpm: 120}""") note_seq.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)]) note_seq.testing_lib.add_chords_to_sequence(note_sequence, [('N.C.', 0.0), ('Am9', 5.0), ('D7', 10.0)]) quantizer = note_sequence_pipelines.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 = note_seq.ConditionalEventSequenceEncoderDecoder( note_seq.OneHotEventSequenceEncoderDecoder( note_seq.MajorMinorChordOneHotEncoding()), note_seq.OneHotEventSequenceEncoderDecoder( note_seq.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 = pipelines_common.make_sequence_example( *conditional_encoding.encode(lead_sheet.chords, lead_sheet.melody)) expected_result = { 'training_lead_sheets': [encoded], 'eval_lead_sheets': [] } pipeline_inst = improv_rnn_pipeline.get_pipeline(self.config, eval_ratio=0.0) result = pipeline_inst.transform(note_sequence) self.assertEqual(expected_result, result)
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. """ # Transpose up to a major third in either direction. transposition_range = list(range(-4, 5)) 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 = note_sequence_pipelines.TimeChangeSplitter( name='TimeChangeSplitter_' + mode) quantizer = note_sequence_pipelines.Quantizer( steps_per_quarter=config.steps_per_quarter, name='Quantizer_' + mode) transposition_pipeline = note_sequence_pipelines.TranspositionPipeline( transposition_range, name='TranspositionPipeline_' + mode) pianoroll_extractor = PianorollSequenceExtractor( min_steps=min_steps, max_steps=max_steps, name='PianorollExtractor_' + mode) encoder_pipeline = event_sequence_pipeline.EncoderPipeline( mm.PianorollSequence, config.encoder_decoder, name='EncoderPipeline_' + mode) dag[time_change_splitter] = partitioner[mode + '_pianoroll_tracks'] dag[quantizer] = time_change_splitter dag[transposition_pipeline] = quantizer dag[pianoroll_extractor] = transposition_pipeline dag[encoder_pipeline] = pianoroll_extractor dag[dag_pipeline.DagOutput(mode + '_pianoroll_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.quantize_note_sequence( note_sequence, steps_per_quarter) unit = note_sequence_pipelines.Quantizer(steps_per_quarter) self._unit_transform_test(unit, note_sequence, [expected_quantized_sequence])