def prime_model(self): """Primes the model with its default midi primer.""" with self.graph.as_default(): tf.logging.debug('Priming the model with MIDI file %s', self.midi_primer) # Convert primer Melody to model inputs. encoder = note_seq.OneHotEventSequenceEncoderDecoder( note_seq.MelodyOneHotEncoding(min_note=rl_tuner_ops.MIN_NOTE, max_note=rl_tuner_ops.MAX_NOTE)) primer_input, _ = encoder.encode(self.primer) # Run model over primer sequence. primer_input_batch = np.tile([primer_input], (self.batch_size, 1, 1)) self.state_value, softmax = self.session.run( [self.state_tensor, self.softmax], feed_dict={ self.initial_state: self.state_value, self.melody_sequence: primer_input_batch, self.lengths: np.full(self.batch_size, len(self.primer), dtype=int) }) priming_output = softmax[-1, :] self.priming_note = self.get_note_from_softmax(priming_output)
def convert_to_note_events(one_hot_events): _, result = np.where(one_hot_events == 1.) encoder_decoder = note_seq.MelodyOneHotEncoding(BASIC_DEFAULT_MIN_NOTE, BASIC_DEFAULT_MAX_NOTE) result = np.array( [encoder_decoder.decode_event(event) for event in result]) return result
def setUp(self): super().setUp() self.config = melody_rnn_model.MelodyRnnConfig( None, note_seq.OneHotEventSequenceEncoderDecoder( note_seq.MelodyOneHotEncoding(0, 127)), contrib_training.HParams(), min_note=0, max_note=127, transpose_to_key=0)
def lookback_melody_encoder_decoder(min_note, max_note): """Return a LookbackEventSequenceEncoderDecoder for melodies. Args: min_note: The minimum midi pitch the encoded melodies can have. max_note: The maximum midi pitch (exclusive) the encoded melodies can have. Returns: A melody LookbackEventSequenceEncoderDecoder. """ return note_seq.LookbackEventSequenceEncoderDecoder( note_seq.MelodyOneHotEncoding(min_note, max_note))
def setUp(self): super().setUp() self.config = improv_rnn_model.ImprovRnnConfig( None, note_seq.ConditionalEventSequenceEncoderDecoder( note_seq.OneHotEventSequenceEncoderDecoder( note_seq.MajorMinorChordOneHotEncoding()), note_seq.OneHotEventSequenceEncoderDecoder( note_seq.MelodyOneHotEncoding(0, 127))), contrib_training.HParams(), min_note=0, max_note=127, transpose_to_key=0)
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 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)]) 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 = note_seq.OneHotEventSequenceEncoderDecoder( note_seq.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 = pipelines_common.make_sequence_example( *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 __init__(self, min_pitch, max_pitch): self._encoding = note_seq.MelodyOneHotEncoding(min_note=min_pitch, max_note=max_pitch + 1)
self.transpose_to_key = transpose_to_key # Default configurations. default_configs = { 'basic_improv': ImprovRnnConfig( generator_pb2.GeneratorDetails( id='basic_improv', description='Basic melody-given-chords RNN with one-hot triad ' 'encoding for chords.'), note_seq.ConditionalEventSequenceEncoderDecoder( note_seq.OneHotEventSequenceEncoderDecoder( note_seq.TriadChordOneHotEncoding()), note_seq.OneHotEventSequenceEncoderDecoder( note_seq.MelodyOneHotEncoding(min_note=DEFAULT_MIN_NOTE, max_note=DEFAULT_MAX_NOTE))), contrib_training.HParams(batch_size=128, rnn_layer_sizes=[64, 64], dropout_keep_prob=0.5, clip_norm=5, learning_rate=0.001)), 'attention_improv': ImprovRnnConfig( generator_pb2.GeneratorDetails( id='attention_improv', description= 'Melody-given-chords RNN with one-hot triad encoding for ' 'chords, attention, and binary counters.'), note_seq.ConditionalEventSequenceEncoderDecoder( note_seq.OneHotEventSequenceEncoderDecoder( note_seq.TriadChordOneHotEncoding()),