def testToNoteSequenceMultipleChunksWithChords(self):
sequence = copy.deepcopy(self.sequence)
testing_lib.add_track_to_sequence(sequence, 0, [
(64, 100, 0, 2),
(60, 100, 0, 4),
(67, 100, 2, 4),
(62, 100, 4, 6),
(59, 100, 4, 8),
(67, 100, 6, 8),
])
testing_lib.add_track_to_sequence(sequence,
1, [
(40, 100, 0, 0.125),
(50, 100, 0, 0.125),
(50, 100, 2, 2.125),
(40, 100, 4, 4.125),
(50, 100, 4, 4.125),
(50, 100, 6, 6.125),
],
is_drum=True)
testing_lib.add_chords_to_sequence(sequence, [('C', 0), ('G', 4)])
converter = data_hierarchical.MultiInstrumentPerformanceConverter(
hop_size_bars=4,
chunk_size_bars=2,
chord_encoding=note_seq.MajorMinorChordOneHotEncoding())
tensors = converter.to_tensors(sequence)
self.assertEqual(1, len(tensors.outputs))
sequences = converter.from_tensors(tensors.outputs, tensors.controls)
self.assertEqual(1, len(sequences))
self.assertProtoEquals(sequence, sequences[0])
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)