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 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 setUp(self):
super().setUp()
self.config = events_rnn_model.EventSequenceRnnConfig(
None,
note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.MultiDrumOneHotEncoding()),
contrib_training.HParams())
def setUp(self):
super(PerformancePipelineTest, self).setUp()
self.config = performance_model.PerformanceRnnConfig(
None,
note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.PerformanceOneHotEncoding()),
contrib_training.HParams())
def setUp(self):
super().setUp()
self.config = events_rnn_model.EventSequenceRnnConfig(
None,
note_seq.OneHotEventSequenceEncoderDecoder(
polyphony_encoder_decoder.PolyphonyOneHotEncoding()),
contrib_training.HParams())
def testDrumsRNNPipeline(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, [(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 = note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.MultiDrumOneHotEncoding())
quantized = quantizer.transform(note_sequence)[0]
drums = drums_extractor.transform(quantized)[0]
one_hot = pipelines_common.make_sequence_example(
*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 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 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 one_hot_melody_encoder_decoder(min_note, max_note):
"""Return a OneHotEventSequenceEncoderDecoder 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 OneHotEventSequenceEncoderDecoder.
"""
return note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.MelodyOneHotEncoding(min_note, max_note))
def setUp(self):
self._sequence_file = tempfile.NamedTemporaryFile(
prefix='EventSequenceRNNGraphTest')
self.config = events_rnn_model.EventSequenceRnnConfig(
None,
note_seq.OneHotEventSequenceEncoderDecoder(
testing_lib.TrivialOneHotEncoding(12)),
contrib_training.HParams(batch_size=128,
rnn_layer_sizes=[128, 128],
dropout_keep_prob=0.5,
clip_norm=5,
learning_rate=0.01))
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)
# open hi-hat
[46, 67, 72, 74, 79, 81, 26,
49, 52, 55, 57, 58, # crash
51, 53, 59, 82], # ride
]
# Default configurations.
default_configs = {
'one_drum':
events_rnn_model.EventSequenceRnnConfig(
generator_pb2.GeneratorDetails(
id='one_drum', description='Drums RNN with 2-state encoding.'),
note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.MultiDrumOneHotEncoding(
[[39] + # use hand clap as default when decoding
list(range(note_seq.MIN_MIDI_PITCH, 39)) +
list(range(39, note_seq.MAX_MIDI_PITCH + 1))])),
contrib_training.HParams(
batch_size=128,
rnn_layer_sizes=[128, 128],
dropout_keep_prob=0.5,
clip_norm=5,
learning_rate=0.001),
steps_per_quarter=2),
'drum_kit':
events_rnn_model.EventSequenceRnnConfig(
generator_pb2.GeneratorDetails(
id='drum_kit',
description='Drums RNN with multiple drums and binary counters.'
),
control_encoder, encoder_decoder)
super(PerformanceRnnConfig, self).__init__(
details, encoder_decoder, hparams)
self.num_velocity_bins = num_velocity_bins
self.control_signals = control_signals
self.optional_conditioning = optional_conditioning
self.note_performance = note_performance
default_configs = {
'performance':
PerformanceRnnConfig(
generator_pb2.GeneratorDetails(
id='performance', description='Performance RNN'),
note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.PerformanceOneHotEncoding()),
contrib_training.HParams(
batch_size=64,
rnn_layer_sizes=[512, 512, 512],
dropout_keep_prob=1.0,
clip_norm=3,
learning_rate=0.001)),
'performance_with_dynamics':
PerformanceRnnConfig(
generator_pb2.GeneratorDetails(
id='performance_with_dynamics',
description='Performance RNN with dynamics'),
note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.PerformanceOneHotEncoding(num_velocity_bins=32)),
contrib_training.HParams(
batch_size=64,
branch_factor,
steps_per_iteration,
modify_events_callback=modify_events_callback)
def polyphonic_sequence_log_likelihood(self, sequence):
"""Evaluate the log likelihood of a polyphonic sequence.
Args:
sequence: The PolyphonicSequence object for which to evaluate the log
likelihood.
Returns:
The log likelihood of `sequence` under this model.
"""
return self._evaluate_log_likelihood([sequence])[0]
default_configs = {
'polyphony':
events_rnn_model.EventSequenceRnnConfig(
generator_pb2.GeneratorDetails(id='polyphony',
description='Polyphonic RNN'),
note_seq.OneHotEventSequenceEncoderDecoder(
polyphony_encoder_decoder.PolyphonyOneHotEncoding()),
contrib_training.HParams(batch_size=64,
rnn_layer_sizes=[256, 256, 256],
dropout_keep_prob=0.5,
clip_norm=5,
learning_rate=0.001)),
}
self.min_note = min_note
self.max_note = max_note
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.'),
raise ValueError('transpose_to_key must be >= 0 and <= 11. '
'transpose_to_key is %d.' % transpose_to_key)
self.min_note = min_note
self.max_note = max_note
self.transpose_to_key = transpose_to_key
# Default configurations.
default_configs = {
'basic_rnn':
MelodyRnnConfig(
generator_pb2.GeneratorDetails(
id='basic_rnn', description='Melody RNN with one-hot encoding.'),
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=[128, 128],
dropout_keep_prob=0.5,
clip_norm=5,
learning_rate=0.001)),
'mono_rnn':
MelodyRnnConfig(generator_pb2.GeneratorDetails(
id='mono_rnn', description='Monophonic RNN with one-hot encoding.'),
note_seq.OneHotEventSequenceEncoderDecoder(
note_seq.MelodyOneHotEncoding(min_note=0,
max_note=128)),
contrib_training.HParams(batch_size=128,
rnn_layer_sizes=[128, 128],
dropout_keep_prob=0.5,
