def build_bach_beat(dataset_manager, batch_size, subdivision, sequences_size, test_bool):
metadatas = [
TickMetadata(subdivision=subdivision),
FermataMetadata(),
KeyMetadata()
]
name = 'bach_chorales'
if test_bool:
name += '_test'
bach_chorales_dataset: ChoraleBeatsDataset = dataset_manager.get_dataset(
name=name,
voice_ids=[0, 1, 2, 3],
metadatas=metadatas,
sequences_size=sequences_size,
subdivision=subdivision
)
(train_dataloader,
val_dataloader,
test_dataloader) = bach_chorales_dataset.data_loaders(
batch_size=batch_size,
cache_dir=dataset_manager.cache_dir,
split=(0.85, 0.10)
)
print('Num Train Batches: ', len(train_dataloader))
print('Num Valid Batches: ', len(val_dataloader))
print('Num Test Batches: ', len(test_dataloader))
def main(note_embedding_dim, metadata_embedding_dim, num_encoder_layers,
encoder_hidden_size, encoder_dropout_prob, latent_space_dim,
num_decoder_layers, decoder_hidden_size, decoder_dropout_prob,
has_metadata, batch_size, num_epochs, train, plot, log, lr):
dataset_manager = DatasetManager()
metadatas = [
BeatMarkerMetadata(subdivision=6),
TickMetadata(subdivision=6)
]
mvae_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
mvae_test_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': False
}
folk_dataset: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **mvae_train_kwargs)
folk_dataset_test: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **mvae_test_kwargs)
model = MeasureVAE(dataset=folk_dataset,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_encoder_layers=num_encoder_layers,
encoder_hidden_size=encoder_hidden_size,
encoder_dropout_prob=encoder_dropout_prob,
latent_space_dim=latent_space_dim,
num_decoder_layers=num_decoder_layers,
decoder_hidden_size=decoder_hidden_size,
decoder_dropout_prob=decoder_dropout_prob,
has_metadata=has_metadata)
if train:
if torch.cuda.is_available():
model.cuda()
trainer = VAETrainer(dataset=folk_dataset, model=model, lr=lr)
trainer.train_model(batch_size=batch_size,
num_epochs=num_epochs,
plot=plot,
log=log)
else:
model.load()
model.cuda()
model.eval()
tester = VAETester(dataset=folk_dataset_test, model=model)
tester.test_model()
def main(note_embedding_dim,
meta_embedding_dim,
num_layers,
lstm_hidden_size,
dropout_lstm,
linear_hidden_size,
batch_size,
num_epochs,
train,
num_iterations,
sequence_length_ticks):
dataset_manager = DatasetManager()
metadatas = [
FermataMetadata(),
TickMetadata(subdivision=4),
KeyMetadata()
]
chorale_dataset_kwargs = {
'voice_ids': [0, 1, 2, 3],
'metadatas': metadatas,
'sequences_size': 8,
'subdivision': 4
}
bach_chorales_dataset = dataset_manager.get_dataset(
name='bach_chorales',
**chorale_dataset_kwargs
)
dataset = bach_chorales_dataset
deepbach = DeepBach(
dataset=dataset,
note_embedding_dim=note_embedding_dim,
meta_embedding_dim=meta_embedding_dim,
num_layers=num_layers,
lstm_hidden_size=lstm_hidden_size,
dropout_lstm=dropout_lstm,
linear_hidden_size=linear_hidden_size
)
if train:
deepbach.train(batch_size=batch_size,
num_epochs=num_epochs)
else:
deepbach.load()
deepbach.cuda()
print('Generation')
score, tensor_chorale, tensor_metadata = deepbach.generation(
num_iterations=num_iterations,
length=sequence_length_ticks,
)
score.write('midi', fp = 'test.mid')
def main(
note_embedding_dim,
meta_embedding_dim,
num_layers,
lstm_hidden_size,
dropout_lstm,
input_dropout,
linear_hidden_size,
batch_size,
num_epochs,
train,
no_metadata,
):
metadatas = [
TickMetadata(subdivision=4),
]
dataset_manager = DatasetManager()
chorale_dataset_kwargs = {
'voice_ids': [0],
'metadatas': metadatas,
'sequences_size': 20,
'subdivision': 4
}
bach_chorales_dataset: ChoraleDataset = dataset_manager.get_dataset(
name='bach_chorales', **chorale_dataset_kwargs)
model = AnticipationRNN(
chorale_dataset=bach_chorales_dataset,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=meta_embedding_dim,
num_layers=num_layers,
num_lstm_constraints_units=lstm_hidden_size,
num_lstm_generation_units=lstm_hidden_size,
linear_hidden_size=linear_hidden_size,
dropout_prob=dropout_lstm,
dropout_input_prob=input_dropout,
unary_constraint=True,
no_metadata=no_metadata,
)
if train:
model.cuda()
model.train_model(batch_size=batch_size, num_epochs=num_epochs)
else:
model.load()
model.cuda()
print('Fill')
score, _, _ = model.fill(C3)
score.show()
def main(include_transpositions):
dataset_manager = DatasetManager()
print('step 1/3: prepare dataset')
metadatas = [FermataMetadata(), TickMetadata(subdivision=4), KeyMetadata()]
chorale_dataset_kwargs = {
'voice_ids': [0, 1, 2, 3],
'metadatas': metadatas,
'sequences_size': 8,
'subdivision': 4,
'include_transpositions': include_transpositions,
}
bach_chorales_dataset: ChoraleDataset = dataset_manager.get_dataset(
name='bach_chorales', **chorale_dataset_kwargs)
dataset = bach_chorales_dataset
get_pairs(dataset, model_ids=[5, 9])
def setup(self):
"""Load the model"""
# music21.environment.set("musicxmlPath", "/bin/true")
note_embedding_dim = 20
meta_embedding_dim = 20
num_layers = 2
lstm_hidden_size = 256
dropout_lstm = 0.5
linear_hidden_size = 256
batch_size = 256
num_epochs = 5
train = False
num_iterations = 500
sequence_length_ticks = 64
dataset_manager = DatasetManager()
metadatas = [FermataMetadata(), TickMetadata(subdivision=4), KeyMetadata()]
chorale_dataset_kwargs = {
"voice_ids": [0, 1, 2, 3],
"metadatas": metadatas,
"sequences_size": 8,
"subdivision": 4,
}
bach_chorales_dataset: ChoraleDataset = dataset_manager.get_dataset(
name="bach_chorales", **chorale_dataset_kwargs
)
dataset = bach_chorales_dataset
self.deepbach = DeepBach(
dataset=dataset,
note_embedding_dim=note_embedding_dim,
meta_embedding_dim=meta_embedding_dim,
num_layers=num_layers,
lstm_hidden_size=lstm_hidden_size,
dropout_lstm=dropout_lstm,
linear_hidden_size=linear_hidden_size,
)
self.deepbach.load()
# load fluidsynth fo rmidi 2 audio conversion
self.fs = FluidSynth()
def init_app(
note_embedding_dim,
meta_embedding_dim,
num_layers,
lstm_hidden_size,
dropout_lstm,
input_dropout,
linear_hidden_size,
):
metadatas = [
TickMetadata(subdivision=4),
]
dataset_manager = DatasetManager()
chorale_dataset_kwargs = {
'voice_ids': [0],
'metadatas': metadatas,
'sequences_size': 20,
'subdivision': 4
}
bach_chorales_dataset: ChoraleDataset = dataset_manager.get_dataset(
name='bach_chorales', **chorale_dataset_kwargs)
global model
model = AnticipationRNN(
chorale_dataset=bach_chorales_dataset,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=meta_embedding_dim,
num_layers=num_layers,
num_lstm_constraints_units=lstm_hidden_size,
num_lstm_generation_units=lstm_hidden_size,
linear_hidden_size=linear_hidden_size,
dropout_prob=dropout_lstm,
dropout_input_prob=input_dropout,
unary_constraint=True,
)
model.load()
model.cuda()
# launch the script
# accessible only locally:
app.run()
def build_folk(dataset_manager, batch_size, subdivision, sequences_size):
metadatas = [
BeatMarkerMetadata(subdivision=subdivision),
TickMetadata(subdivision=subdivision)
]
folk_dataset_kwargs = {
'metadatas': metadatas,
'sequences_size': sequences_size
}
folk_dataset: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars',
**folk_dataset_kwargs
)
(train_dataloader,
val_dataloader,
test_dataloader) = folk_dataset.data_loaders(
batch_size=batch_size,
split=(0.7, 0.2)
)
print('Num Train Batches: ', len(train_dataloader))
print('Num Valid Batches: ', len(val_dataloader))
print('Num Test Batches: ', len(test_dataloader))
def get_dataset(dataset_manager, dataset_type, subdivision, sequence_size,
velocity_quantization, max_transposition, num_heads,
per_head_dim, local_position_embedding_dim, block_attention,
group_instrument_per_section, nade, cpc_config_name,
double_conditioning, instrument_presence_in_encoder):
if dataset_type == 'bach':
if nade:
raise Exception(
'j ai l impression que nade c est nimps dans le data processor; check before using'
)
metadatas = [
FermataMetadata(),
TickMetadata(subdivision=subdivision),
KeyMetadata()
]
voices_ids = [0, 1, 2, 3]
if cpc_config_name is not None:
# notes to compute the first cpc code, we need to waste block_size tokens
cpc_model = init_cpc_model(cpc_config_name)
block_size = cpc_model.dataloader_generator.num_tokens_per_block // (
subdivision * len(voices_ids))
sequence_size += block_size
chorale_dataset_kwargs = {
'voice_ids': voices_ids,
'metadatas': metadatas,
'sequences_size': sequence_size,
'subdivision': subdivision,
}
dataset: ChoraleBeatsDataset = dataset_manager.get_dataset(
name='bach_chorales_beats', **chorale_dataset_kwargs)
if cpc_config_name is None:
processor_encoder = BachBeatsDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=True,
monophonic_flag=False,
nade_flag=nade)
processor_decoder = BachBeatsDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=False,
monophonic_flag=False,
nade_flag=nade)
else:
processor_encoder = BachBeatsCPCDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=True,
monophonic_flag=False,
nade_flag=nade,
cpc_model=cpc_model)
processor_decoder = BachBeatsCPCDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=False,
monophonic_flag=False,
nade_flag=nade,
cpc_model=cpc_model)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'bach_small':
metadatas = [
FermataMetadata(),
TickMetadata(subdivision=subdivision),
KeyMetadata()
]
voices_ids = [0, 1, 2, 3]
if cpc_config_name is not None:
# notes to compute the first cpc code, we need to waste block_size tokens
cpc_model = init_cpc_model(cpc_config_name)
num_tokens_per_block = cpc_model.dataloader_generator.num_tokens_per_block // (
subdivision * len(voices_ids))
sequence_size += num_tokens_per_block
chorale_dataset_kwargs = {
'voice_ids': voices_ids,
'metadatas': metadatas,
'sequences_size': sequence_size,
'subdivision': subdivision,
}
dataset: ChoraleBeatsDataset = dataset_manager.get_dataset(
name='bach_chorales_beats_test', **chorale_dataset_kwargs)
if cpc_config_name is None:
processor_encoder = BachBeatsDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=True,
monophonic_flag=False,
nade_flag=nade)
processor_decoder = BachBeatsDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=False,
monophonic_flag=False,
nade_flag=nade)
else:
processor_encoder = BachBeatsCPCDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=True,
monophonic_flag=False,
nade_flag=nade,
cpc_model=cpc_model)
processor_decoder = BachBeatsCPCDataProcessor(
dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8,
encoder_flag=False,
monophonic_flag=False,
nade_flag=nade,
cpc_model=cpc_model)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'lsdb':
# leadsheet_dataset_kwargs = {
# 'sequences_size': 24,
# }
# leadsheet_dataset_kwargs = {
# 'sequences_size': 32,
# }
leadsheet_dataset_kwargs = {
'sequences_size': 12,
}
dataset: LsdbDataset = dataset_manager.get_dataset(
name='lsdb', **leadsheet_dataset_kwargs)
processor_encoder = LsdbDataProcessor(dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8)
processor_decoder = LsdbDataProcessor(dataset=dataset,
embedding_dim=512 - 8,
reducer_input_dim=512,
local_position_embedding_dim=8)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'velocity_quantization': velocity_quantization,
'max_transposition': max_transposition,
'compute_statistics_flag': False
}
dataset: ArrangementDataset = dataset_manager.get_dataset(
name='arrangement', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction_large':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'velocity_quantization': velocity_quantization,
'max_transposition': max_transposition,
'compute_statistics_flag': False
}
dataset: ArrangementDataset = dataset_manager.get_dataset(
name='arrangement_large', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction_small':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'velocity_quantization': velocity_quantization,
'max_transposition': max_transposition,
'compute_statistics_flag': False
}
dataset: ArrangementDataset = dataset_manager.get_dataset(
name='arrangement_small', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'arrangement':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'velocity_quantization': velocity_quantization,
'max_transposition': max_transposition,
'integrate_discretization': True,
'alignement_type': 'complete',
'compute_statistics_flag': False
}
dataset: ArrangementDataset = dataset_manager.get_dataset(
name='arrangement', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ArrangementDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_decoder = ArrangementDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_encodencoder = ArrangementDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='instruments',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'arrangement_small':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'velocity_quantization': velocity_quantization,
'max_transposition': max_transposition,
'integrate_discretization': True,
'alignement_type': 'complete',
'compute_statistics_flag': False
}
dataset: ArrangementDataset = dataset_manager.get_dataset(
name='arrangement_small', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ArrangementDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_decoder = ArrangementDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_encodencoder = ArrangementDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='instruments',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'arrangement_midiPiano':
# For now just try a small value, anyway exception if too small
mean_number_messages_per_time_frame = 14
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'compute_statistics_flag': False,
'mean_number_messages_per_time_frame':
mean_number_messages_per_time_frame,
'integrate_discretization': True,
'alignement_type': 'complete',
}
dataset: ArrangementMidipianoDataset = dataset_manager.get_dataset(
name='arrangement_midiPiano', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ArrangementMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_decoder = ArrangementMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_encodencoder = ArrangementMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='instruments',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'arrangement_midiPiano_small':
mean_number_messages_per_time_frame = 14
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'compute_statistics_flag': False,
'mean_number_messages_per_time_frame':
mean_number_messages_per_time_frame,
'integrate_discretization': True,
'alignement_type': 'complete'
}
dataset: ArrangementMidipianoDataset = dataset_manager.get_dataset(
name='arrangement_midiPiano_small', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ArrangementMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_decoder = ArrangementMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_encodencoder = ArrangementMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='instruments',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'arrangement_voice':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'integrate_discretization': True,
'alignement_type': 'complete',
'compute_statistics_flag': False,
}
dataset: ArrangementVoiceDataset = dataset_manager.get_dataset(
name='arrangement_voice', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ArrangementVoiceDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_decoder = ArrangementVoiceDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_encodencoder = ArrangementVoiceDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='instruments',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'arrangement_voice_small':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'integrate_discretization': True,
'alignement_type': 'complete',
'compute_statistics_flag': False,
}
dataset: ArrangementVoiceDataset = dataset_manager.get_dataset(
name='arrangement_voice_small', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ArrangementVoiceDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_decoder = ArrangementVoiceDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
processor_encodencoder = ArrangementVoiceDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='instruments',
block_attention=block_attention,
nade=nade,
double_conditioning=double_conditioning)
return dataset, processor_decoder, processor_encoder, processor_encodencoder
# elif dataset_type == 'arrangement_minimal':
#
# arrangement_dataset_kwargs = {
# 'transpose_to_sounding_pitch': True,
# 'subdivision': subdivision,
# 'sequence_size': sequence_size,
# 'velocity_quantization': velocity_quantization,
# 'max_transposition': max_transposition,
# 'compute_statistics_flag': False
# }
# dataset: ArrangementDataset = dataset_manager.get_dataset(
# name='arrangement',
# **arrangement_dataset_kwargs
# )
#
# reducer_input_dim = num_heads * per_head_dim
#
# processor_encoder = ArrangementDataProcessorMinimal(dataset=dataset,
# embedding_dim=reducer_input_dim - local_position_embedding_dim,
# reducer_input_dim=reducer_input_dim,
# local_position_embedding_dim=local_position_embedding_dim,
# flag_orchestra=False,
# block_attention=block_attention)
#
# processor_decoder = ArrangementDataProcessorMinimal(dataset=dataset,
# embedding_dim=reducer_input_dim - local_position_embedding_dim,
# reducer_input_dim=reducer_input_dim,
# local_position_embedding_dim=local_position_embedding_dim,
# flag_orchestra=True,
# block_attention=block_attention)
#
# processor_encodencoder = None
#
# return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'ar':
dataset: ARDataset = ARDataset(phis=[0.9], length=128, c=0)
# todo create BachTransformer and put BachBeats data processor in it
processor_encoder = ARDataProcessor(dataset=dataset)
processor_decoder = ARDataProcessor(dataset=dataset)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction_categorical':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'compute_statistics_flag': False,
'group_instrument_per_section': group_instrument_per_section
}
dataset: ArrangementVoiceDataset = dataset_manager.get_dataset(
name='arrangement_categorical', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionCategoricalDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionCategoricalDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction_categorical_small':
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'compute_statistics_flag': False,
'group_instrument_per_section': group_instrument_per_section
}
dataset: ArrangementVoiceDataset = dataset_manager.get_dataset(
name='arrangement_categorical_small', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionCategoricalDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionCategoricalDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction_midiPiano':
# For now just try a small value, anyway exception if too small
mean_number_messages_per_time_frame = 14
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'compute_statistics_flag': False,
'mean_number_messages_per_time_frame':
mean_number_messages_per_time_frame,
'integrate_discretization': True
}
dataset: ArrangementMidipianoDataset = dataset_manager.get_dataset(
name='arrangement_midiPiano', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
elif dataset_type == 'reduction_midiPiano_small':
# Todo: compuyte value before ?
# For now just try a small value, anyway exception if too small
mean_number_messages_per_time_frame = 14
arrangement_dataset_kwargs = {
'transpose_to_sounding_pitch': True,
'subdivision': subdivision,
'sequence_size': sequence_size,
'max_transposition': max_transposition,
'compute_statistics_flag': False,
'mean_number_messages_per_time_frame':
mean_number_messages_per_time_frame,
'integrate_discretization': True
}
dataset: ArrangementMidipianoDataset = dataset_manager.get_dataset(
name='arrangement_midiPiano_small', **arrangement_dataset_kwargs)
reducer_input_dim = num_heads * per_head_dim
processor_encoder = ReductionMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='orchestra',
block_attention=block_attention)
processor_decoder = ReductionMidiPianoDataProcessor(
dataset=dataset,
embedding_dim=reducer_input_dim - local_position_embedding_dim,
reducer_input_dim=reducer_input_dim,
local_position_embedding_dim=local_position_embedding_dim,
flag='piano',
block_attention=block_attention)
processor_encodencoder = None
return dataset, processor_decoder, processor_encoder, processor_encodencoder
else:
raise NotImplementedError
def main(note_embedding_dim, metadata_embedding_dim, num_encoder_layers,
encoder_hidden_size, encoder_dropout_prob, latent_space_dim,
num_decoder_layers, decoder_hidden_size, decoder_dropout_prob,
has_metadata, num_latent_rnn_layers, latent_rnn_hidden_size,
latent_rnn_dropout_prob, num_layers, lstm_hidden_size, dropout_lstm,
input_dropout, linear_hidden_size, batch_size, num_target,
num_models):
# init dataset
dataset_manager = DatasetManager()
metadatas = [
BeatMarkerMetadata(subdivision=6),
TickMetadata(subdivision=6)
]
mvae_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_dataset_vae: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **mvae_train_kwargs)
# init vae model
vae_model = MeasureVAE(dataset=folk_dataset_vae,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_encoder_layers=num_encoder_layers,
encoder_hidden_size=encoder_hidden_size,
encoder_dropout_prob=encoder_dropout_prob,
latent_space_dim=latent_space_dim,
num_decoder_layers=num_decoder_layers,
decoder_hidden_size=decoder_hidden_size,
decoder_dropout_prob=decoder_dropout_prob,
has_metadata=has_metadata)
vae_model.load() # VAE model must be pre-trained
if torch.cuda.is_available():
vae_model.cuda()
folk_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_test_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': False
}
folk_dataset_train: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **folk_train_kwargs)
folk_dataset_test: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **folk_test_kwargs)
# init latent_rnn model and latent_rnn_tester
latent_rnn_model = LatentRNN(dataset=folk_dataset_train,
vae_model=vae_model,
num_rnn_layers=num_latent_rnn_layers,
rnn_hidden_size=latent_rnn_hidden_size,
dropout=latent_rnn_dropout_prob,
rnn_class=torch.nn.GRU,
auto_reg=False,
teacher_forcing=True)
latent_rnn_model.load() # latent_rnn model must be pre-trained
if torch.cuda.is_available():
latent_rnn_model.cuda()
latent_rnn_tester = LatentRNNTester(dataset=folk_dataset_test,
model=latent_rnn_model)
# inti arnn model and arnn_testes
arnn_model = ConstraintModelGaussianReg(
dataset=folk_dataset_train,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_layers=num_layers,
num_lstm_constraints_units=lstm_hidden_size,
num_lstm_generation_units=lstm_hidden_size,
linear_hidden_size=linear_hidden_size,
dropout_prob=dropout_lstm,
dropout_input_prob=input_dropout,
unary_constraint=True,
teacher_forcing=True)
arnn_model.load() # ARNN model must be pre-trained
if torch.cuda.is_available():
arnn_model.cuda()
arnn_tester = AnticipationRNNTester(dataset=folk_dataset_test,
model=arnn_model)
arnn_baseline_model = AnticipationRNNBaseline(
dataset=folk_dataset_train,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_layers=num_layers,
num_lstm_constraints_units=lstm_hidden_size,
num_lstm_generation_units=lstm_hidden_size,
linear_hidden_size=linear_hidden_size,
dropout_prob=dropout_lstm,
dropout_input_prob=input_dropout,
unary_constraint=True,
teacher_forcing=True)
arnn_baseline_model.load() # ARNN model must be pre-trained
if torch.cuda.is_available():
arnn_baseline_model.cuda()
arnn_baseline_tester = AnticipationRNNTester(dataset=folk_dataset_test,
model=arnn_baseline_model)
# create test dataloader
(_, _,
test_dataloader) = folk_dataset_test.data_loaders(batch_size=batch_size,
split=(0.01, 0.01))
# test
print('Num Test Batches: ', len(test_dataloader))
latent_rnn_mean_loss, latent_rnn_mean_accuracy, \
arnn_mean_loss, arnn_mean_accuracy, \
arnn_baseline_mean_loss, arnn_baseline_mean_accuracy = loss_and_acc_test(
data_loader=test_dataloader,
latent_rnn_tester=latent_rnn_tester,
arnn_tester=arnn_tester,
arnn_baseline_tester=arnn_baseline_tester,
num_target_measures=num_target,
num_models=num_models
)
print('Test Epoch:')
print('latent_rnn Test Loss: ', latent_rnn_mean_loss, '\n'
'latent_rnn Test Accuracy: ', latent_rnn_mean_accuracy * 100, '\n'
'ARNN Test Loss: ', arnn_mean_loss, '\n'
'ARNN Test Accuracy: ', arnn_mean_accuracy * 100, '\n'
'ARNN Baseline Test Loss: ', arnn_baseline_mean_loss, '\n'
'ARNN Baseline Test Accuracy: ', arnn_baseline_mean_accuracy * 100,
'\n')
def main(note_embedding_dim, metadata_embedding_dim, num_encoder_layers,
encoder_hidden_size, encoder_dropout_prob, latent_space_dim,
num_decoder_layers, decoder_hidden_size, decoder_dropout_prob,
has_metadata, num_latent_rnn_layers, latent_rnn_hidden_size,
latent_rnn_dropout_prob, num_layers, lstm_hidden_size, dropout_lstm,
input_dropout, linear_hidden_size, batch_size, num_target,
num_models):
random.seed(0)
# init dataset
dataset_manager = DatasetManager()
metadatas = [
BeatMarkerMetadata(subdivision=6),
TickMetadata(subdivision=6)
]
mvae_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_dataset_vae: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **mvae_train_kwargs)
# init vae model
vae_model = MeasureVAE(dataset=folk_dataset_vae,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_encoder_layers=num_encoder_layers,
encoder_hidden_size=encoder_hidden_size,
encoder_dropout_prob=encoder_dropout_prob,
latent_space_dim=latent_space_dim,
num_decoder_layers=num_decoder_layers,
decoder_hidden_size=decoder_hidden_size,
decoder_dropout_prob=decoder_dropout_prob,
has_metadata=has_metadata)
vae_model.load() # VAE model must be pre-trained
if torch.cuda.is_available():
vae_model.cuda()
folk_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_test_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': False
}
folk_dataset_train: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **folk_train_kwargs)
folk_dataset_test: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **folk_test_kwargs)
# Initialize stuff
test_filenames = folk_dataset_test.dataset_filenames
num_melodies = 32
num_measures = 16
req_length = num_measures * 4 * 6
num_past = 6
num_future = 6
num_target = 4
cur_dir = os.path.dirname(os.path.realpath(__file__))
save_folder = 'saved_midi/'
# First save original data
for i in tqdm(range(num_melodies)):
f = test_filenames[i]
f_id = f[:-4]
# save original scores
save_filename = os.path.join(cur_dir,
save_folder + f_id + '_original.mid')
if os.path.isfile(save_filename):
continue
f = os.path.join(folk_dataset_test.corpus_it_gen.raw_dataset_dir, f)
score = folk_dataset_test.corpus_it_gen.get_score_from_path(
f, fix_and_expand=True)
score_tensor = folk_dataset_test.get_score_tensor(score)
metadata_tensor = folk_dataset_test.get_metadata_tensor(score)
# ignore scores with less than 16 measures
if score_tensor.size(1) < req_length:
continue
score_tensor = score_tensor[:, :req_length]
metadata_tensor = metadata_tensor[:, :req_length, :]
trunc_score = folk_dataset_test.tensor_to_score(score_tensor)
trunc_score.write('midi', fp=save_filename)
# Initialize models and testers
latent_rnn_model = LatentRNN(dataset=folk_dataset_train,
vae_model=vae_model,
num_rnn_layers=num_latent_rnn_layers,
rnn_hidden_size=latent_rnn_hidden_size,
dropout=latent_rnn_dropout_prob,
rnn_class=torch.nn.GRU,
auto_reg=False,
teacher_forcing=True)
latent_rnn_model.load() # Latent RNN model must be pre-trained
if torch.cuda.is_available():
latent_rnn_model.cuda()
latent_rnn_tester = LatentRNNTester(dataset=folk_dataset_test,
model=latent_rnn_model)
def process_latent_rnn_batch(score_tensor,
num_past=6,
num_future=6,
num_target=4):
assert (num_past + num_future + num_target == 16)
score_tensor = score_tensor.unsqueeze(0)
score_tensor = LatentRNNTrainer.split_to_measures(score_tensor, 24)
tensor_past, tensor_future, tensor_target = LatentRNNTrainer.split_score(
score_tensor=score_tensor,
num_past=num_past,
num_future=num_future,
num_target=num_target,
measure_seq_len=24)
return tensor_past, tensor_future, tensor_target
# Second save latent_rnn generations
for i in tqdm(range(num_melodies)):
f = test_filenames[i]
f_id = f[:-4]
save_filename = os.path.join(cur_dir,
save_folder + f_id + '_latent_rnn.mid')
if os.path.isfile(save_filename):
continue
f = os.path.join(folk_dataset_test.corpus_it_gen.raw_dataset_dir, f)
score = folk_dataset_test.corpus_it_gen.get_score_from_path(
f, fix_and_expand=True)
score_tensor = folk_dataset_test.get_score_tensor(score)
# metadata_tensor = folk_dataset_test.get_metadata_tensor(score)
# ignore scores with less than 16 measures
if score_tensor.size(1) < req_length:
continue
score_tensor = score_tensor[:, :req_length]
# metadata_tensor = metadata_tensor[:, :req_length, :]
# save regeneration using latent_rnn
tensor_past, tensor_future, tensor_target = process_latent_rnn_batch(
score_tensor, num_past, num_future, num_target)
# forward pass through latent_rnn
weights, gen_target, _ = latent_rnn_tester.model(
past_context=tensor_past,
future_context=tensor_future,
target=tensor_target,
measures_to_generate=num_target,
train=False,
)
# convert to score
batch_size, _, _ = gen_target.size()
gen_target = gen_target.view(batch_size, num_target, 24)
gen_score_tensor = torch.cat((tensor_past, gen_target, tensor_future),
1)
latent_rnn_score = folk_dataset_test.tensor_to_score(
gen_score_tensor.cpu())
latent_rnn_score.write('midi', fp=save_filename)
# Intialize arnn model and arnn_tester
arnn_model = ConstraintModelGaussianReg(
dataset=folk_dataset_train,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_layers=num_layers,
num_lstm_constraints_units=lstm_hidden_size,
num_lstm_generation_units=lstm_hidden_size,
linear_hidden_size=linear_hidden_size,
dropout_prob=dropout_lstm,
dropout_input_prob=input_dropout,
unary_constraint=True,
teacher_forcing=True)
arnn_model.load() # ARNN model must be pre-trained
if torch.cuda.is_available():
arnn_model.cuda()
arnn_tester = AnticipationRNNTester(dataset=folk_dataset_test,
model=arnn_model)
def process_arnn_batch(score_tensor,
metadata_tensor,
arnn_tester,
num_past=6,
num_target=4):
score_tensor = score_tensor.unsqueeze(0)
metadata_tensor = metadata_tensor.unsqueeze(0)
tensor_score = to_cuda_variable_long(score_tensor)
tensor_metadata = to_cuda_variable_long(metadata_tensor)
constraints_location, start_tick, end_tick = arnn_tester.get_constraints_location(
tensor_score,
is_stochastic=False,
start_measure=num_past,
num_measures=num_target)
arnn_batch = (tensor_score, tensor_metadata, constraints_location,
start_tick, end_tick)
return arnn_batch
# Third save ARNN-Reg generations
for i in tqdm(range(num_melodies)):
f = test_filenames[i]
f_id = f[:-4]
save_filename = os.path.join(cur_dir,
save_folder + f_id + '_arnn_reg.mid')
if os.path.isfile(save_filename):
continue
f = os.path.join(folk_dataset_test.corpus_it_gen.raw_dataset_dir, f)
score = folk_dataset_test.corpus_it_gen.get_score_from_path(
f, fix_and_expand=True)
score_tensor = folk_dataset_test.get_score_tensor(score)
metadata_tensor = folk_dataset_test.get_metadata_tensor(score)
# ignore scores with less than 16 measures
if score_tensor.size(1) < req_length:
continue
score_tensor = score_tensor[:, :req_length]
metadata_tensor = metadata_tensor[:, :req_length, :]
# save regeneration using latent_rnn
tensor_score, tensor_metadata, constraints_location, start_tick, end_tick = \
process_arnn_batch(score_tensor, metadata_tensor, arnn_tester, num_past, num_target)
# forward pass through latent_rnn
_, gen_target = arnn_tester.model.forward_inpaint(
score_tensor=tensor_score,
metadata_tensor=tensor_metadata,
constraints_loc=constraints_location,
start_tick=start_tick,
end_tick=end_tick,
)
# convert to score
arnn_score = folk_dataset_test.tensor_to_score(gen_target.cpu())
arnn_score.write('midi', fp=save_filename)
# Intialize arnn-baseline model and arnn_tester
arnn_baseline_model = AnticipationRNNBaseline(
dataset=folk_dataset_train,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_layers=num_layers,
num_lstm_constraints_units=lstm_hidden_size,
num_lstm_generation_units=lstm_hidden_size,
linear_hidden_size=linear_hidden_size,
dropout_prob=dropout_lstm,
dropout_input_prob=input_dropout,
unary_constraint=True,
teacher_forcing=True)
arnn_baseline_model.load() # ARNN model must be pre-trained
if torch.cuda.is_available():
arnn_baseline_model.cuda()
arnn_baseline_tester = AnticipationRNNTester(dataset=folk_dataset_test,
model=arnn_baseline_model)
# Fourth save ARNN-Baseline generations
for i in tqdm(range(num_melodies)):
f = test_filenames[i]
f_id = f[:-4]
save_filename = os.path.join(cur_dir,
save_folder + f_id + '_arnn_baseline.mid')
if os.path.isfile(save_filename):
continue
f = os.path.join(folk_dataset_test.corpus_it_gen.raw_dataset_dir, f)
score = folk_dataset_test.corpus_it_gen.get_score_from_path(
f, fix_and_expand=True)
score_tensor = folk_dataset_test.get_score_tensor(score)
metadata_tensor = folk_dataset_test.get_metadata_tensor(score)
# ignore scores with less than 16 measures
if score_tensor.size(1) < req_length:
continue
score_tensor = score_tensor[:, :req_length]
metadata_tensor = metadata_tensor[:, :req_length, :]
# save regeneration using latent_rnn
tensor_score, tensor_metadata, constraints_location, start_tick, end_tick = \
process_arnn_batch(score_tensor, metadata_tensor, arnn_baseline_tester, num_past, num_target)
# forward pass through latent_rnn
_, gen_target = arnn_baseline_tester.model.forward_inpaint(
score_tensor=tensor_score,
metadata_tensor=tensor_metadata,
constraints_loc=constraints_location,
start_tick=start_tick,
end_tick=end_tick,
)
# convert to score
arnn_baseline_score = folk_dataset_test.tensor_to_score(
gen_target.cpu())
arnn_baseline_score.write('midi', fp=save_filename)
def main(note_embedding_dim,
metadata_embedding_dim,
num_encoder_layers,
encoder_hidden_size,
encoder_dropout_prob,
latent_space_dim,
num_decoder_layers,
decoder_hidden_size,
decoder_dropout_prob,
has_metadata,
num_latent_rnn_layers,
latent_rnn_hidden_size,
latent_rnn_dropout_prob,
batch_size,
num_epochs,
train,
lr,
plot,
log,
auto_reg,
teacher_forcing,
early_stop
):
# init dataset
dataset_manager = DatasetManager()
metadatas = [
BeatMarkerMetadata(subdivision=6),
TickMetadata(subdivision=6)
]
mvae_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_dataset_vae: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train',
**mvae_train_kwargs
)
# init vae model
vae_model = MeasureVAE(
dataset=folk_dataset_vae,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_encoder_layers=num_encoder_layers,
encoder_hidden_size=encoder_hidden_size,
encoder_dropout_prob=encoder_dropout_prob,
latent_space_dim=latent_space_dim,
num_decoder_layers=num_decoder_layers,
decoder_hidden_size=decoder_hidden_size,
decoder_dropout_prob=decoder_dropout_prob,
has_metadata=has_metadata
)
vae_model.load() # VAE model must be pre-trained
folk_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_test_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': False
}
folk_dataset_train: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train',
**folk_train_kwargs
)
folk_dataset_test: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train',
**folk_test_kwargs
)
# init latent_rnn model
model = LatentRNN(
dataset=folk_dataset_train,
vae_model=vae_model,
num_rnn_layers=num_latent_rnn_layers,
rnn_hidden_size=latent_rnn_hidden_size,
dropout=latent_rnn_dropout_prob,
rnn_class=torch.nn.GRU,
auto_reg=auto_reg,
teacher_forcing=teacher_forcing
)
if train:
if torch.cuda.is_available():
model.cuda()
trainer = LatentRNNTrainer(
dataset=folk_dataset_train,
model=model,
lr=lr,
early_stopping=early_stop
)
trainer.train_model(
batch_size=batch_size,
num_epochs=num_epochs,
plot=plot,
log=log
)
else:
model.load()
model.cuda()
model.eval()
tester = LatentRNNTester(
dataset=folk_dataset_test,
model=model
)
tester.test_model(
batch_size=batch_size
)
gen_score, score, original_score = tester.generation_random(
tensor_score=None,
start_measure=8,
num_measures_gen=2
)
print( " --- score --- " )
print( score )
gen_score.show()
original_score.show()
gen_score2, score, original_score2 = tester.generation_test()
gen_score2.show()
original_score2.show()
print( " --- score --- " )
print( score )
def main(note_embedding_dim, meta_embedding_dim, num_layers, lstm_hidden_size,
dropout_lstm, linear_hidden_size, batch_size, num_epochs, train,
update, num_iterations, sequence_length_ticks, model_id,
include_transpositions, update_iterations, generations_per_iteration,
num_generations, score_chorales, write_scores):
print('step 1/3: prepare dataset')
dataset_manager = DatasetManager()
metadatas = [FermataMetadata(), TickMetadata(subdivision=4), KeyMetadata()]
chorale_dataset_kwargs = {
'voice_ids': [0, 1, 2, 3],
'metadatas': metadatas,
'sequences_size': 8,
'subdivision': 4,
'include_transpositions': include_transpositions,
}
bach_chorales_dataset: ChoraleDataset = dataset_manager.get_dataset(
name='bach_chorales', **chorale_dataset_kwargs)
dataset = bach_chorales_dataset
load_or_pickle_distributions(dataset)
print('step 2/3: prepare model')
print(f'Model ID: {model_id}')
deepbach = DeepBach(
dataset=dataset,
note_embedding_dim=note_embedding_dim,
meta_embedding_dim=meta_embedding_dim,
num_layers=num_layers,
lstm_hidden_size=lstm_hidden_size,
dropout_lstm=dropout_lstm,
linear_hidden_size=linear_hidden_size,
model_id=model_id,
)
if train:
print('step 2a/3: train base model')
deepbach.train(batch_size=batch_size,
num_epochs=num_epochs,
split=[0.85, 0.15])
else:
print('step 2a/3: load model')
deepbach.load()
deepbach.cuda()
if update:
print(
f'step 2b/3: update base model over {update_iterations} iterations'
)
thres = get_threshold('data/chorale_scores.csv', col=-1)
print(f'Threshold for selection: {thres}')
update_file = open('data/update_scores.csv', 'w')
reader = csv.writer(update_file)
reader.writerow(['iteration', 'chorale ID', 'score'])
for i in range(update_iterations):
print(f'----------- Iteration {i} -----------')
picked_chorales = []
num_picked_chorales = 0
ensure_dir(f'generations/{model_id}/{i}')
for j in tqdm(range(generations_per_iteration)):
chorale, tensor_chorale, tensor_metadata = deepbach.generation(
num_iterations=num_iterations,
sequence_length_ticks=sequence_length_ticks,
)
score = score_chorale(chorale, dataset)
# write data to csv file
reader.writerow([i, j,
score]) # iteration, generation #, score
# worst Bach chorale score rounded up to nearest .01
if score > thres:
print(f'Picked chorale {j} with score {score}')
picked_chorales.append(chorale)
num_picked_chorales += 1
chorale.write('midi', f'generations/{model_id}/{i}/c{j}.mid')
print(
f'Number of picked chorales for iteration {i}: {num_picked_chorales}'
)
if num_picked_chorales == 0:
continue
all_datasets.update({
f'generated_chorales_{i}': {
'dataset_class_name': ChoraleDataset,
'corpus_it_gen':
GeneratedChoraleIteratorGen(picked_chorales)
}
})
generated_dataset: ChoraleDataset = dataset_manager.get_dataset(
name=f'generated_chorales_{i}',
index2note_dicts=dataset.index2note_dicts,
note2index_dicts=dataset.note2index_dicts,
voice_ranges=dataset.voice_ranges,
**chorale_dataset_kwargs)
deepbach.dataset = generated_dataset
deepbach.train(
batch_size=batch_size,
num_epochs=2,
split=[1, 0], # use all selected chorales for training
early_stopping=False)
# generate chorales
if score_chorales:
chorale_scores = {}
print('Scoring real chorales')
for chorale_id, chorale in tqdm(enumerate(dataset.iterator_gen()),
total=num_generations):
score = score_chorale(chorale, dataset)
chorale_scores[chorale_id] = score
if chorale_id == num_generations:
break
# write scores to file
if write_scores:
with open('data/chorale_scores.csv', 'w') as chorale_file:
reader = csv.writer(chorale_file)
reader.writerow(['', 'score'] + list(weights.keys()))
for id, value in chorale_scores.items():
reader.writerow([id, value])
if num_generations != 0:
generation_scores = {}
print('Generating and scoring generated chorales')
ensure_dir(f'generations/{model_id}')
for i in range(num_generations):
chorale, tensor_chorale, tensor_metadata = deepbach.generation(
num_iterations=num_iterations,
sequence_length_ticks=sequence_length_ticks,
)
chorale.write('midi', f'generations/{model_id}/c{i}.mid')
score = score_chorale(chorale, dataset)
generation_scores[i] = score
# write scores to file
if write_scores:
with open(f'data/model{model_id}_scores.csv',
'w') as generation_file:
reader = csv.writer(generation_file)
reader.writerow(['', 'score'] + list(weights.keys()))
for id, value in generation_scores.items():
reader.writerow([id, value])
num_datapoints, 1, length, num_metadata)
dataset = TensorDataset(score_tensor_dataset, metadata_tensor_dataset)
print(f'Sizes: {score_tensor_dataset.size()}')
print(f'Sizes: {metadata_tensor_dataset.size()}')
return dataset
if __name__ == '__main__':
from DatasetManager.dataset_manager import DatasetManager
from DatasetManager.metadata import BeatMarkerMetadata, TickMetadata
dataset_manager = DatasetManager()
metadatas = [
BeatMarkerMetadata(subdivision=6),
TickMetadata(subdivision=6)
]
folk_dataset_kwargs = {'metadatas': metadatas, 'sequences_size': 32}
folk_dataset: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4measures_test', **folk_dataset_kwargs)
(train_dataloader, val_dataloader,
test_dataloader) = folk_dataset.data_loaders(batch_size=100,
split=(0.7, 0.2))
print('Num Train Batches: ', len(train_dataloader))
print('Num Valid Batches: ', len(val_dataloader))
print('Num Test Batches: ', len(test_dataloader))
for sample_id, (score, _) in tqdm(enumerate(train_dataloader)):
score = score.long()
if torch.cuda.is_available():
score = torch.autograd.Variable(score.cuda())
from grader.grader import score_chorale
from DatasetManager.chorale_dataset import ChoraleDataset
from DatasetManager.dataset_manager import DatasetManager, all_datasets
from DatasetManager.metadata import FermataMetadata, TickMetadata, KeyMetadata
from DatasetManager.helpers import GeneratedChoraleIteratorGen
from DeepBach.model_manager import DeepBach
from DeepBach.helpers import *
print('step 1/3: prepare dataset')
dataset_manager = DatasetManager()
metadatas = [FermataMetadata(), TickMetadata(subdivision=4), KeyMetadata()]
chorale_dataset_kwargs = {
'voice_ids': [1, 1, 2, 3],
'metadatas': metadatas,
'sequences_size': 8,
'subdivision': 4,
'include_transpositions': False,
}
bach_chorales_dataset: ChoraleDataset = dataset_manager.get_dataset(
name='bach_chorales', **chorale_dataset_kwargs)
dataset = bach_chorales_dataset
load_or_pickle_distributions(dataset)
print(dataset.gaussian.covariances_)
# chorale = converter.parse('generations/6/c187.mid')
# score = score_chorale(chorale, dataset)
# print(score)
# Piano score
_piano = None
# Orchestra init (before even the first pass of the model, i.e. filled with MASK and REST symbols
_orchestra_init = None
_orchestra_silenced_instruments = None
# TODO use this parameter or extract it from the metadata somehow
timesignature = music21.meter.TimeSignature('4/4')
# generation parameters
# todo put in click?
batch_size_per_voice = 8
metadatas = [
FermataMetadata(),
TickMetadata(subdivision=_subdivision),
KeyMetadata()
]
# def get_fermatas_tensor(metadata_tensor: torch.Tensor) -> torch.Tensor:
# """
# Extract the fermatas tensor from a metadata tensor
# """
# fermatas_index = [m.__class__ for m in metadatas].index(
# FermataMetadata().__class__)
# # fermatas are shared across all voices so we only consider the first voice
# soprano_voice_metadata = metadata_tensor[0]
#
# # `soprano_voice_metadata` has shape
# # `(sequence_duration, len(metadatas + 1))` (accouting for the voice
# # index metadata)
deepbach = None
_num_iterations = None
_sequence_length_ticks = None
_ticks_per_quarter = None
# TODO use this parameter or extract it from the metadata somehow
timesignature = music21.meter.TimeSignature('4/4')
# generation parameters
# todo put in click?
batch_size_per_voice = 8
metadatas = [
FermataMetadata(),
TickMetadata(subdivision=_ticks_per_quarter),
KeyMetadata()
]
def get_fermatas_tensor(metadata_tensor: torch.Tensor) -> torch.Tensor:
"""
Extract the fermatas tensor from a metadata tensor
"""
fermatas_index = [m.__class__
for m in metadatas].index(FermataMetadata().__class__)
# fermatas are shared across all voices so we only consider the first voice
soprano_voice_metadata = metadata_tensor[0]
# `soprano_voice_metadata` has shape
# `(sequence_duration, len(metadatas + 1))` (accouting for the voice
def main(note_embedding_dim, metadata_embedding_dim, num_encoder_layers,
encoder_hidden_size, encoder_dropout_prob, latent_space_dim,
num_decoder_layers, decoder_hidden_size, decoder_dropout_prob,
has_metadata, num_latent_rnn_layers, latent_rnn_hidden_size,
latent_rnn_dropout_prob, num_layers, lstm_hidden_size, dropout_lstm,
input_dropout, linear_hidden_size, batch_size, num_target,
num_models):
random.seed(0)
# init dataset
dataset_manager = DatasetManager()
metadatas = [
BeatMarkerMetadata(subdivision=6),
TickMetadata(subdivision=6)
]
mvae_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_dataset_vae: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **mvae_train_kwargs)
# init vae model
vae_model = MeasureVAE(dataset=folk_dataset_vae,
note_embedding_dim=note_embedding_dim,
metadata_embedding_dim=metadata_embedding_dim,
num_encoder_layers=num_encoder_layers,
encoder_hidden_size=encoder_hidden_size,
encoder_dropout_prob=encoder_dropout_prob,
latent_space_dim=latent_space_dim,
num_decoder_layers=num_decoder_layers,
decoder_hidden_size=decoder_hidden_size,
decoder_dropout_prob=decoder_dropout_prob,
has_metadata=has_metadata)
vae_model.load() # VAE model must be pre-trained
if torch.cuda.is_available():
vae_model.cuda()
folk_train_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': True
}
folk_test_kwargs = {
'metadatas': metadatas,
'sequences_size': 32,
'num_bars': 16,
'train': False
}
folk_dataset_train: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **folk_train_kwargs)
folk_dataset_test: FolkDataset = dataset_manager.get_dataset(
name='folk_4by4nbars_train', **folk_test_kwargs)
# Initialize stuff
test_filenames = folk_dataset_test.dataset_filenames
num_melodies = 32
num_measures = 16
req_length = num_measures * 4 * 6
num_past = 6
num_future = 6
num_target = 4
cur_dir = os.path.dirname(os.path.realpath(__file__))
save_folder = 'saved_midi/'
# Initialize models and testers
latent_rnn_model = LatentRNN(dataset=folk_dataset_train,
vae_model=vae_model,
num_rnn_layers=num_latent_rnn_layers,
rnn_hidden_size=latent_rnn_hidden_size,
dropout=latent_rnn_dropout_prob,
rnn_class=torch.nn.GRU,
auto_reg=False,
teacher_forcing=True)
latent_rnn_model.load() # latent_rnn model must be pre-trained
if torch.cuda.is_available():
latent_rnn_model.cuda()
latent_rnn_tester = LatentRNNTester(dataset=folk_dataset_test,
model=latent_rnn_model)
def process_latent_rnn_batch(score_tensor,
num_past=6,
num_future=6,
num_target=4):
assert (num_past + num_future + num_target == 16)
score_tensor = score_tensor.unsqueeze(0)
score_tensor = LatentRNNTrainer.split_to_measures(score_tensor, 24)
tensor_past, tensor_future, tensor_target = LatentRNNTrainer.split_score(
score_tensor=score_tensor,
num_past=num_past,
num_future=num_future,
num_target=num_target,
measure_seq_len=24)
return tensor_past, tensor_future, tensor_target
# Second save latent_rnn generations
for i in tqdm(range(num_melodies)):
f = test_filenames[i]
f_id = f[:-4]
if f_id == 'tune_16154':
for j in range(15):
save_filename = os.path.join(
cur_dir,
save_folder + f_id + '_' + str(j) + '_latent_rnn.mid')
f = os.path.join(
folk_dataset_test.corpus_it_gen.raw_dataset_dir, f)
score = folk_dataset_test.corpus_it_gen.get_score_from_path(
f, fix_and_expand=True)
score_tensor = folk_dataset_test.get_score_tensor(score)
# ignore scores with less than 16 measures
if score_tensor.size(1) < req_length:
continue
score_tensor = score_tensor[:, :req_length]
# metadata_tensor = metadata_tensor[:, :req_length, :]
# save regeneration using latent_rnn
tensor_past, tensor_future, tensor_target = process_latent_rnn_batch(
score_tensor, num_past, num_future, num_target)
# forward pass through latent_rnn
weights, gen_target, _ = latent_rnn_tester.model(
past_context=tensor_past,
future_context=tensor_future,
target=tensor_target,
measures_to_generate=num_target,
train=False,
)
# convert to score
batch_size, _, _ = gen_target.size()
gen_target = gen_target.view(batch_size, num_target, 24)
gen_score_tensor = torch.cat(
(tensor_past, gen_target, tensor_future), 1)
latent_rnn_score = folk_dataset_test.tensor_to_score(
gen_score_tensor.cpu())
latent_rnn_score.write('midi', fp=save_filename)