def build_model():
x_in = optimus.Input(name="x", shape=(None, 2))
class_idx = optimus.Input(name="y", shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
layer0 = optimus.Affine(name='layer0',
input_shape=x_in.shape,
output_shape=(None, 100),
act_type='relu')
layer1 = optimus.Affine(name='layer1',
input_shape=layer0.output.shape,
output_shape=(None, 100),
act_type='relu')
classifier = optimus.Softmax(name='classifier',
input_shape=layer1.output.shape,
n_out=N_CLASSES,
act_type='linear')
nll = optimus.NegativeLogLikelihood(name="nll")
posterior = optimus.Output(name='posterior')
trainer_edges = optimus.ConnectionManager([
(x_in, layer0.input), (layer0.output, layer1.input),
(layer1.output, classifier.input), (classifier.output, nll.likelihood),
(class_idx, nll.target_idx)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, classifier.weights), (learning_rate, classifier.bias)
])
trainer = optimus.Graph(name='trainer',
inputs=[x_in, class_idx, learning_rate],
nodes=[layer0, layer1, classifier],
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[nll],
updates=update_manager.connections)
optimus.random_init(layer0.weights)
optimus.random_init(layer1.weights)
optimus.random_init(classifier.weights)
predictor_edges = optimus.ConnectionManager([
(x_in, layer0.input), (layer0.output, layer1.input),
(layer1.output, classifier.input), (classifier.output, posterior)
])
predictor = optimus.Graph(name='predictor',
inputs=[x_in],
nodes=[layer0, layer1, classifier],
connections=predictor_edges.connections,
outputs=[posterior])
driver = optimus.Driver(graph=trainer, name='test')
return driver, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 5, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 5, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 2, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
512,
),
act_type='relu')
chord_classifier = optimus.Softmax(name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(name="chord_nll")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll],
updates=update_manager.connections)
optimus.random_init(chord_classifier.weights)
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
source = optimus.Queue(optimus.File(args.training_file),
transformers=[
T.chord_sample(input_data.shape[2]),
T.pitch_shift(8),
T.map_to_index(VOCAB)
],
**SOURCE_ARGS)
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
driver.fit(source, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def build_model():
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt',
shape=(None, OCTAVE_DIM, TIME_DIM, PITCH_DIM))
fret_map = optimus.Input(name='fret_map', shape=(None, 6, 9))
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(32, None, 5, 5),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 7),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 6),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
strings = []
for n in range(6):
strings.append(
optimus.Affine(name='string_%d' % n,
input_shape=layer3.output.shape,
output_shape=(None, 9),
act_type='sigmoid'))
param_nodes = [layer0, layer1, layer2, layer3] + strings
# 1.1 Create Loss
stack = optimus.Stack('stack', axes=[1, 0, 2])
error = optimus.SquaredEuclidean(name='squared_error')
loss = optimus.Mean(name='mse')
# 2. Define Edges
base_edges = [(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, strings[0].input),
(strings[0].output, stack.input_list),
(layer3.output, strings[1].input),
(strings[1].output, stack.input_list),
(layer3.output, strings[2].input),
(strings[2].output, stack.input_list),
(layer3.output, strings[3].input),
(strings[3].output, stack.input_list),
(layer3.output, strings[4].input),
(strings[4].output, stack.input_list),
(layer3.output, strings[5].input),
(strings[5].output, stack.input_list)]
trainer_edges = optimus.ConnectionManager(base_edges + [(
stack.output,
error.input_a), (fret_map, error.input_b), (error.output, loss.input)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, fret_map, learning_rate],
nodes=param_nodes + [stack, error, loss],
connections=trainer_edges.connections,
outputs=[loss.output],
loss=loss.output,
updates=update_manager.connections,
verbose=True)
for n in param_nodes:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
fret_posterior = optimus.Output(name='fret_posterior')
predictor_edges = optimus.ConnectionManager(base_edges +
[(stack.output,
fret_posterior)])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + [stack],
connections=predictor_edges.connections,
outputs=[fret_posterior])
return trainer, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
margin = optimus.Input(name='margin', shape=None)
margin_weight = optimus.Input(name='margin_weight', shape=None)
nll_weight = optimus.Input(name='nll_weight', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 7, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 6, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 512),
act_type='relu')
chord_classifier = optimus.Affine(name='chord_classifier',
input_shape=layer3.output.shape,
output_shape=(None, VOCAB),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
nll = optimus.NegativeLogLikelihood(name="nll", weighted=True)
likelihood_margin = optimus.LikelihoodMargin(name="likelihood_margin",
mode='l1',
weighted=True)
# likelihood_margin = optimus.NLLMargin(
# name="likelihood_margin",
# mode='l2',
# weighted=True)
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, likelihood_margin.likelihood),
(chord_idx, likelihood_margin.target_idx),
(margin, likelihood_margin.margin),
(margin_weight, likelihood_margin.weight),
(chord_classifier.output, nll.likelihood), (chord_idx, nll.target_idx),
(nll_weight, nll.weight)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[
input_data, chord_idx, margin, learning_rate,
margin_weight, nll_weight
],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[nll, likelihood_margin],
updates=update_manager.connections)
optimus.random_init(chord_classifier.weights)
optimus.random_init(chord_classifier.bias)
validator = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, margin, margin_weight, nll_weight],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[nll, likelihood_margin])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
stash = biggie.Stash(args.training_file)
stream = S.minibatch(D.create_uniform_quality_stream(stash,
TIME_DIM,
vocab_dim=VOCAB),
batch_size=50)
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {
learning_rate.name: LEARNING_RATE,
margin_weight.name: MARGIN_WEIGHT,
nll_weight.name: NLL_WEIGHT,
margin.name: MARGIN
}
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 6, TIME_DIM, 40))
target = optimus.Input(name='target', shape=(None, VOCAB))
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(32, None, 5, 5),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 7),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 6),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
chord_estimator = optimus.Affine(name='chord_estimator',
input_shape=layer3.output.shape,
output_shape=(
None,
VOCAB,
),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3, chord_estimator]
# 1.1 Create Losses
chord_xentropy = optimus.CrossEntropy(name="chord_xentropy")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_estimator.input),
(chord_estimator.output, chord_xentropy.prediction),
(target, chord_xentropy.target)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_estimator.weights),
(learning_rate, chord_estimator.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, target, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_xentropy],
updates=update_manager.connections,
momentum=None)
for n in all_nodes:
optimus.random_init(n.weights, 0, 0.01)
optimus.random_init(n.bias, 0, 0.01)
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, target],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_xentropy])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_estimator.input),
(chord_estimator.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
# partition_labels = json.load(
# open("/home/ejhumphrey/Dropbox/tmp/train0_v2_merged_partition.json"))
stream = D.create_uniform_chord_stream(stash,
TIME_DIM,
pitch_shift=False,
vocab_dim=VOCAB,
working_size=5)
stream = S.minibatch(FX.chord_index_to_affinity_vectors(
FX.wrap_cqt(stream, length=40, stride=36), VOCAB),
batch_size=BATCH_SIZE)
print "Starting '%s'" % args.trial_name
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
is_chord = optimus.Input(name='is_chord', shape=(None, ))
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 7, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 6, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
512,
),
act_type='relu')
chord_estimator = optimus.Affine(name='chord_estimator',
input_shape=layer3.output.shape,
output_shape=(None, VOCAB),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3, chord_estimator]
# 1.1 Create Losses
chord_mse = optimus.SparseMeanSquaredError(
# chord_mse = optimus.SparseCrossEntropy(
name="chord_mse")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_estimator.input),
(chord_estimator.output, chord_mse.prediction),
(chord_idx, chord_mse.index), (is_chord, chord_mse.target)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_estimator.weights),
(learning_rate, chord_estimator.bias)
])
print "Building trainer"
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, is_chord, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_mse],
updates=update_manager.connections)
optimus.random_init(chord_estimator.weights)
print "Building validator"
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx, is_chord],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_mse])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_estimator.input),
(chord_estimator.output, posterior)
])
print "Building predictor"
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Opening Data"
stash = biggie.Stash(args.training_file)
stream = S.minibatch(D.create_contrastive_quality_stream(stash,
TIME_DIM,
vocab_dim=VOCAB),
batch_size=50)
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
print "...aaand we're off!"
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def iXc3_nll(n_in, size='large', use_dropout=False):
k0, k1, k2 = dict(
small=(10, 20, 40),
med=(12, 24, 48),
large=(16, 32, 64),
xlarge=(20, 40, 80),
xxlarge=(24, 48, 96))[size]
n0, n1, n2 = {
1: (1, 1, 1),
4: (3, 2, 1),
8: (5, 3, 2),
10: (3, 3, 1),
20: (5, 5, 1)}[n_in]
p0, p1, p2 = {
1: (1, 1, 1),
4: (1, 1, 1),
8: (1, 1, 1),
10: (2, 2, 1),
12: (2, 2, 1),
20: (2, 2, 2)}[n_in]
input_data = optimus.Input(
name='cqt',
shape=(None, 1, n_in, 252))
indexes = []
for name in 'EADGBe':
indexes.append(optimus.Input(
name='{0}_index'.format(name),
shape=(None,),
dtype='int32'))
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
inputs = [input_data, learning_rate] + indexes
dropout = optimus.Input(
name='dropout',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(k0, None, n0, 13),
pool_shape=(p0, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, n1, 37),
pool_shape=(p1, 1),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, n2, 33),
pool_shape=(p2, 1),
act_type='relu')
trainer_edges = []
if use_dropout:
layer0.enable_dropout()
layer1.enable_dropout()
layer2.enable_dropout()
inputs += [dropout]
trainer_edges += [(dropout, layer0.dropout),
(dropout, layer1.dropout),
(dropout, layer2.dropout)]
predictors = []
softmaxes = []
for name in 'EADGBe':
predictors.append(optimus.Affine(
name='{0}_predictor'.format(name),
input_shape=layer2.output.shape,
output_shape=(None, NUM_FRETS),
act_type='linear'))
softmaxes.append(optimus.Softmax('{0}_softmax'.format(name)))
stack = optimus.Stack('stacker', num_inputs=6, axes=(1, 0, 2))
param_nodes = [layer0, layer1, layer2] + predictors
misc_nodes = [stack] + softmaxes
# 1.1 Create Loss
likelihoods = []
logs = []
neg_ones = []
for name in 'EADGBe':
likelihoods.append(
optimus.SelectIndex(name='{0}_likelihood'.format(name)))
logs.append(optimus.Log(name='{0}_log'.format(name)))
neg_ones.append(optimus.Multiply(name='{0}_gain'.format(name),
weight_shape=None))
neg_ones[-1].weight.value = -1.0
loss_sum = optimus.Add(name='loss_sum', num_inputs=6)
ave_loss = optimus.Mean(name='ave_loss')
loss_nodes = likelihoods + logs + neg_ones + [loss_sum, ave_loss]
total_loss = optimus.Output(name='total_loss')
fretboard = optimus.Output(name='fretboard')
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input)]
for p, smax in zip(predictors, softmaxes):
base_edges += [
(layer2.output, p.input),
(p.output, smax.input),
]
base_edges += [
(softmaxes[0].output, stack.input_0),
(softmaxes[1].output, stack.input_1),
(softmaxes[2].output, stack.input_2),
(softmaxes[3].output, stack.input_3),
(softmaxes[4].output, stack.input_4),
(softmaxes[5].output, stack.input_5),
(stack.output, fretboard)
]
for n, name in enumerate('EADGBe'):
trainer_edges += [
(softmaxes[n].output, likelihoods[n].input),
(indexes[n], likelihoods[n].index),
(likelihoods[n].output, logs[n].input),
(logs[n].output, neg_ones[n].input)
]
trainer_edges += [
(neg_ones[0].output, loss_sum.input_0),
(neg_ones[1].output, loss_sum.input_1),
(neg_ones[2].output, loss_sum.input_2),
(neg_ones[3].output, loss_sum.input_3),
(neg_ones[4].output, loss_sum.input_4),
(neg_ones[5].output, loss_sum.input_5),
(loss_sum.output, ave_loss.input),
(ave_loss.output, total_loss)
]
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
classifier_init(param_nodes)
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=inputs,
nodes=param_nodes + misc_nodes + loss_nodes,
connections=optimus.ConnectionManager(
base_edges + trainer_edges).connections,
outputs=[total_loss, fretboard],
loss=total_loss,
updates=update_manager.connections,
verbose=True)
if use_dropout:
layer0.disable_dropout()
layer1.disable_dropout()
layer2.disable_dropout()
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes,
connections=optimus.ConnectionManager(base_edges).connections,
outputs=[fretboard],
verbose=True)
return trainer, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(
name='cqt',
shape=(None, 1, TIME_DIM, PITCH_DIM))
target = optimus.Input(
name='target',
shape=(None, VOCAB))
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(32, 1, 5, 19),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 15),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 15),
act_type='relu')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 1024,),
act_type='relu')
chord_classifier = optimus.Affine(
name='chord_classifier',
input_shape=layer3.output.shape,
output_shape=(None, 6,),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_mse = optimus.MeanSquaredError(
name="chord_mse")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_mse.prediction),
(target, chord_mse.target)])
update_manager = optimus.ConnectionManager([
# (learning_rate, layer0.weights),
# (learning_rate, layer0.bias),
# (learning_rate, layer1.weights),
# (learning_rate, layer1.bias),
# (learning_rate, layer2.weights),
# (learning_rate, layer2.bias),
(learning_rate, layer3.weights),
(learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)])
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, target, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_mse],
updates=update_manager.connections)
for n in all_nodes:
optimus.random_init(n.weights, 0, 0.01)
optimus.random_init(n.bias, 0, 0.01)
if args.init_param_file:
param_values = dict(np.load(args.init_param_file))
keys = param_values.keys()
for key in keys:
if chord_classifier.name in key or layer3.name in key:
print "skipping %s" % key
del param_values[key]
trainer.param_values = param_values
posterior = optimus.Output(
name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)])
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
stream = D.create_uniform_chord_stream(
stash, TIME_DIM, pitch_shift=0, vocab_dim=VOCAB, working_size=10)
stream = S.minibatch(
FX.chord_index_to_tonnetz(stream, vocab_dim=VOCAB),
batch_size=BATCH_SIZE)
print "Starting '%s'" % args.trial_name
driver = optimus.Driver(
graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
def i8c4b10_nll_dropout(size='large'):
k0, k1, k2 = dict(
large=(24, 48, 64))[size]
input_data = optimus.Input(
name='cqt',
shape=(None, 1, 8, 252))
chord_idx = optimus.Input(
name='chord_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
dropout = optimus.Input(
name='dropout',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(k0, None, 3, 13),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, 3, 37),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, 3, 33),
act_type='relu')
layer3 = optimus.Conv3D(
name='layer3',
input_shape=layer2.output.shape,
weight_shape=(10, None, 2, 1),
act_type='relu')
chord_classifier = optimus.Conv3D(
name='chord_classifier',
input_shape=layer3.output.shape,
weight_shape=(13, None, 1, 1),
act_type='linear')
flatten = optimus.Flatten('flatten', 2)
null_classifier = optimus.Affine(
name='null_classifier',
input_shape=layer3.output.shape,
output_shape=(None, 1),
act_type='linear')
cat = optimus.Concatenate('concatenate', num_inputs=2, axis=1)
softmax = optimus.Softmax('softmax')
param_nodes = [layer0, layer1, layer2, layer3,
null_classifier, chord_classifier]
misc_nodes = [flatten, cat, softmax]
# 1.1 Create Loss
likelihoods = optimus.SelectIndex(name='likelihoods')
log = optimus.Log(name='log')
neg = optimus.Gain(name='gain')
neg.weight.value = -1.0
loss = optimus.Mean(name='negative_log_likelihood')
loss_nodes = [likelihoods, log, neg, loss]
total_loss = optimus.Output(name='total_loss')
layer0.enable_dropout()
layer1.enable_dropout()
layer2.enable_dropout()
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(layer3.output, null_classifier.input),
(chord_classifier.output, flatten.input),
(flatten.output, cat.input_0),
(null_classifier.output, cat.input_1),
(cat.output, softmax.input)]
trainer_edges = optimus.ConnectionManager(
base_edges + [
(dropout, layer0.dropout),
(dropout, layer1.dropout),
(dropout, layer2.dropout),
(softmax.output, likelihoods.input),
(chord_idx, likelihoods.index),
(likelihoods.output, log.input),
(log.output, neg.input),
(neg.output, loss.input),
(loss.output, total_loss)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes[:-1]) +
map(lambda n: (learning_rate, n.bias), param_nodes[:-1]))
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate, dropout],
nodes=param_nodes + misc_nodes + loss_nodes,
connections=trainer_edges.connections,
outputs=[total_loss],
loss=total_loss,
updates=update_manager.connections,
verbose=True)
classifier_init(param_nodes[:-1])
semitones = L.semitone_matrix(157)[:13, 2:]
chord_classifier.weights.value = semitones.reshape(13, 10, 1, 1)
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager(
base_edges + [(softmax.output, posterior)])
layer0.disable_dropout()
layer1.disable_dropout()
layer2.disable_dropout()
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
return trainer, predictor
def wcqt_likelihood_wmoia(n_dim=VOCAB):
input_data = optimus.Input(
name='cqt',
shape=(None, 6, TIME_DIM, 40))
target = optimus.Input(
name='target',
shape=(None, 1))
chord_idx = optimus.Input(
name='chord_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(32, None, 5, 5),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 7),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 6),
act_type='relu')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 1024,),
act_type='relu')
chord_estimator = optimus.Affine(
name='chord_estimator',
input_shape=layer3.output.shape,
output_shape=(None, n_dim),
act_type='sigmoid')
param_nodes = [layer0, layer1, layer2, layer3, chord_estimator]
# 1.1 Create Loss
likelihoods = optimus.SelectIndex('select')
dimshuffle = optimus.Dimshuffle('dimshuffle', (0, 'x'))
error = optimus.SquaredEuclidean(name='squared_error')
main_loss = optimus.Mean(name='mean_squared_error')
loss_nodes1 = [likelihoods, dimshuffle, error, main_loss]
negone = optimus.Gain(name='negate')
negone.weight.value = -1.0
summer = optimus.Add(name='moia_sum')
flatten = optimus.Sum('flatten', axis=1)
dimshuffle2 = optimus.Dimshuffle('dimshuffle2', (0, 'x'))
margin = optimus.RectifiedLinear(name='margin')
weight = optimus.Multiply(name="margin_weight")
margin_loss = optimus.Mean(name='margin_loss', axis=None)
loss_nodes2 = [negone, summer, margin, flatten,
dimshuffle2, margin_loss, weight]
total_loss = optimus.Add("total_loss")
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_estimator.input)]
trainer_edges = optimus.ConnectionManager(
base_edges + [
(chord_estimator.output, likelihoods.input),
(chord_idx, likelihoods.index),
(likelihoods.output, dimshuffle.input),
(dimshuffle.output, error.input_a),
(target, error.input_b),
(error.output, main_loss.input),
# Margin loss
(dimshuffle.output, negone.input),
(negone.output, summer.input_list),
(chord_estimator.output, summer.input_list),
(summer.output, margin.input),
(margin.output, flatten.input),
(flatten.output, dimshuffle2.input),
(dimshuffle2.output, weight.input_a),
(target, weight.input_b),
(weight.output, margin_loss.input),
(margin_loss.output, total_loss.input_list),
(main_loss.output, total_loss.input_list)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
all_nodes = param_nodes + loss_nodes1 + loss_nodes2 + [total_loss]
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, target, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[total_loss.output],
loss=total_loss.output,
updates=update_manager.connections,
verbose=True)
for n in param_nodes:
for p in n.params.values():
optimus.random_init(p)
posterior = optimus.Output(
name='posterior')
predictor_edges = optimus.ConnectionManager(
base_edges + [(chord_estimator.output, posterior)])
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
return trainer, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(
name='cqt',
shape=(None, 1, TIME_DIM, 252))
target_chroma = optimus.Input(
name='target_chroma',
shape=(None, 12),)
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 7, 15),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 6, 15),
act_type='relu')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 512,),
act_type='relu')
layer4 = optimus.Affine(
name='layer4',
input_shape=layer3.output.shape,
output_shape=(None, 12,),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3, layer4]
# 1.1 Create Losses
chroma_xentropy = optimus.CrossEntropy(
name="chroma_xentropy")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, layer4.input),
(layer4.output, chroma_xentropy.prediction),
(target_chroma, chroma_xentropy.target)])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights),
(learning_rate, layer0.bias),
(learning_rate, layer1.weights),
(learning_rate, layer1.bias),
(learning_rate, layer2.weights),
(learning_rate, layer2.bias),
(learning_rate, layer3.weights),
(learning_rate, layer3.bias),
(learning_rate, layer4.weights),
(learning_rate, layer4.bias)])
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, target_chroma, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chroma_xentropy],
updates=update_manager.connections)
optimus.random_init(layer0.weights)
optimus.random_init(layer1.weights)
optimus.random_init(layer2.weights)
optimus.random_init(layer3.weights)
optimus.random_init(layer4.weights)
validator = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, target_chroma],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chroma_xentropy])
chroma_out = optimus.Output(
name='chroma')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, layer4.input),
(layer4.output, chroma_out)])
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[chroma_out])
# 3. Create Data
stash = biggie.Stash(args.training_file)
stream = S.minibatch(
D.uniform_quality_chroma_stream(stash, TIME_DIM),
batch_size=50)
driver = optimus.Driver(
graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def iX_c3f2_oY(n_in, n_out, size='large'):
# Kernel shapes
k0, k1, k2, k3 = dict(
small=(10, 20, 40, 96),
med=(12, 24, 48, 128),
large=(16, 32, 64, 192),
xlarge=(20, 40, 80, 256),
xxlarge=(24, 48, 96, 512))[size]
# Input dimensions
n0, n1, n2 = {
1: (1, 1, 1),
4: (3, 2, 1),
8: (5, 3, 2),
10: (3, 3, 1),
20: (5, 5, 1)}[n_in]
# Pool shapes
p0, p1, p2 = {
1: (1, 1, 1),
4: (1, 1, 1),
8: (1, 1, 1),
10: (2, 2, 1),
12: (2, 2, 1),
20: (2, 2, 2)}[n_in]
input_data = optimus.Input(
name='cqt',
shape=(None, 1, n_in, 192))
input_data_2 = optimus.Input(
name='cqt_2',
shape=(None, 1, n_in, 192))
score = optimus.Input(
name='score',
shape=(None,))
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
sim_margin = optimus.Input(
name='sim_margin',
shape=None)
diff_margin = optimus.Input(
name='diff_margin',
shape=None)
inputs = [input_data, input_data_2, score, learning_rate,
sim_margin, diff_margin]
# 1.2 Create Nodes
logscale = optimus.Log("logscale", 1.0)
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(k0, None, n0, 13),
pool_shape=(p0, 2),
act_type='tanh')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, n1, 11),
pool_shape=(p1, 2),
act_type='tanh')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, n2, 9),
pool_shape=(p2, 2),
act_type='tanh')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, k3),
act_type='tanh')
layer4 = optimus.Affine(
name='layer4',
input_shape=layer3.output.shape,
output_shape=(None, n_out),
act_type='linear')
param_nodes = [layer0, layer1, layer2, layer3, layer4]
# 1.1 Create cloned nodes
logscale_2 = logscale.clone("logscale_2")
layer0_2 = layer0.clone('layer0_2')
layer1_2 = layer1.clone('layer1_2')
layer2_2 = layer2.clone('layer2_2')
layer3_2 = layer3.clone('layer3_2')
layer4_2 = layer4.clone('layer4_2')
param_nodes_2 = [layer0_2, layer1_2, layer2_2, layer3_2, layer4_2]
# 1.2 Create Loss
# ---------------
# sim_cost = y*hwr(D - sim_margin)^2
# diff_cost = (1 - y) * hwr(diff_margin - D)^2
# total = ave(sim_cost + diff_cost)
sqdistance = optimus.SquaredEuclidean(name='euclidean')
distance = optimus.Sqrt(name='sqrt')
# Sim terms
sim_margin_sum = optimus.Add(name="sim_margin_sum", num_inputs=2)
sim_hwr = optimus.RectifiedLinear(name="sim_hwr")
sim_sqhwr = optimus.Power(name='sim_sqhwr', exponent=2.0)
sim_cost = optimus.Product(name="sim_cost")
# Diff terms
neg_distance = optimus.Multiply(name='neg_distance', weight_shape=None)
neg_distance.weight.value = -1.0
diff_margin_sum = optimus.Add(name="diff_margin_sum", num_inputs=2)
diff_hwr = optimus.RectifiedLinear(name="diff_hwr")
diff_sqhwr = optimus.Power(name='diff_sqhwr', exponent=2.0)
pos_one = optimus.Constant(name='pos_one', shape=None)
pos_one.data.value = 1.0
neg_score = optimus.Multiply(name='neg_score', weight_shape=None)
neg_score.weight.value = -1.0
diff_selector = optimus.Add("diff_selector", num_inputs=2)
diff_cost = optimus.Product(name='diff_cost')
total_cost = optimus.Add('total_cost', num_inputs=2)
loss = optimus.Mean(name='loss')
loss_nodes = [sqdistance, distance,
sim_margin_sum, sim_hwr, sim_sqhwr, sim_cost,
neg_distance, diff_margin_sum, diff_hwr, diff_sqhwr,
pos_one, neg_score, diff_selector, diff_cost,
total_cost, loss]
# Graph outputs
total_loss = optimus.Output(name='total_loss')
embedding = optimus.Output(name='embedding')
embedding_2 = optimus.Output(name='embedding_2')
# 2. Define Edges
base_edges = [
(input_data, logscale.input),
(logscale.output, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, layer4.input),
(layer4.output, embedding)]
base_edges_2 = [
(input_data_2, logscale_2.input),
(logscale_2.output, layer0_2.input),
(layer0_2.output, layer1_2.input),
(layer1_2.output, layer2_2.input),
(layer2_2.output, layer3_2.input),
(layer3_2.output, layer4_2.input),
(layer4_2.output, embedding_2)]
cost_edges = [
(layer4.output, sqdistance.input_a),
(layer4_2.output, sqdistance.input_b),
(sqdistance.output, distance.input),
# Sim terms
(score, sim_cost.input_a),
(distance.output, sim_margin_sum.input_0),
(sim_margin, sim_margin_sum.input_1),
(sim_margin_sum.output, sim_hwr.input),
(sim_hwr.output, sim_sqhwr.input),
(sim_sqhwr.output, sim_cost.input_b),
(sim_cost.output, total_cost.input_0),
# Diff terms
# - margin term
(distance.output, neg_distance.input),
(diff_margin, diff_margin_sum.input_0),
(neg_distance.output, diff_margin_sum.input_1),
(diff_margin_sum.output, diff_hwr.input),
(diff_hwr.output, diff_sqhwr.input),
# - score selector
(score, neg_score.input),
(pos_one.output, diff_selector.input_0),
(neg_score.output, diff_selector.input_1),
# - product
(diff_selector.output, diff_cost.input_a),
(diff_sqhwr.output, diff_cost.input_b),
(diff_cost.output, total_cost.input_1)]
trainer_edges = optimus.ConnectionManager(
base_edges + base_edges_2 + cost_edges + [
# Combined
(total_cost.output, loss.input),
(loss.output, total_loss)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
param_init(param_nodes)
misc_nodes = [logscale, logscale_2]
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=inputs,
nodes=param_nodes + param_nodes_2 + loss_nodes + misc_nodes,
connections=trainer_edges.connections,
outputs=[total_loss, embedding, embedding_2],
loss=total_loss,
updates=update_manager.connections,
verbose=False)
pw_cost = optimus.Output(name='pw_cost')
zerofilt_edges = optimus.ConnectionManager(
base_edges + base_edges_2 + cost_edges + [
# Combined
(total_cost.output, pw_cost)])
zerofilter = optimus.Graph(
name=GRAPH_NAME + "_zerofilter",
inputs=[input_data, input_data_2, score, sim_margin, diff_margin],
nodes=param_nodes + param_nodes_2 + loss_nodes[:-1] + misc_nodes,
connections=zerofilt_edges.connections,
outputs=[pw_cost, embedding, embedding_2],
verbose=False)
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + [logscale],
connections=optimus.ConnectionManager(base_edges).connections,
outputs=[embedding],
verbose=False)
return trainer, predictor, zerofilter
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(
name='cqt',
shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(
name='chord_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
limiter_weight = optimus.Input(
name='limiter_weight',
shape=None)
likelihood_threshold = optimus.Input(
name='likelihood_threshold',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 7, 15),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 6, 15),
act_type='relu')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 512,),
act_type='relu')
chord_classifier = optimus.Softmax(
name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(
name="chord_nll")
max_likelihood = optimus.Max(
name="max_likelihood")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx),
(chord_classifier.output, max_likelihood.input),
(limiter_weight, max_likelihood.weight),
(likelihood_threshold, max_likelihood.threshold)])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights),
(learning_rate, layer0.bias),
(learning_rate, layer1.weights),
(learning_rate, layer1.bias),
(learning_rate, layer2.weights),
(learning_rate, layer2.bias),
(learning_rate, layer3.weights),
(learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)])
print "Trainer"
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate,
limiter_weight, likelihood_threshold],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll, max_likelihood],
updates=update_manager.connections)
optimus.random_init(chord_classifier.weights)
print "Validator"
validator = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, limiter_weight, likelihood_threshold],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll, max_likelihood])
posterior = optimus.Output(
name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)])
print "Predictor"
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
stash = biggie.Stash(args.training_file)
stream = S.minibatch(
D.create_uniform_quality_stream(stash, TIME_DIM, vocab_dim=VOCAB),
batch_size=50)
driver = optimus.Driver(
graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE,
likelihood_threshold.name: LIKELIHOOD_THRESHOLD,
limiter_weight.name: LIMITER_WEIGHT}
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
target_chroma = optimus.Input(
name='target_chroma',
shape=(None, 12),
)
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 3, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 3, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 1, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
12,
),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3]
# 1.1 Create Losses
chroma_xentropy = optimus.CrossEntropy(name="chroma_xentropy")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chroma_xentropy.prediction),
(target_chroma, chroma_xentropy.target)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, target_chroma, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chroma_xentropy],
updates=update_manager.connections)
optimus.random_init(layer0.weights)
optimus.random_init(layer1.weights)
optimus.random_init(layer2.weights)
optimus.random_init(layer3.weights)
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, target_chroma],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chroma_xentropy])
chroma_out = optimus.Output(name='chroma')
predictor_edges = optimus.ConnectionManager([(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chroma_out)])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[chroma_out])
# 3. Create Data
source = optimus.Queue(optimus.File(args.training_file),
transformers=[
T.chord_sample(input_data.shape[2]),
T.pitch_shift(8), T.map_to_chroma
],
**SOURCE_ARGS)
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
driver.fit(source, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def iXc3_fc_nll(n_in, size='large', use_dropout=False):
k0, k1, k2 = dict(
small=(10, 20, 40),
med=(12, 24, 48),
large=(16, 32, 64),
xlarge=(20, 40, 80),
xxlarge=(24, 48, 96))[size]
n0, n1, n2 = {
1: (1, 1, 1),
4: (3, 2, 1),
8: (5, 3, 2),
10: (3, 3, 1),
20: (5, 5, 1)}[n_in]
p0, p1, p2 = {
1: (1, 1, 1),
4: (1, 1, 1),
8: (1, 1, 1),
10: (2, 2, 1),
12: (2, 2, 1),
20: (2, 2, 2)}[n_in]
input_data = optimus.Input(
name='data',
shape=(None, 1, n_in, 252))
chord_idx = optimus.Input(
name='class_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
inputs = [input_data, chord_idx, learning_rate]
dropout = optimus.Input(
name='dropout',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(k0, None, n0, 13),
pool_shape=(p0, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, n1, 37),
pool_shape=(p1, 1),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, n2, 33),
pool_shape=(p2, 1),
act_type='relu')
dropout_edges = []
if use_dropout:
layer0.enable_dropout()
layer1.enable_dropout()
layer2.enable_dropout()
inputs += [dropout]
dropout_edges += [(dropout, layer0.dropout),
(dropout, layer1.dropout),
(dropout, layer2.dropout)]
chord_classifier = optimus.Affine(
name='chord_classifier',
input_shape=layer2.output.shape,
output_shape=(None, VOCAB),
act_type='softmax')
prior = optimus.Multiply("prior", weight_shape=(1, 157), broadcast=[0])
prior.weight.value = np.ones([1, 157])
param_nodes = [layer0, layer1, layer2, chord_classifier]
misc_nodes = [prior]
# 1.1 Create Loss
nll = optimus.NegativeLogLikelihoodLoss(name='negative_log_likelihood')
total_loss = optimus.Output(name='total_loss')
# features = optimus.Output(name='features')
posterior = optimus.Output(name='posterior')
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, chord_classifier.input),
(chord_classifier.output, prior.input),
(prior.output, posterior)]
trainer_edges = optimus.ConnectionManager(
base_edges + dropout_edges + [
(chord_classifier.output, nll.likelihoods),
(chord_idx, nll.index),
(nll.output, total_loss)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
classifier_init(param_nodes)
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=inputs,
nodes=param_nodes + misc_nodes + [nll],
connections=trainer_edges.connections,
outputs=[total_loss, posterior],
loss=total_loss,
updates=update_manager.connections,
verbose=True)
if use_dropout:
layer0.disable_dropout()
layer1.disable_dropout()
layer2.disable_dropout()
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes,
connections=optimus.ConnectionManager(base_edges).connections,
outputs=[posterior],
verbose=True)
return trainer, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(30, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(50, None, 7, 15),
act_type='relu')
layer2 = optimus.Affine(name='layer2',
input_shape=layer1.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
chord_classifier = optimus.Softmax(name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(name="chord_nll")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll],
updates=update_manager.connections)
for n in all_nodes:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
stash = biggie.Stash(args.training_file)
hyperparams = {learning_rate.name: LEARNING_RATE}
valid_idx = [0]
for q in range(1, 13):
valid_idx.append(q)
stream = S.minibatch(D.create_uniform_quality_stream(
stash, TIME_DIM, vocab_dim=VOCAB, valid_idx=valid_idx),
batch_size=BATCH_SIZE)
driver = optimus.Driver(graph=trainer,
name=args.trial_name + "_c%02d" % q,
output_directory=args.model_directory)
driver.fit(stream,
hyperparams=hyperparams,
max_iter=20000,
**DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def i8x1a3T_nll2(size, use_dropout=False):
k0, k1, k2 = dict(
large=(2048, 2048, 40),)[size]
input_data = optimus.Input(
name='data',
shape=(None, 8, 1, 252))
chord_idx = optimus.Input(
name='class_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
inputs = [input_data, chord_idx, learning_rate]
dropout = optimus.Input(
name='dropout',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Affine(
name='layer0',
input_shape=input_data.shape,
output_shape=(None, k0),
act_type='relu')
layer1 = optimus.Affine(
name='layer1',
input_shape=layer0.output.shape,
output_shape=(None, k1),
act_type='relu')
layer2 = optimus.Affine(
name='layer2',
input_shape=layer1.output.shape,
output_shape=(None, k2, 1, 12),
act_type='relu')
dropout_edges = []
if use_dropout:
layer0.enable_dropout()
layer1.enable_dropout()
layer2.enable_dropout()
inputs += [dropout]
dropout_edges += [(dropout, layer0.dropout),
(dropout, layer1.dropout),
(dropout, layer2.dropout)]
chord_classifier = optimus.Conv3D(
name='chord_classifier',
input_shape=layer2.output.shape,
weight_shape=(13, None, 1, 1),
act_type='linear')
flatten = optimus.Flatten('flatten', 2)
null_classifier = optimus.Affine(
name='null_classifier',
input_shape=layer0.output.shape,
output_shape=(None, 1),
act_type='linear')
cat = optimus.Concatenate('concatenate', num_inputs=2, axis=1)
softmax = optimus.Softmax('softmax')
prior = optimus.Multiply("prior", weight_shape=(1, 157), broadcast=[0])
prior.weight.value = np.ones([1, 157])
param_nodes = [layer0, layer1, layer2, null_classifier, chord_classifier]
misc_nodes = [flatten, cat, softmax, prior]
# 1.1 Create Loss
likelihoods = optimus.SelectIndex(name='likelihoods')
log = optimus.Log(name='log')
neg = optimus.Multiply(name='gain', weight_shape=None)
neg.weight.value = -1.0
loss = optimus.Mean(name='negative_log_likelihood')
loss_nodes = [likelihoods, log, neg, loss]
total_loss = optimus.Output(name='total_loss')
posterior = optimus.Output(name='posterior')
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, chord_classifier.input),
(layer0.output, null_classifier.input),
(chord_classifier.output, flatten.input),
(flatten.output, cat.input_0),
(null_classifier.output, cat.input_1),
(cat.output, softmax.input),
(softmax.output, prior.input),
(prior.output, posterior)]
trainer_edges = optimus.ConnectionManager(
base_edges + dropout_edges + [
(softmax.output, likelihoods.input),
(chord_idx, likelihoods.index),
(likelihoods.output, log.input),
(log.output, neg.input),
(neg.output, loss.input),
(loss.output, total_loss)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
classifier_init(param_nodes)
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=inputs,
nodes=param_nodes + misc_nodes + loss_nodes,
connections=trainer_edges.connections,
outputs=[total_loss, posterior],
loss=total_loss,
updates=update_manager.connections,
verbose=True)
if use_dropout:
layer0.disable_dropout()
layer1.disable_dropout()
layer2.disable_dropout()
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes,
connections=optimus.ConnectionManager(base_edges).connections,
outputs=[posterior],
verbose=True)
return trainer, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(
name='cqt',
shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(
name='chord_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 7, 15),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 6, 15),
act_type='relu')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 512,),
act_type='relu')
chord_classifier = optimus.Softmax(
name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(
name="chord_nll")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx)])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights),
(learning_rate, layer0.bias),
(learning_rate, layer1.weights),
(learning_rate, layer1.bias),
(learning_rate, layer2.weights),
(learning_rate, layer2.bias),
(learning_rate, layer3.weights),
(learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)])
print "Building trainer"
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll],
updates=update_manager.connections)
optimus.random_init(chord_classifier.weights)
print "Building validator"
validator = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll])
posterior = optimus.Output(
name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)])
print "Building predictor"
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Opening Data"
stash = biggie.Stash(args.training_file)
stream = S.minibatch(
D.create_uniform_quality_stream(stash, TIME_DIM),
batch_size=50,
functions=[FX.pitch_shift(), FX.map_to_chord_index(VOCAB)])
driver = optimus.Driver(
graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
print "...aaand we're off!"
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def i8c3_pwmse(size='large'):
k0, k1, k2 = dict(
small=(8, 16, 20),
med=(12, 24, 32),
large=(16, 32, 48))[size]
input_data = optimus.Input(
name='cqt',
shape=(None, 1, 8, 252))
target = optimus.Input(
name='target',
shape=(None, 1))
chord_idx = optimus.Input(
name='chord_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(k0, None, 3, 13),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, 3, 37),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, 3, 33),
act_type='relu')
chord_classifier = optimus.Conv3D(
name='chord_classifier',
input_shape=layer2.output.shape,
weight_shape=(13, None, 2, 1),
act_type='sigmoid')
flatten = optimus.Flatten('flatten', 2)
null_classifier = optimus.Affine(
name='null_classifier',
input_shape=layer2.output.shape,
output_shape=(None, 1),
act_type='sigmoid')
cat = optimus.Concatenate('concatenate', num_inputs=2, axis=1)
param_nodes = [layer0, layer1, layer2, chord_classifier, null_classifier]
misc_nodes = [flatten, cat]
# 1.1 Create Loss
likelihoods = optimus.SelectIndex(name='likelihoods')
dimshuffle = optimus.Dimshuffle('dimshuffle', (0, 'x'))
squared_error = optimus.SquaredEuclidean(name='squared_error')
loss = optimus.Mean(name='mean_squared_error')
loss_nodes = [likelihoods, dimshuffle, squared_error, loss]
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, chord_classifier.input),
(layer2.output, null_classifier.input),
(chord_classifier.output, flatten.input),
(flatten.output, cat.input_0),
(null_classifier.output, cat.input_1)]
trainer_edges = optimus.ConnectionManager(
base_edges + [
(cat.output, likelihoods.input),
(chord_idx, likelihoods.index),
(likelihoods.output, dimshuffle.input),
(dimshuffle.output, squared_error.input_a),
(target, squared_error.input_b),
(squared_error.output, loss.input)])
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, target, chord_idx, learning_rate],
nodes=param_nodes + misc_nodes + loss_nodes,
connections=trainer_edges.connections,
outputs=[loss.output],
loss=loss.output,
updates=update_manager.connections,
verbose=True)
classifier_init(param_nodes)
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager(
base_edges + [(cat.output, posterior)])
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
return trainer, predictor
def iXc3_rbf_weighted(n_in, size='large', use_dropout=False):
k0, k1, k2 = dict(
small=(10, 20, 40),
med=(12, 24, 48),
large=(16, 32, 64),
xlarge=(20, 40, 80),
xxlarge=(24, 48, 96))[size]
n0, n1, n2 = {
1: (1, 1, 1),
4: (3, 2, 1),
8: (5, 3, 2),
10: (3, 3, 1),
20: (5, 5, 1)}[n_in]
p0, p1, p2 = {
1: (1, 1, 1),
4: (1, 1, 1),
8: (1, 1, 1),
10: (2, 2, 1),
12: (2, 2, 1),
20: (2, 2, 2)}[n_in]
input_data = optimus.Input(
name='data',
shape=(None, 1, n_in, 252))
chord_idx = optimus.Input(
name='class_idx',
shape=(None,),
dtype='int32')
class_weight = optimus.Input(
name='class_weight',
shape=(None,))
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
inputs = [input_data, chord_idx, class_weight, learning_rate]
dropout = optimus.Input(
name='dropout',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(k0, None, n0, 13),
pool_shape=(p0, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, n1, 37),
pool_shape=(p1, 1),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, n2, 33),
pool_shape=(p2, 1),
act_type='relu')
trainer_edges = []
if use_dropout:
layer0.enable_dropout()
layer1.enable_dropout()
layer2.enable_dropout()
inputs += [dropout]
trainer_edges += [(dropout, layer0.dropout),
(dropout, layer1.dropout),
(dropout, layer2.dropout)]
predictors = []
softmaxes = []
for name in 'EADGBe':
predictors.append(optimus.Affine(
name='{0}_predictor'.format(name),
input_shape=layer2.output.shape,
output_shape=(None, NUM_FRETS),
act_type='linear'))
softmaxes.append(optimus.Softmax('{0}_softmax'.format(name)))
stack = optimus.Stack('stacker', num_inputs=6, axes=(1, 0, 2))
param_nodes = [layer0, layer1, layer2] + predictors
misc_nodes = [stack] + softmaxes
# 1.1 Create Loss
rbf = optimus.RadialBasis(
name='rbf',
input_shape=(None, 6, NUM_FRETS),
output_shape=(None, 157))
inverter = optimus.Multiply(name='inverter', weight_shape=None)
inverter.weight.value = -1.0
class_softmax = optimus.Softmax("class_softmax")
energies = optimus.SelectIndex(name='energies')
importance = optimus.Product(name='importance_weighting')
ave_loss = optimus.Mean(name='ave_loss')
total_loss = optimus.Output(name='total_loss')
# 2. Define Edges
base_edges = [
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input)]
for p, smax in zip(predictors, softmaxes):
base_edges += [(layer2.output, p.input),
(p.output, smax.input)]
base_edges += [(softmaxes[0].output, stack.input_0),
(softmaxes[1].output, stack.input_1),
(softmaxes[2].output, stack.input_2),
(softmaxes[3].output, stack.input_3),
(softmaxes[4].output, stack.input_4),
(softmaxes[5].output, stack.input_5)]
trainer_edges += base_edges + [
(stack.output, rbf.input),
(rbf.output, energies.input),
(rbf.output, inverter.input),
(chord_idx, energies.index),
(energies.output, importance.input_a),
(class_weight, importance.input_b),
(importance.output, ave_loss.input),
(ave_loss.output, total_loss)]
update_manager = optimus.ConnectionManager(
map(lambda n: (learning_rate, n.weights), param_nodes) +
map(lambda n: (learning_rate, n.bias), param_nodes))
classifier_init(param_nodes)
train_nodes = [rbf, inverter, energies, importance, ave_loss]
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=inputs,
nodes=param_nodes + misc_nodes + train_nodes,
connections=optimus.ConnectionManager(trainer_edges).connections,
outputs=[total_loss],
loss=total_loss,
updates=update_manager.connections,
verbose=True)
if use_dropout:
layer0.disable_dropout()
layer1.disable_dropout()
layer2.disable_dropout()
fretboard = optimus.Output(name='fretboard')
fret_predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes,
connections=optimus.ConnectionManager(
base_edges + [(stack.output, fretboard)]).connections,
outputs=[fretboard],
verbose=True)
posterior = optimus.Output(name='posterior')
classifier_edges = base_edges + [
(stack.output, rbf.input),
(rbf.output, inverter.input),
(inverter.output, class_softmax.input),
(class_softmax.output, posterior)]
classifier = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=param_nodes + misc_nodes + [rbf, inverter, class_softmax],
connections=optimus.ConnectionManager(classifier_edges).connections,
outputs=[posterior],
verbose=True)
return trainer, fret_predictor, classifier
def nlse_iX_c3f2_oY(n_in, n_out, size='large', verbose=False):
"""Variable length input, 5-layer model.
Parameters
----------
n_in : int
Length of input window, in [1, 4, 8, 10, 20].
n_out : int
Numer of output dimensions.
size : str
One of ['small', 'med', 'large', 'xlarge', 'xxlarge']
Returns
-------
trainer, predictor, zero_filt : optimus.Graphs
Fully operational optimus graphs.
"""
# Kernel shapes
k0, k1, k2, k3 = dict(small=(10, 20, 40, 96),
med=(12, 24, 48, 128),
large=(16, 32, 64, 192),
xlarge=(20, 40, 80, 256),
xxlarge=(24, 48, 96, 512))[size]
# Input dimensions
n0, n1, n2 = {
1: (1, 1, 1),
4: (3, 2, 1),
8: (5, 3, 2),
10: (3, 3, 1),
20: (5, 5, 1)
}[n_in]
# Pool shapes
p0, p1, p2 = {
1: (1, 1, 1),
4: (1, 1, 1),
8: (1, 1, 1),
10: (2, 2, 1),
12: (2, 2, 1),
20: (2, 2, 2)
}[n_in]
# Inputs
# ------
x_in = optimus.Input(name='x_in', shape=(None, 1, n_in, 192))
x_same = optimus.Input(name='x_same', shape=x_in.shape)
x_diff = optimus.Input(name='x_diff', shape=x_in.shape)
learning_rate = optimus.Input(name='learning_rate', shape=None)
margin_same = optimus.Input(name='margin_same', shape=None)
margin_diff = optimus.Input(name='margin_diff', shape=None)
origin_penalty = optimus.Input(name='origin_penalty', shape=None)
inputs = [
x_in, x_same, x_diff, learning_rate, margin_same, margin_diff,
origin_penalty
]
# 1.2 Create Nodes
logscale = optimus.Log(name="logscale", epsilon=1.0, gain=50.0)
layer0 = optimus.Conv3D(name='layer0',
input_shape=x_in.shape,
weight_shape=(k0, None, n0, 13),
pool_shape=(p0, 1),
act_type='tanh')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(k1, None, n1, 11),
pool_shape=(p1, 1),
act_type='tanh')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(k2, None, n2, 9),
pool_shape=(p2, 1),
act_type='tanh')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, k3),
act_type='tanh')
layer4 = optimus.Affine(name='layer4',
input_shape=layer3.output.shape,
output_shape=(None, n_out),
act_type='linear')
param_nodes = [layer0, layer1, layer2, layer3, layer4]
# 1.1 Create cloned nodes
logscale_scopy = logscale.clone("logscale_scopy")
logscale_dcopy = logscale.clone("logscale_dcopy")
nodes_same = [l.clone(l.name + "_scopy") for l in param_nodes]
nodes_diff = [l.clone(l.name + "_dcopy") for l in param_nodes]
# 1.2 Create Loss
# ---------------
cost_same = optimus.Euclidean(name='cost_same')
cost_diff = optimus.Euclidean(name='cost_diff')
# Sim terms
criterion = optimus.ContrastiveMargin(name='contrastive_margin')
decay = optimus.WeightDecayPenalty(name='decay')
total_loss = optimus.Add(name='total_loss', num_inputs=2)
loss_nodes = [cost_same, cost_diff, criterion, decay, total_loss]
# Graph outputs
loss = optimus.Output(name='loss')
z_out = optimus.Output(name='z_out')
# 2. Define Edges
base_edges = [(x_in, logscale.input), (logscale.output, layer0.input),
(layer0.output, layer1.input), (layer1.output, layer2.input),
(layer2.output, layer3.input), (layer3.output, layer4.input),
(layer4.output, z_out)]
base_edges_same = [(x_same, logscale_scopy.input),
(logscale_scopy.output, nodes_same[0].input),
(nodes_same[0].output, nodes_same[1].input),
(nodes_same[1].output, nodes_same[2].input),
(nodes_same[2].output, nodes_same[3].input),
(nodes_same[3].output, nodes_same[4].input)]
base_edges_diff = [(x_diff, logscale_dcopy.input),
(logscale_dcopy.output, nodes_diff[0].input),
(nodes_diff[0].output, nodes_diff[1].input),
(nodes_diff[1].output, nodes_diff[2].input),
(nodes_diff[2].output, nodes_diff[3].input),
(nodes_diff[3].output, nodes_diff[4].input)]
cost_edges = [(param_nodes[-1].output, cost_same.input_a),
(nodes_same[-1].output, cost_same.input_b),
(param_nodes[-1].output, cost_diff.input_a),
(nodes_diff[-1].output, cost_diff.input_b),
(cost_same.output, criterion.cost_sim),
(cost_diff.output, criterion.cost_diff),
(margin_same, criterion.margin_sim),
(margin_diff, criterion.margin_diff),
(criterion.output, total_loss.input_0),
(origin_penalty, decay.weight),
(param_nodes[-1].output, decay.input),
(decay.output, total_loss.input_1),
(total_loss.output, loss)]
trainer_edges = optimus.ConnectionManager(base_edges + base_edges_same +
base_edges_diff + cost_edges)
update_manager = optimus.ConnectionManager(
list(map(lambda n: (learning_rate, n.weights), param_nodes)) +
list(map(lambda n: (learning_rate, n.bias), param_nodes)))
param_init(param_nodes)
misc_nodes = [logscale, logscale_scopy, logscale_dcopy]
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=inputs,
nodes=param_nodes + nodes_same + nodes_diff +
loss_nodes + misc_nodes,
connections=trainer_edges.connections,
outputs=[loss, z_out],
loss=loss,
updates=update_manager.connections,
verbose=verbose)
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[x_in],
nodes=param_nodes + [logscale],
connections=optimus.ConnectionManager(base_edges).connections,
outputs=[z_out],
verbose=verbose)
return trainer, predictor
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt',
shape=(None, 1, TIME_DIM, PITCH_DIM))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(32, 1, 5, 19),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
chord_classifier = optimus.Softmax(name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_mce = optimus.ClassificationError(name="chord_mce")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_mce.prediction),
(chord_idx, chord_mce.target_idx)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_mce],
updates=update_manager.connections)
for n in all_nodes:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
if args.init_param_file:
trainer.load_param_values(args.init_param_file)
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
synth_stash = biggie.Stash(args.secondary_source)
stream = D.muxed_uniform_chord_stream(stash,
synth_stash,
TIME_DIM,
pitch_shift=0,
vocab_dim=VOCAB,
working_size=10)
# stream = D.create_uniform_chord_stream(
# stash, TIME_DIM, pitch_shift=0, vocab_dim=VOCAB, working_size=10)
# if args.secondary_source:
# print "Loading %s" % args.secondary_source
# stash2 = biggie.Stash(args.secondary_source)
# stream2 = D.create_uniform_chord_stream(
# stash2, TIME_DIM, pitch_shift=0, vocab_dim=VOCAB, working_size=5)
# stream = S.mux([stream, stream2], [0.5, 0.5])
stream = S.minibatch(stream, batch_size=BATCH_SIZE)
print "Starting '%s'" % args.trial_name
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(30, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(50, None, 7, 15),
act_type='relu')
layer2 = optimus.Affine(name='layer2',
input_shape=layer1.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
chord_classifier = optimus.Softmax(name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(name="chord_nll")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll],
updates=update_manager.connections,
momentum=None)
for n in all_nodes:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
trainer.load_param_values(
"/media/attic/dl4mir/chord_estimation/models/nll_chord_uniform_2big/synth_data_01/0/classifier-V157-synth_data_01-041750-2014-08-25_21h59m56s.npz"
)
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
stream = D.create_uniform_chord_stream(stash,
TIME_DIM,
pitch_shift=False,
vocab_dim=VOCAB,
working_size=3)
stream = S.minibatch(stream, batch_size=BATCH_SIZE)
print "Starting '%s'" % args.trial_name
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt',
shape=(None, 1, TIME_DIM, PITCH_DIM))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
input_scalar = optimus.Normalize(name='input_scalar',
mode='l2',
scale_factor=50.0)
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(32, 1, 5, 19),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
chord_classifier = optimus.Softmax(name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [
input_scalar, layer0, layer1, layer2, layer3, chord_classifier
]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(name="chord_nll")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, input_scalar.input), (input_scalar.output, layer0.input),
(layer0.output, layer1.input), (layer1.output, layer2.input),
(layer2.output, layer3.input), (layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll],
updates=update_manager.connections)
for n in all_nodes[1:]:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
if args.init_param_file:
param_values = dict(np.load(args.init_param_file))
keys = param_values.keys()
for key in keys:
if chord_classifier.name in key or layer3.name in key:
print "skipping %s" % key
del param_values[key]
trainer.param_values = param_values
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, input_scalar.input), (input_scalar.output, layer0.input),
(layer0.output, layer1.input), (layer1.output, layer2.input),
(layer2.output, layer3.input), (layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
stream = S.minibatch(D.create_uniform_chord_stream(stash,
TIME_DIM,
pitch_shift=0,
vocab_dim=VOCAB,
working_size=10),
batch_size=BATCH_SIZE)
print "Starting '%s'" % args.trial_name
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
chord_idx = optimus.Input(name='chord_idx', shape=(None, ), dtype='int32')
learning_rate = optimus.Input(name='learning_rate', shape=None)
dropout = optimus.Input(name='dropout', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(30, 1, 9, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(50, None, 7, 15),
act_type='relu')
layer2 = optimus.Affine(name='layer2',
input_shape=layer1.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
1024,
),
act_type='relu')
for n in [layer2, layer3]:
n.enable_dropout()
chord_classifier = optimus.Softmax(name='chord_classifier',
input_shape=layer3.output.shape,
n_out=VOCAB,
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
# 1.1 Create Losses
chord_nll = optimus.NegativeLogLikelihood(name="chord_nll")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx), (dropout, layer2.dropout),
(dropout, layer3.dropout)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, chord_classifier.weights),
(learning_rate, chord_classifier.bias)
])
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate, dropout],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll],
updates=update_manager.connections)
for n in all_nodes:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
validator_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, chord_nll.likelihood),
(chord_idx, chord_nll.target_idx)
])
for n in [layer2, layer3]:
n.disable_dropout()
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, chord_idx],
nodes=all_nodes,
connections=validator_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[chord_nll])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
s = D.create_uniform_chord_stream(stash,
TIME_DIM,
pitch_shift=6,
vocab_dim=VOCAB,
working_size=10)
stream = S.minibatch(FX.drop_frames(FX.awgn(s, 0.05), 0.1),
batch_size=BATCH_SIZE)
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE, dropout.name: DROPOUT}
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
print "Starting '%s'" % args.trial_name
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(name='cqt', shape=(None, 1, TIME_DIM, 252))
fret_bitmap = optimus.Input(name='fret_bitmap', shape=(None, 6, FRET_DIM))
learning_rate = optimus.Input(name='learning_rate', shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(name='layer0',
input_shape=input_data.shape,
weight_shape=(12, 1, 3, 19),
pool_shape=(1, 3),
act_type='relu')
layer1 = optimus.Conv3D(name='layer1',
input_shape=layer0.output.shape,
weight_shape=(16, None, 3, 15),
act_type='relu')
layer2 = optimus.Conv3D(name='layer2',
input_shape=layer1.output.shape,
weight_shape=(20, None, 1, 15),
act_type='relu')
layer3 = optimus.Affine(name='layer3',
input_shape=layer2.output.shape,
output_shape=(
None,
512,
),
act_type='relu')
fretboard = optimus.MultiSoftmax(name='fretboard',
input_shape=layer3.output.shape,
output_shape=(None, 6, FRET_DIM),
act_type='linear')
all_nodes = [layer0, layer1, layer2, layer3, fretboard]
# 1.1 Create Losses
mse = optimus.MeanSquaredError(name="mean_squared_error")
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, fretboard.input), (fretboard.output, mse.prediction),
(fret_bitmap, mse.target)
])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights), (learning_rate, layer0.bias),
(learning_rate, layer1.weights), (learning_rate, layer1.bias),
(learning_rate, layer2.weights), (learning_rate, layer2.bias),
(learning_rate, layer3.weights), (learning_rate, layer3.bias),
(learning_rate, fretboard.weights), (learning_rate, fretboard.bias)
])
trainer = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, fret_bitmap, learning_rate],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[mse],
updates=update_manager.connections)
optimus.random_init(fretboard.weights)
validator = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data, fret_bitmap],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
losses=[mse])
posterior = optimus.Output(name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input), (layer0.output, layer1.input),
(layer1.output, layer2.input), (layer2.output, layer3.input),
(layer3.output, fretboard.input), (fretboard.output, posterior)
])
predictor = optimus.Graph(name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
source = optimus.Queue(optimus.File(args.training_file),
transformers=[
T.cqt_sample(input_data.shape[2]),
T.pitch_shift(MAX_FRETS, bins_per_pitch=3),
T.fret_indexes_to_bitmap(FRET_DIM)
],
**SOURCE_ARGS)
driver = optimus.Driver(graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE}
driver.fit(source, hyperparams=hyperparams, **DRIVER_ARGS)
validator_file = path.join(driver.output_directory, args.validator_file)
optimus.save(validator, def_file=validator_file)
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
def main(args):
# 1.1 Create Inputs
input_data = optimus.Input(
name='cqt',
shape=(None, OCTAVE_DIM, TIME_DIM, PITCH_DIM))
chord_idx = optimus.Input(
name='chord_idx',
shape=(None,),
dtype='int32')
learning_rate = optimus.Input(
name='learning_rate',
shape=None)
margin = optimus.Input(
name='margin',
shape=None)
# 1.2 Create Nodes
layer0 = optimus.Conv3D(
name='layer0',
input_shape=input_data.shape,
weight_shape=(32, None, 5, 5),
pool_shape=(2, 3),
act_type='relu')
layer1 = optimus.Conv3D(
name='layer1',
input_shape=layer0.output.shape,
weight_shape=(64, None, 5, 7),
act_type='relu')
layer2 = optimus.Conv3D(
name='layer2',
input_shape=layer1.output.shape,
weight_shape=(128, None, 3, 6),
act_type='relu')
layer3 = optimus.Affine(
name='layer3',
input_shape=layer2.output.shape,
output_shape=(None, 1024,),
act_type='relu')
chord_estimator = optimus.Softmax(
name='chord_estimator',
input_shape=layer3.output.shape,
output_shape=(None, VOCAB,),
act_type='sigmoid')
all_nodes = [layer0, layer1, layer2, layer3, chord_classifier]
log = optimus.Log(name='log')
neg = optimus.Gain(name='gain')
neg.weight = np.array(-1)
energy = optimus.SelectIndex(name='selector')
loss = optimus.Mean(name='total_loss')
# 1.1 Create Losses
chord_margin = optimus.Margin(
name="chord_margin",
mode='max')
# 2. Define Edges
trainer_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_estimator.input),
(chord_estimator.output, log.input),
(log.output, neg.input),
(neg.output, energy.input),
(chord_idx, energy.index),
(energy.output, loss.input)])
update_manager = optimus.ConnectionManager([
(learning_rate, layer0.weights),
(learning_rate, layer0.bias),
(learning_rate, layer1.weights),
(learning_rate, layer1.bias),
(learning_rate, layer2.weights),
(learning_rate, layer2.bias),
(learning_rate, layer3.weights),
(learning_rate, layer3.bias),
(learning_rate, chord_estimator.weights),
(learning_rate, chord_estimator.bias)])
trainer = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data, chord_idx, learning_rate, margin],
nodes=all_nodes,
connections=trainer_edges.connections,
outputs=[optimus.Graph.TOTAL_LOSS],
loss=[loss.output],
updates=update_manager.connections)
for n in all_nodes:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
if args.init_param_file:
print "Loading parameters: %s" % args.init_param_file
trainer.load_param_values(args.init_param_file)
for n in all_nodes[-2:]:
optimus.random_init(n.weights)
optimus.random_init(n.bias)
posterior = optimus.Output(
name='posterior')
predictor_edges = optimus.ConnectionManager([
(input_data, layer0.input),
(layer0.output, layer1.input),
(layer1.output, layer2.input),
(layer2.output, layer3.input),
(layer3.output, chord_classifier.input),
(chord_classifier.output, posterior)])
predictor = optimus.Graph(
name=GRAPH_NAME,
inputs=[input_data],
nodes=all_nodes,
connections=predictor_edges.connections,
outputs=[posterior])
# 3. Create Data
print "Loading %s" % args.training_file
stash = biggie.Stash(args.training_file)
stream = D.create_stash_stream(
stash, TIME_DIM, pitch_shift=0, vocab_dim=VOCAB, pool_size=25)
if args.secondary_source:
stash2 = biggie.Stash(args.secondary_source)
stream2 = D.create_uniform_chord_stream(
stash2, TIME_DIM, pitch_shift=0, vocab_dim=VOCAB, working_size=5)
stream = S.mux([stream, stream2], [0.5, 0.5])
stream = S.minibatch(stream, batch_size=BATCH_SIZE)
print "Starting '%s'" % args.trial_name
driver = optimus.Driver(
graph=trainer,
name=args.trial_name,
output_directory=args.model_directory)
hyperparams = {learning_rate.name: LEARNING_RATE,
margin.name: MARGIN}
predictor_file = path.join(driver.output_directory, args.predictor_file)
optimus.save(predictor, def_file=predictor_file)
driver.fit(stream, hyperparams=hyperparams, **DRIVER_ARGS)