whiten_downsample = preprocessor(downsampling, whitening=True)
###################
# Create datasets #
###################
train = LibriSpeechDataset(training_set, n_seconds)
valid = LibriSpeechDataset(validation_set, n_seconds, stochastic=False)
train_generator = (whiten_downsample(batch)
for batch in train.yield_verification_batches(batchsize))
valid_generator = (whiten_downsample(batch)
for batch in valid.yield_verification_batches(batchsize))
################
# Define model #
################
encoder = get_baseline_convolutional_encoder(model_n_filters,
model_embedding_dimension)
siamese = build_siamese_net(encoder, (input_length, 1))
opt = Adam(clipnorm=1.)
siamese.compile(loss=contrastive_loss, optimizer=opt, metrics=['accuracy'])
#################
# Training Loop #
#################
siamese.fit_generator(
generator=train_generator,
steps_per_epoch=evaluate_every_n_batches,
validation_data=valid_generator,
validation_steps=100,
epochs=num_epochs,
workers=multiprocessing.cpu_count(),
use_multiprocessing=True,
y = np.array([speaker_id_mapping[i] for i in y[:, 0]])[:, np.newaxis]
return to_categorical(y, num_classes)
return label_preprocessor_
batch_preprocessor = BatchPreProcessor(
'classifier', preprocess_instances(downsampling),
label_preprocessor(train.num_classes(), speaker_id_mapping))
train_generator = BatchedSequence(train, batch_preprocessor, batchsize)
################
# Define model #
################
classifier = get_baseline_convolutional_encoder(filters, embedding_dimension,
(input_length, 1))
# Add output classification layer
classifier.add(Dense(train.num_classes(), activation='softmax'))
opt = Adam(clipnorm=1.)
classifier.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
#plot_model(classifier, show_shapes=True, to_file=PATH + '/plots/classifier.png')
print(classifier.summary())
#################
# Training Loop #
#################
classifier.fit_generator(
generator=train_generator,
n_seconds,
stochastic=False,
pad=pad)
batch_preprocessor = BatchPreProcessor('siamese',
preprocess_instances(downsampling))
train_generator = (batch_preprocessor(batch)
for batch in train.yield_verification_batches(batchsize))
valid_generator = (batch_preprocessor(batch)
for batch in valid.yield_verification_batches(batchsize))
################
# Define model #
################
encoder = get_baseline_convolutional_encoder(filters,
embedding_dimension,
dropout=dropout)
siamese = build_siamese_net(encoder, (input_length, 1),
distance_metric='uniform_euclidean')
opt = Adam(clipnorm=1.)
siamese.compile(loss='binary_crossentropy',
optimizer=opt,
metrics=['accuracy'])
# plot_model(siamese, show_shapes=True, to_file=PATH + '/plots/siamese.png')
print(siamese.summary())
#################
# Training Loop #
#################
callbacks = [
# First generate custom n-shot classification metric
train = LibriSpeechDataset(training_set, n_seconds)
valid = LibriSpeechDataset(validation_set, n_seconds, stochastic=False)
batch_preprocessor = BatchPreProcessor('siamese',
preprocess_instances(downsampling))
train_generator = (batch_preprocessor(batch)
for batch in train.yield_verification_batches(batchsize))
valid_generator = (batch_preprocessor(batch)
for batch in valid.yield_verification_batches(batchsize))
#################
# Training Loop #
#################
for f, emb, drop in product(filters, embedding, dropout):
# Define model
encoder = get_baseline_convolutional_encoder(f, emb, dropout=drop)
siamese = build_siamese_net(encoder, (input_length, 1))
opt = Adam(clipnorm=1., decay=2e-5)
siamese.compile(loss='binary_crossentropy',
optimizer=opt,
metrics=['accuracy'])
# Train
param_str = 'siamese__filters_{}__embed_{}__drop_{}'.format(f, emb, drop)
print(param_str)
siamese.fit_generator(
generator=train_generator,
steps_per_epoch=evaluate_every_n_batches,
validation_data=valid_generator,
validation_steps=100,
epochs=num_epochs,