def train_plda(iv_file, train_list, val_list, preproc_file,
epochs, ml_md, md_epochs,
output_path, **kwargs):
if preproc_file is not None:
preproc = TransformList.load(preproc_file)
else:
preproc = None
vcr_args = VCR.filter_args(**kwargs)
vcr_train = VCR(iv_file, train_list, preproc, **vcr_args)
x, class_ids = vcr_train.read()
x_val = None
class_ids_val = None
if val_list is not None:
vcr_val = VCR(iv_file, val_list, preproc, **vcr_args)
x_val, class_ids_val = vcr_val.read()
t1 = time.time()
plda_args = F.filter_train_args(**kwargs)
model = F.create_plda(**plda_args)
elbos = model.fit(x, class_ids, x_val=x_val, class_ids_val=class_ids_val,
epochs=epochs, ml_md=ml_md, md_epochs=md_epochs)
logging.info('Elapsed time: %.2f s.' % (time.time()-t1))
model.save(output_path)
elbo = np.vstack(elbos)
num = np.arange(epochs)
elbo = np.vstack((num, elbo)).T
elbo_path=os.path.splitext(output_path)[0] + '.csv'
np.savetxt(elbo_path, elbo, delimiter=',')
def train_be(iv_file, train_list, adapt_iv_file, adapt_list, lda_dim,
plda_type, y_dim, z_dim, epochs, ml_md, md_epochs, w_mu, w_B, w_W,
output_path, **kwargs):
# Read data
logging.info('loading data')
vcr_args = VCR.filter_args(**kwargs)
vcr_train = VCR(iv_file, train_list, None, **vcr_args)
x, class_ids = vcr_train.read()
# Train LDA
logging.info('train LDA')
t1 = time.time()
lda = LDA(lda_dim=lda_dim, name='lda')
lda.fit(x, class_ids)
x_lda = lda.predict(x)
logging.info('LDA elapsed time: %.2f s.' % (time.time() - t1))
# Train centering and whitening
logging.info('train length norm')
t1 = time.time()
lnorm = LNorm(name='lnorm')
lnorm.fit(x_lda)
x_ln = lnorm.predict(x_lda)
logging.info('length norm elapsed time: %.2f s.' % (time.time() - t1))
# Train PLDA
logging.info('train PLDA')
t1 = time.time()
plda = F.create_plda(plda_type, y_dim=y_dim, z_dim=z_dim, name='plda')
elbo = plda.fit(x_ln,
class_ids,
epochs=epochs,
ml_md=ml_md,
md_epochs=md_epochs)
logging.info('PLDA elapsed time: %.2f s.' % (time.time() - t1))
# Save models
logging.info('saving models')
preproc = TransformList(lda)
preproc.append(lnorm)
if not os.path.exists(output_path):
os.makedirs(ouput_path)
preproc.save(output_path + '/lda_lnorm.h5')
plda.save(output_path + '/plda.h5')
num = np.arange(epochs)
elbo = np.vstack((num, elbo)).T
np.savetxt(output_path + '/elbo.csv', elbo, delimiter=',')
#adaptation
vcr = VCR(adapt_iv_file, adapt_list, None)
x, class_ids = vcr.read()
x_lda = lda.predict(x)
lnorm.update_T = False
lnorm.fit(x_lda)
preproc = TransformList(lda)
preproc.append(lnorm)
preproc.save(output_path + '/lda_lnorm_adapt.h5')
x_ln = lnorm.predict(x_lda)
plda_adapt = plda.copy()
elbo = plda.fit(x_ln, class_ids, epochs=epochs)
plda_adapt.weighted_avg_model(plda, w_mu, w_B, w_W)
plda_adapt.save(output_path + '/plda_adapt.h5')
num = np.arange(epochs)
elbo = np.vstack((num, elbo)).T
np.savetxt(output_path + '/elbo_adapt.csv', elbo, delimiter=',')