def kmeans_initialize(self, force=False):
"""Initializes the K-Means training (non-parallel)."""
output_file = self.m_configuration.kmeans_intermediate_file % 0
if self.m_tool_chain.__check_file__(output_file, force, 1000):
utils.info(
"UBM training: Skipping KMeans initialization since the file '%s' already exists"
% output_file)
else:
# read data
utils.info("UBM training: initializing kmeans")
training_list = self.m_file_selector.training_feature_list()
data = numpy.vstack([
bob.io.load(str(training_list[index]))
for index in utils.quasi_random_indices(
len(training_list), self.m_args.limit_training_examples)
])
# Perform KMeans initialization
kmeans_machine = bob.machine.KMeansMachine(self.m_tool.m_gaussians,
data.shape[1])
# Creates the KMeansTrainer and call the initialization procedure
kmeans_trainer = bob.trainer.KMeansTrainer()
kmeans_trainer.initialize(kmeans_machine, data)
utils.ensure_dir(os.path.dirname(output_file))
kmeans_machine.save(bob.io.HDF5File(output_file, 'w'))
utils.info("UBM training: saved initial KMeans machine to '%s'" %
output_file)
def gmm_initialize(self, force=False):
"""Initializes the GMM calculation with the result of the K-Means algorithm (non-parallel).
This might require a lot of memory."""
output_file = self.m_configuration.gmm_intermediate_file % 0
if self.m_tool_chain.__check_file__(output_file, force, 800):
utils.info("UBM Training: Skipping GMM initialization since '%s' already exists" % output_file)
else:
training_list = self.m_file_selector.training_feature_list()
utils.info("UBM Training: Initializing GMM")
# load KMeans machine
kmeans_machine = bob.machine.KMeansMachine(bob.io.HDF5File(self.m_configuration.kmeans_file))
# read features
data = numpy.vstack([bob.io.load(str(training_list[index])) for index in utils.quasi_random_indices(len(training_list), self.m_args.limit_training_examples)])
# Create initial GMM Machine
gmm_machine = bob.machine.GMMMachine(self.m_tool.m_gaussians, data.shape[1])
[variances, weights] = kmeans_machine.get_variances_and_weights_for_each_cluster(data)
# Initializes the GMM
gmm_machine.means = kmeans_machine.means
gmm_machine.variances = variances
gmm_machine.weights = weights
gmm_machine.set_variance_thresholds(self.m_tool.m_variance_threshold)
utils.ensure_dir(os.path.dirname(output_file))
gmm_machine.save(bob.io.HDF5File(os.path.join(output_file), 'w'))
utils.info("UBM Training: Wrote GMM file '%s'" % output_file)
def gmm_initialize(self, force=False):
"""Initializes the GMM calculation with the result of the K-Means algorithm (non-parallel).
This might require a lot of memory."""
output_file = self.m_configuration.gmm_intermediate_file % 0
if self.m_tool_chain.__check_file__(output_file, force, 800):
utils.info(
"UBM Training: Skipping GMM initialization since '%s' already exists"
% output_file)
else:
training_list = self.m_file_selector.training_feature_list()
utils.info("UBM Training: Initializing GMM")
# load KMeans machine
kmeans_machine = bob.machine.KMeansMachine(
bob.io.HDF5File(self.m_configuration.kmeans_file))
# read features
data = numpy.vstack([
bob.io.load(str(training_list[index]))
for index in utils.quasi_random_indices(
len(training_list), self.m_args.limit_training_examples)
])
# Create initial GMM Machine
gmm_machine = bob.machine.GMMMachine(self.m_tool.m_gaussians,
data.shape[1])
[
variances, weights
] = kmeans_machine.get_variances_and_weights_for_each_cluster(data)
# Initializes the GMM
gmm_machine.means = kmeans_machine.means
gmm_machine.variances = variances
gmm_machine.weights = weights
gmm_machine.set_variance_thresholds(
self.m_tool.m_variance_threshold)
utils.ensure_dir(os.path.dirname(output_file))
gmm_machine.save(bob.io.HDF5File(os.path.join(output_file), 'w'))
utils.info("UBM Training: Wrote GMM file '%s'" % output_file)
def kmeans_initialize(self, force=False):
"""Initializes the K-Means training (non-parallel)."""
output_file = self.m_configuration.kmeans_intermediate_file % 0
if self.m_tool_chain.__check_file__(output_file, force, 1000):
utils.info("UBM training: Skipping KMeans initialization since the file '%s' already exists" % output_file)
else:
# read data
utils.info("UBM training: initializing kmeans")
training_list = self.m_file_selector.training_feature_list()
data = numpy.vstack([bob.io.load(str(training_list[index])) for index in utils.quasi_random_indices(len(training_list), self.m_args.limit_training_examples)])
# Perform KMeans initialization
kmeans_machine = bob.machine.KMeansMachine(self.m_tool.m_gaussians, data.shape[1])
# Creates the KMeansTrainer and call the initialization procedure
kmeans_trainer = bob.trainer.KMeansTrainer()
kmeans_trainer.initialize(kmeans_machine, data)
utils.ensure_dir(os.path.dirname(output_file))
kmeans_machine.save(bob.io.HDF5File(output_file, 'w'))
utils.info("UBM training: saved initial KMeans machine to '%s'" % output_file)