def test_enroll():
# Load the UBM
ubm = GMMMachine.from_hdf5(
pkg_resources.resource_filename("bob.bio.gmm.test",
"data/gmm_ubm.hdf5"))
# Create a GMM object with that UBM
gmm1 = GMM(
number_of_gaussians=2,
enroll_update_means=True,
enroll_update_variances=True,
)
gmm1.ubm = ubm
# Enroll the biometric reference from random features
enroll = utils.random_training_set((20, 45), 5, -5.0, 5.0, seed=seed_value)
biometric_reference = gmm1.enroll(enroll)
assert not biometric_reference.is_similar_to(biometric_reference.ubm)
assert isinstance(biometric_reference, GMMMachine)
reference_file = pkg_resources.resource_filename("bob.bio.gmm.test",
"data/gmm_enrolled.hdf5")
if regenerate_refs:
gmm1.write_biometric_reference(biometric_reference, reference_file)
# Compare to pre-generated file
gmm2 = gmm1.read_biometric_reference(reference_file)
assert biometric_reference.is_similar_to(gmm2)
with tempfile.NamedTemporaryFile(prefix="bob_",
suffix="_bioref.hdf5") as fd:
temp_file = fd.name
gmm1.write_biometric_reference(biometric_reference, temp_file)
assert GMMMachine.from_hdf5(temp_file, ubm).is_similar_to(gmm2)
def test_training():
"""Tests the generation of the UBM."""
# Set a small training iteration count
gmm1 = GMM(
number_of_gaussians=2,
kmeans_training_iterations=5,
ubm_training_iterations=5,
init_seed=seed_value,
kmeans_oversampling_factor=2,
)
train_data = utils.random_training_set((100, 45),
count=5,
minimum=-5.0,
maximum=5.0)
train_data = numpy.vstack(train_data)
# Train the UBM (projector)
gmm1.fit(train_data)
# Test saving and loading of projector
with tempfile.NamedTemporaryFile(prefix="bob_",
suffix="_model.hdf5") as fd:
temp_file = fd.name
gmm1.save_model(temp_file)
reference_file = pkg_resources.resource_filename(
"bob.bio.gmm.test", "data/gmm_ubm.hdf5")
if regenerate_refs:
gmm1.save_model(reference_file)
gmm2 = GMM(number_of_gaussians=2)
gmm2.load_model(temp_file)
ubm_reference = GMMMachine.from_hdf5(reference_file)
assert gmm2.ubm.is_similar_to(ubm_reference)
def test_score():
gmm1 = GMM(number_of_gaussians=2)
gmm1.load_model(
pkg_resources.resource_filename("bob.bio.gmm.test",
"data/gmm_ubm.hdf5"))
biometric_reference = GMMMachine.from_hdf5(
pkg_resources.resource_filename("bob.bio.gmm.test",
"data/gmm_enrolled.hdf5"),
ubm=gmm1.ubm,
)
probe = GMMStats.from_hdf5(
pkg_resources.resource_filename("bob.bio.gmm.test",
"data/gmm_projected.hdf5"))
probe_data = utils.random_array((20, 45), -5.0, 5.0, seed=seed_value)
reference_score = 0.6509
numpy.testing.assert_almost_equal(gmm1.score(biometric_reference, probe),
reference_score,
decimal=5)
multi_refs = gmm1.score_multiple_biometric_references(
[biometric_reference, biometric_reference, biometric_reference], probe)
assert multi_refs.shape == (3, 1), multi_refs.shape
numpy.testing.assert_almost_equal(multi_refs, reference_score, decimal=5)
# With not projected data
numpy.testing.assert_almost_equal(gmm1.score(biometric_reference,
probe_data),
reference_score,
decimal=5)
def test_gmm_ML_1():
"""Trains a GMMMachine with ML_GMMTrainer"""
ar = load_array(
resource_filename("bob.learn.em", "data/faithful.torch3_f64.hdf5"))
gmm_ref = GMMMachine.from_hdf5(
HDF5File(resource_filename("bob.learn.em", "data/gmm_ML.hdf5"), "r"))
for transform in (to_numpy, to_dask_array):
ar = transform(ar)
gmm = loadGMM()
# test rng handling
gmm.convergence_threshold = 0.001
gmm.update_means = True
gmm.update_variances = True
gmm.update_weights = True
gmm.random_state = np.random.RandomState(seed=12345)
gmm = gmm.fit(ar)
gmm = loadGMM()
gmm.convergence_threshold = 0.001
gmm.update_means = True
gmm.update_variances = True
gmm.update_weights = True
# Generate reference
# gmm.save(HDF5File(resource_filename("bob.learn.em", "data/gmm_ML.hdf5"), "w"))
gmm = gmm.fit(ar)
assert_gmm_equal(gmm, gmm_ref)
def load_model(self, ubm_file):
"""Loads the projector (UBM) from a file."""
hdf5file = HDF5File(ubm_file, "r")
logger.debug("Loading model from file '%s'", ubm_file)
# Read the UBM
self.ubm = GMMMachine.from_hdf5(hdf5file)
self.ubm.variance_thresholds = self.variance_threshold
def test_gmm_MAP_1():
# Train a GMMMachine with MAP_GMMTrainer
ar = load_array(
resource_filename("bob.learn.em", "data/faithful.torch3_f64.hdf5"))
# test with rng
gmmprior = GMMMachine.from_hdf5(
HDF5File(resource_filename("bob.learn.em", "data/gmm_ML.hdf5"), "r"))
gmm = GMMMachine.from_hdf5(
HDF5File(resource_filename("bob.learn.em", "data/gmm_ML.hdf5"), "r"),
ubm=gmmprior,
)
gmm.update_means = True
gmm.update_variances = False
gmm.update_weights = False
rng = np.random.RandomState(seed=12345)
gmm.random_state = rng
gmm = gmm.fit(ar)
gmmprior = GMMMachine.from_hdf5(
HDF5File(resource_filename("bob.learn.em", "data/gmm_ML.hdf5"), "r"))
gmm = GMMMachine.from_hdf5(
HDF5File(resource_filename("bob.learn.em", "data/gmm_ML.hdf5"), "r"),
ubm=gmmprior,
)
gmm.update_means = True
gmm.update_variances = False
gmm.update_weights = False
# Generate reference
# gmm.save(HDF5File(resource_filename("bob.learn.em", "data/gmm_MAP.hdf5"), "w"))
gmm_ref = GMMMachine.from_hdf5(
HDF5File(resource_filename("bob.learn.em", "data/gmm_MAP.hdf5"), "r"))
for transform in (to_numpy, to_dask_array):
ar = transform(ar)
gmm = gmm.fit(ar)
np.testing.assert_almost_equal(gmm.means, gmm_ref.means, decimal=3)
np.testing.assert_almost_equal(gmm.variances,
gmm_ref.variances,
decimal=3)
np.testing.assert_almost_equal(gmm.weights, gmm_ref.weights, decimal=3)
def test_projector():
"""Tests the projector."""
# Load the UBM
gmm1 = GMM(number_of_gaussians=2)
gmm1.ubm = GMMMachine.from_hdf5(
pkg_resources.resource_filename("bob.bio.gmm.test",
"data/gmm_ubm.hdf5"))
# Generate and project random feature
feature = utils.random_array((20, 45), -5.0, 5.0, seed=seed_value)
projected = gmm1.project(feature)
assert isinstance(projected, GMMStats)
reference_file = pkg_resources.resource_filename(
"bob.bio.gmm.test", "data/gmm_projected.hdf5")
if regenerate_refs:
projected.save(reference_file)
reference = GMMStats.from_hdf5(reference_file)
assert projected.is_similar_to(reference)
def custom_enrolled_load_fn(self, path):
return GMMMachine.from_hdf5(path, ubm=self)
def read_biometric_reference(self, model_file):
"""Reads an enrolled reference model, which is a MAP GMMMachine."""
return GMMMachine.from_hdf5(HDF5File(model_file, "r"), ubm=self)
def test_GMMMachine():
# Test a GMMMachine basic features
weights = np.array([0.5, 0.5], "float64")
weights2 = np.array([0.6, 0.4], "float64")
means = np.array([[3, 70, 0], [4, 72, 0]], "float64")
means2 = np.array([[3, 7, 0], [4, 72, 0]], "float64")
variances = np.array([[1, 10, 1], [2, 5, 2]], "float64")
variances2 = np.array([[10, 10, 1], [2, 5, 2]], "float64")
varianceThresholds = np.array([[0, 0, 0], [0, 0, 0]], "float64")
varianceThresholds2 = np.array([[0.0005, 0.0005, 0.0005], [0, 0, 0]],
"float64")
# Initializes a GMMMachine
gmm = GMMMachine(n_gaussians=2)
# Sets the weights, means, variances and varianceThresholds and
# Checks correctness
gmm.weights = weights
gmm.means = means
gmm.variances = variances
gmm.variance_thresholds = varianceThresholds
assert gmm.shape == (2, 3)
np.testing.assert_equal(gmm.weights, weights)
np.testing.assert_equal(gmm.means, means)
np.testing.assert_equal(gmm.variances, variances)
np.testing.assert_equal(gmm.variance_thresholds, varianceThresholds)
newMeans = np.array([[3, 70, 2], [4, 72, 2]], "float64")
newVariances = np.array([[1, 1, 1], [2, 2, 2]], "float64")
# Checks particular varianceThresholds-related methods
varianceThresholds1D = np.array([0.3, 1, 0.5], "float64")
gmm.variance_thresholds = varianceThresholds1D
np.testing.assert_equal(gmm.variance_thresholds, varianceThresholds1D)
gmm.variance_thresholds = 0.005
np.testing.assert_equal(gmm.variance_thresholds, 0.005)
gmm.means = newMeans
gmm.variances = newVariances
np.testing.assert_equal(gmm.means, newMeans)
np.testing.assert_equal(gmm.variances, newVariances)
# Checks comparison
gmm2 = deepcopy(gmm)
gmm3 = GMMMachine(n_gaussians=2)
gmm3.weights = weights2
gmm3.means = means
gmm3.variances = variances
gmm3.variance_thresholds = varianceThresholds
gmm4 = GMMMachine(n_gaussians=2)
gmm4.weights = weights
gmm4.means = means2
gmm4.variances = variances
gmm4.variance_thresholds = varianceThresholds
gmm5 = GMMMachine(n_gaussians=2)
gmm5.weights = weights
gmm5.means = means
gmm5.variances = variances2
gmm5.variance_thresholds = varianceThresholds
gmm6 = GMMMachine(n_gaussians=2)
gmm6.weights = weights
gmm6.means = means
gmm6.variances = variances
gmm6.variance_thresholds = varianceThresholds2
assert_gmm_equal(gmm, gmm2)
assert (gmm != gmm2) is False
assert gmm.is_similar_to(gmm2)
assert gmm != gmm3
assert gmm.is_similar_to(gmm3) is False
assert gmm != gmm4
assert gmm.is_similar_to(gmm4) is False
assert gmm != gmm5
assert gmm.is_similar_to(gmm5) is False
assert gmm != gmm6
assert gmm.is_similar_to(gmm6) is False
# Saving and loading
with tempfile.NamedTemporaryFile(suffix=".hdf5") as f:
filename = f.name
gmm.save(HDF5File(filename, "w"))
# Using from_hdf5
gmm1 = GMMMachine.from_hdf5(HDF5File(filename, "r"))
assert type(gmm1.n_gaussians) is np.int64
assert type(gmm1.update_means) is np.bool_
assert type(gmm1.update_variances) is np.bool_
assert type(gmm1.update_weights) is np.bool_
assert type(gmm1.trainer) is str
assert gmm1.ubm is None
assert_gmm_equal(gmm, gmm1)
# Using load
gmm1 = GMMMachine(n_gaussians=gmm.n_gaussians)
gmm1.load(HDF5File(filename, "r"))
assert type(gmm1.n_gaussians) is np.int64
assert type(gmm1.update_means) is np.bool_
assert type(gmm1.update_variances) is np.bool_
assert type(gmm1.update_weights) is np.bool_
assert type(gmm1.trainer) is str
assert gmm1.ubm is None
assert_gmm_equal(gmm, gmm1)
with tempfile.NamedTemporaryFile(suffix=".hdf5") as f:
filename = f.name
gmm.save(filename)
gmm1 = GMMMachine.from_hdf5(filename)
assert_gmm_equal(gmm, gmm1)
# Weights
n_gaussians = 5
machine = GMMMachine(n_gaussians)
default_weights = np.full(shape=(n_gaussians, ),
fill_value=1.0 / n_gaussians)
default_log_weights = np.full(shape=(n_gaussians, ),
fill_value=np.log(1.0 / n_gaussians))
# Test weights getting and setting
np.testing.assert_almost_equal(machine.weights, default_weights)
np.testing.assert_almost_equal(machine.log_weights, default_log_weights)
modified_weights = default_weights
modified_weights[:n_gaussians // 2] = (1 / n_gaussians) / 2
modified_weights[n_gaussians // 2 +
n_gaussians % 2:] = (1 / n_gaussians) * 1.5
# Ensure setter works (log_weights is updated correctly)
machine.weights = modified_weights
np.testing.assert_almost_equal(machine.weights, modified_weights)
np.testing.assert_almost_equal(machine.log_weights,
np.log(modified_weights))
def read_biometric_reference(self, model_file):
"""Reads an enrolled reference model, which is a MAP GMMMachine."""
if self.ubm is None:
raise ValueError(
"You must load a UBM before reading a biometric reference.")
return GMMMachine.from_hdf5(HDF5File(model_file, "r"), ubm=self.ubm)
