diff --git a/bob/learn/em/test/test_kmeans_trainer.py b/bob/learn/em/test/test_kmeans_trainer.py
index 978ce7234461725d7d96c006eb4ba66c299dd104..2ebf1fd1298b2298093e131153063fc33e6ec5a5 100644
--- a/bob/learn/em/test/test_kmeans_trainer.py
+++ b/bob/learn/em/test/test_kmeans_trainer.py
@@ -184,10 +184,10 @@ def test_trainer_execption():
machine = KMeansMachine(2, 2)
data = numpy.array([[1.0, 2.0], [2, 3.], [1, 1.], [2, 5.], [numpy.inf, 1.0]])
trainer = KMeansTrainer()
- assert_raises(ValueError, bob.learn.em.train, trainer, machine, data, 0.001)
+ assert_raises(ValueError, bob.learn.em.train, trainer, machine, data, 10)
# Testing Nan
machine = KMeansMachine(2, 2)
data = numpy.array([[1.0, 2.0], [2, 3.], [1, numpy.nan], [2, 5.], [2.0, 1.0]])
trainer = KMeansTrainer()
- assert_raises(ValueError, bob.learn.em.train, trainer, machine, data, 0.001)
+ assert_raises(ValueError, bob.learn.em.train, trainer, machine, data, 10)
diff --git a/bob/learn/em/train.py b/bob/learn/em/train.py
index a4263e7830a7e7afeb5e441bf02b056b6725745e..6927015a5ecdd012a643b445f2f6111c30ab6cda 100644
--- a/bob/learn/em/train.py
+++ b/bob/learn/em/train.py
@@ -31,10 +31,12 @@ def train(trainer, machine, data, max_iterations=50, convergence_threshold=None,
If True, runs the initialization procedure
rng : :py:class:`bob.core.random.mt19937`
The Mersenne Twister mt19937 random generator used for the initialization of subspaces/arrays before the EM loop
- check_inputs: Shallow checks in the inputs. Check for inf and NaN
+ check_inputs:
+ Shallow checks in the inputs. Check for inf and NaN
"""
- if check_inputs:
+ if check_inputs and type(data) is numpy.ndarray:
+
if numpy.isinf(numpy.sum(data)):
raise ValueError("Please, check your inputs; numpy.inf detected in `data` ")
diff --git a/doc/guide.rst b/doc/guide.rst
index d85c8a5e831f2062b69ac402afc2db489030c5a7..f506b58ca18627ad272dc74267cb069befe7ea0a 100644
--- a/doc/guide.rst
+++ b/doc/guide.rst
@@ -709,7 +709,7 @@ Z-Norm
======
.. _znorm:
-Given a score :math:`s_i`, Z-Norm (zero-normalisation) scales this value by the
+Given a score :math:`s_i`, Z-Norm [Auckenthaler2000]_ and [Mariethoz2005]_ (zero-normalisation) scales this value by the
mean (:math:`\mu`) and standard deviation (:math:`\sigma`) of an impostor score
distribution. This score distribution can be computed before hand and it is
defined as the following.
@@ -734,7 +734,7 @@ T-Norm
======
.. _tnorm:
-T-norm (Test-normalization) operates in a probe-centric manner. If in the
+T-norm [Auckenthaler2000]_ and [Mariethoz2005]_ (Test-normalization) operates in a probe-centric manner. If in the
Z-Norm :math:`\mu` and :math:`\sigma` are estimated using an impostor set of
models and its scores, the t-norm computes these statistics using the current
probe sample against at set of models in a co-hort :math:`\Theta_{c}`. A co-
@@ -771,7 +771,7 @@ ZT-Norm
=======
.. _ztnorm:
-ZT-Norm consists in the application of :ref:`Z-Norm <znorm>` followed by a
+ZT-Norm [Auckenthaler2000]_ and [Mariethoz2005]_ consists in the application of :ref:`Z-Norm <znorm>` followed by a
:ref:`T-Norm <tnorm>` and it is implemented in :py:func:`bob.learn.em.ztnorm`.
Follow bellow an example of score normalization using
diff --git a/doc/index.rst b/doc/index.rst
index db40d1c611f9e9b6ac90a03dc124d12389fc050b..eab4d4b9b9674f7d06a1ab53d1376493c14febf3 100644
--- a/doc/index.rst
+++ b/doc/index.rst
@@ -44,6 +44,9 @@ References
.. [WikiEM] `Expectation Maximization <http://en.wikipedia.org/wiki/Expectation%E2%80%93maximization_algorithm>`_
.. [Glembek2009] Glembek, Ondrej, et al. "Comparison of scoring methods used in speaker recognition with joint factor analysis." Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on. IEEE, 2009.
+.. [Auckenthaler2000] Auckenthaler, Roland, Michael Carey, and Harvey Lloyd-Thomas. "Score normalization for text-independent speaker verification systems." Digital Signal Processing 10.1 (2000): 42-54.
+.. [Mariethoz2005] Mariethoz, Johnny, and Samy Bengio. "A unified framework for score normalization techniques applied to text-independent speaker verification." IEEE signal processing letters 12.7 (2005): 532-535.
+
Indices and tables
------------------
diff --git a/doc/plot/plot_ISV.py b/doc/plot/plot_ISV.py
index b72cdb16f98364e89a3e8c702970e82df7df470f..855c60154c48373723448b49844036b6da50413e 100755
--- a/doc/plot/plot_ISV.py
+++ b/doc/plot/plot_ISV.py
@@ -7,6 +7,15 @@ numpy.random.seed(2) # FIXING A SEED
def train_ubm(features, n_gaussians):
+ """
+ Train UBM
+
+ **Parameters**
+ features: 2D numpy array with the features
+
+ n_gaussians: Number of Gaussians
+
+ """
input_size = features.shape[1]
kmeans_machine = bob.learn.em.KMeansMachine(int(n_gaussians), input_size)
@@ -38,8 +47,13 @@ def train_ubm(features, n_gaussians):
def isv_train(features, ubm):
"""
- Features com lista de listas [ [data_point_1_user_1,data_point_2_user_1],
- [data_point_1_user_2,data_point_2_user_2] ]
+ Train U matrix
+
+ **Parameters**
+ features: List of :py:class:`bob.learn.em.GMMStats` organized by class
+
+ n_gaussians: UBM (:py:class:`bob.learn.em.GMMMachine`)
+
"""
stats = []
diff --git a/doc/plot/plot_JFA.py b/doc/plot/plot_JFA.py
index 77f4e2ee14e8f7a404f6692eaf5dad92fb24855e..a2b05d5731b3d8aaefd419df0184d0b9daaacf2a 100755
--- a/doc/plot/plot_JFA.py
+++ b/doc/plot/plot_JFA.py
@@ -7,6 +7,16 @@ numpy.random.seed(2) # FIXING A SEED
def train_ubm(features, n_gaussians):
+ """
+ Train UBM
+
+ **Parameters**
+ features: 2D numpy array with the features
+
+ n_gaussians: Number of Gaussians
+
+ """
+
input_size = features.shape[1]
kmeans_machine = bob.learn.em.KMeansMachine(int(n_gaussians), input_size)
@@ -38,8 +48,14 @@ def train_ubm(features, n_gaussians):
def jfa_train(features, ubm):
"""
- Features com lista de listas [ [data_point_1_user_1,data_point_2_user_1], [data_point_1_user_2,data_point_2_user_2] ]
- """
+ Trains U and V matrix
+
+ **Parameters**
+ features: List of :py:class:`bob.learn.em.GMMStats` organized by class
+
+ n_gaussians: UBM (:py:class:`bob.learn.em.GMMMachine`)
+
+ """
stats = []
for user in features:
diff --git a/doc/plot/plot_MAP.py b/doc/plot/plot_MAP.py
index 0c721baead89fd5fa4825f3901168d11bcd33655..0690cf855c4d3ff7f874326133995d023fa5a390 100644
--- a/doc/plot/plot_MAP.py
+++ b/doc/plot/plot_MAP.py
@@ -16,22 +16,17 @@ data = numpy.vstack((setosa, versicolor, virginica))
# Two clusters with a feature dimensionality of 3
mle_machine = bob.learn.em.GMMMachine(3, 2)
-mle_trainer = bob.learn.em.ML_GMMTrainer(True, True, True)
mle_machine.means = numpy.array([[5, 3], [4, 2], [7, 3.]])
-bob.learn.em.train(mle_trainer, mle_machine, data, max_iterations=200,
- convergence_threshold=1e-5) # Train the KMeansMachine
# Creating some random data centered in
-new_data = numpy.random.normal(2, 0.8, (50, 2))
-# Two clusters with a feature dimensionality of 3
map_machine = bob.learn.em.GMMMachine(3, 2)
map_trainer = bob.learn.em.MAP_GMMTrainer(mle_machine, relevance_factor=4)
-bob.learn.em.train(map_trainer, map_machine, new_data, max_iterations=200,
+bob.learn.em.train(map_trainer, map_machine, data, max_iterations=200,
convergence_threshold=1e-5) # Train the KMeansMachine
figure, ax = plt.subplots()
-plt.scatter(new_data[:, 0], new_data[:, 1], c="olivedrab", label="new data")
+#plt.scatter(data[:, 0], data[:, 1], c="olivedrab", label="new data")
plt.scatter(setosa[:, 0], setosa[:, 1], c="darkcyan", label="setosa")
plt.scatter(versicolor[:, 0], versicolor[:, 1],
c="goldenrod", label="versicolor")
diff --git a/doc/plot/plot_iVector.py b/doc/plot/plot_iVector.py
index 8f7d1e1de5442f6838bd79de79270efc9cc75e36..95953d3a2d40c64ca7a08d0dd6eff0d7346524fb 100755
--- a/doc/plot/plot_iVector.py
+++ b/doc/plot/plot_iVector.py
@@ -7,6 +7,16 @@ numpy.random.seed(2) # FIXING A SEED
def train_ubm(features, n_gaussians):
+ """
+ Train UBM
+
+ **Parameters**
+ features: 2D numpy array with the features
+
+ n_gaussians: Number of Gaussians
+
+ """
+
input_size = features.shape[1]
kmeans_machine = bob.learn.em.KMeansMachine(int(n_gaussians), input_size)
@@ -38,9 +48,14 @@ def train_ubm(features, n_gaussians):
def ivector_train(features, ubm):
"""
- Features com lista de listas [ [data_point_1_user_1,data_point_2_user_1],
- [data_point_1_user_2,data_point_2_user_2] ]
- """
+ Trains T matrix
+
+ **Parameters**
+ features: List of :py:class:`bob.learn.em.GMMStats`
+
+ n_gaussians: UBM (:py:class:`bob.learn.em.GMMMachine`)
+
+ """
stats = []
for user in features:
@@ -72,6 +87,9 @@ def acc_stats(data, gmm):
def compute_ivectors(gmm_stats, ivector_machine):
+ """
+ Given :py:class:`bob.learn.em.GMMStats` and an T matrix, get the iVectors.
+ """
ivectors = []
for g in gmm_stats: