diff --git a/bob/learn/misc/MAP_gmm_trainer.cpp b/bob/learn/misc/MAP_gmm_trainer.cpp
index 30cf72901db174808439c4cb90aa7a25546537e8..e9b0fde0b2a70f0a9c3d4ac347930b72a73cafaf 100644
--- a/bob/learn/misc/MAP_gmm_trainer.cpp
+++ b/bob/learn/misc/MAP_gmm_trainer.cpp
@@ -27,7 +27,8 @@ static auto MAP_GMMTrainer_doc = bob::extension::ClassDoc(
)
- .add_prototype("gmm_base_trainer,prior_gmm,[reynolds_adaptation],[relevance_factor],[alpha]","")
+ //.add_prototype("gmm_base_trainer,prior_gmm,[reynolds_adaptation],[relevance_factor],[alpha]","")
+ .add_prototype("gmm_base_trainer, prior_gmm, reynolds_adaptation, [relevance_factor], [alpha]","")
.add_prototype("other","")
.add_prototype("","")
@@ -56,21 +57,24 @@ static int PyBobLearnMiscMAPGMMTrainer_init_copy(PyBobLearnMiscMAPGMMTrainerObje
static int PyBobLearnMiscMAPGMMTrainer_init_base_trainer(PyBobLearnMiscMAPGMMTrainerObject* self, PyObject* args, PyObject* kwargs) {
- char** kwlist = MAP_GMMTrainer_doc.kwlist(1);
+ char** kwlist = MAP_GMMTrainer_doc.kwlist(0);
+
PyBobLearnMiscGMMBaseTrainerObject* gmm_base_trainer;
PyBobLearnMiscGMMMachineObject* gmm_machine;
PyObject* reynolds_adaptation = 0;
double alpha = 0.5;
double relevance_factor = 4.0;
-
- if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O!0!|O!dd", kwlist, &PyBobLearnMiscGMMBaseTrainer_Type, &gmm_base_trainer,
+
+
+ if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O!O!|O!dd", kwlist, &PyBobLearnMiscGMMBaseTrainer_Type, &gmm_base_trainer,
&PyBobLearnMiscGMMMachine_Type, &gmm_machine,
- &PyBool_Type, reynolds_adaptation,
+ &PyBool_Type, &reynolds_adaptation,
&relevance_factor, &alpha )){
+
MAP_GMMTrainer_doc.print_usage();
return -1;
}
-
+
self->cxx.reset(new bob::learn::misc::MAP_GMMTrainer(gmm_base_trainer->cxx, gmm_machine->cxx, f(reynolds_adaptation),relevance_factor, alpha));
return 0;
}
@@ -83,10 +87,11 @@ static int PyBobLearnMiscMAPGMMTrainer_init(PyBobLearnMiscMAPGMMTrainerObject* s
// If the constructor input is GMMBaseTrainer object
if(PyBobLearnMiscMAPGMMTrainer_Check(args))
return PyBobLearnMiscMAPGMMTrainer_init_copy(self, args, kwargs);
- else
+ else{
return PyBobLearnMiscMAPGMMTrainer_init_base_trainer(self, args, kwargs);
+ }
- BOB_CATCH_MEMBER("cannot create GMMMAPTrainer", 0)
+ BOB_CATCH_MEMBER("cannot create MAP_GMMTrainer", 0)
return 0;
}
diff --git a/bob/learn/misc/__MAP_gmm_trainer__.py b/bob/learn/misc/__MAP_gmm_trainer__.py
index e20128df88ca8a7cd2aaea8da360e5a098e5975c..d20efb52311623425d4ff408444b2acfbf744c29 100644
--- a/bob/learn/misc/__MAP_gmm_trainer__.py
+++ b/bob/learn/misc/__MAP_gmm_trainer__.py
@@ -11,7 +11,7 @@ import numpy
# define the class
class MAP_GMMTrainer(_MAP_GMMTrainer):
- def __init__(self, gmm_base_trainer, prior_gmm, convergence_threshold=0.001, max_iterations=10, converge_by_likelihood=True, reynolds_adaptation=False, relevance_factor=4, alpha=0.5):
+ def __init__(self, gmm_base_trainer, prior_gmm, convergence_threshold=0.001, max_iterations=10, converge_by_likelihood=True, reynolds_adaptation=False, relevance_factor=4., alpha=0.5):
"""
:py:class:bob.learn.misc.MAP_GMMTrainer constructor
@@ -35,7 +35,9 @@ class MAP_GMMTrainer(_MAP_GMMTrainer):
"""
- _MAP_GMMTrainer.__init__(self, gmm_base_trainer, prior_gmm, reynolds_adaptation=reynolds_adaptation, relevance_factor=relevance_factor, alpha=alpha)
+ #_MAP_GMMTrainer.__init__(self, gmm_base_trainer, prior_gmm, reynolds_adaptation=reynolds_adaptation, relevance_factor=relevance_factor, alpha=alpha)
+ _MAP_GMMTrainer.__init__(self, gmm_base_trainer, prior_gmm, reynolds_adaptation, relevance_factor=relevance_factor, alpha=alpha)
+
self.convergence_threshold = convergence_threshold
self.max_iterations = max_iterations
self.converge_by_likelihood = converge_by_likelihood
diff --git a/bob/learn/misc/test_em.py b/bob/learn/misc/test_em.py
index 12bc22379382fe2555de80faeea2146c8733acdd..31e510e887ddb14930e04d768b7d31a8bcf9302c 100644
--- a/bob/learn/misc/test_em.py
+++ b/bob/learn/misc/test_em.py
@@ -14,7 +14,7 @@ import bob.io.base
from bob.io.base.test_utils import datafile
from . import KMeansMachine, GMMMachine, KMeansTrainer, \
- GMMBaseTrainer, ML_GMMTrainer
+ GMMBaseTrainer, ML_GMMTrainer, MAP_GMMTrainer
#, MAP_GMMTrainer
@@ -60,13 +60,6 @@ def test_gmm_ML_1():
gmm_ref_32bit_debug = GMMMachine(bob.io.base.HDF5File(datafile('gmm_ML_32bit_debug.hdf5', __name__)))
gmm_ref_32bit_release = GMMMachine(bob.io.base.HDF5File(datafile('gmm_ML_32bit_release.hdf5', __name__)))
-
- print gmm.variance_thresholds
- print gmm_ref.variance_thresholds
- print gmm_ref_32bit_release.variance_thresholds
- print gmm_ref_32bit_release.variance_thresholds
-
-
assert (gmm == gmm_ref) or (gmm == gmm_ref_32bit_release) or (gmm == gmm_ref_32bit_release)
@@ -112,7 +105,7 @@ def test_gmm_ML_2():
assert equals(gmm.weights, weightsML_ref, 1e-4)
-"""
+
def test_gmm_MAP_1():
# Train a GMMMachine with MAP_GMMTrainer
@@ -122,23 +115,22 @@ def test_gmm_MAP_1():
gmm = GMMMachine(bob.io.base.HDF5File(datafile("gmm_ML.hdf5", __name__)))
gmmprior = GMMMachine(bob.io.base.HDF5File(datafile("gmm_ML.hdf5", __name__)))
- map_gmmtrainer = MAP_GMMTrainer(16)
- map_gmmtrainer.set_prior_gmm(gmmprior)
+ map_gmmtrainer = MAP_GMMTrainer(GMMBaseTrainer(True, False, False),gmmprior, reynolds_adaptation=False, relevance_factor=16)
+ #map_gmmtrainer.set_prior_gmm(gmmprior)
map_gmmtrainer.train(gmm, ar)
#config = bob.io.base.HDF5File(datafile('gmm_MAP.hdf5", 'w', __name__))
#gmm.save(config)
gmm_ref = GMMMachine(bob.io.base.HDF5File(datafile('gmm_MAP.hdf5', __name__)))
- #gmm_ref_32bit_release = GMMMachine(bob.io.base.HDF5File(datafile('gmm_MAP_32bit_release.hdf5', __name__)))
assert (equals(gmm.means,gmm_ref.means,1e-3) and equals(gmm.variances,gmm_ref.variances,1e-3) and equals(gmm.weights,gmm_ref.weights,1e-3))
+
def test_gmm_MAP_2():
# Train a GMMMachine with MAP_GMMTrainer and compare with matlab reference
- map_adapt = MAP_GMMTrainer(4., True, False, False, 0.)
data = bob.io.base.load(datafile('data.hdf5', __name__))
data = data.reshape((1, data.shape[0])) # make a 2D array out of it
means = bob.io.base.load(datafile('means.hdf5', __name__))
@@ -150,7 +142,8 @@ def test_gmm_MAP_2():
gmm.variances = variances
gmm.weights = weights
- map_adapt.set_prior_gmm(gmm)
+ map_adapt = MAP_GMMTrainer(GMMBaseTrainer(True, False, False, mean_var_update_responsibilities_threshold=0.),gmm, alpha=4., relevance_factor=4., reynolds_adaptation=True)
+ #map_adapt.set_prior_gmm(gmm)
gmm_adapted = GMMMachine(2,50)
gmm_adapted.means = means
@@ -162,10 +155,14 @@ def test_gmm_MAP_2():
new_means = bob.io.base.load(datafile('new_adapted_mean.hdf5', __name__))
+ # print new_means[0,:]
+ # print gmm_adapted.means[:,0]
+
# Compare to matlab reference
assert equals(new_means[0,:], gmm_adapted.means[:,0], 1e-4)
assert equals(new_means[1,:], gmm_adapted.means[:,1], 1e-4)
+
def test_gmm_MAP_3():
# Train a GMMMachine with MAP_GMMTrainer; compares to old reference
@@ -189,11 +186,9 @@ def test_gmm_MAP_3():
max_iter_gmm = 1
accuracy = 0.00001
map_factor = 0.5
- map_gmmtrainer = MAP_GMMTrainer(relevance_factor, True, False, False, prior)
+ map_gmmtrainer = MAP_GMMTrainer(GMMBaseTrainer(True, False, False, prior), prior_gmm, alpha=map_factor, reynolds_adaptation=False)
map_gmmtrainer.max_iterations = max_iter_gmm
map_gmmtrainer.convergence_threshold = accuracy
- map_gmmtrainer.set_prior_gmm(prior_gmm)
- map_gmmtrainer.set_t3_map(map_factor);
gmm = GMMMachine(n_gaussians, n_inputs)
gmm.set_variance_thresholds(threshold)
@@ -215,6 +210,7 @@ def test_gmm_MAP_3():
assert equals(gmm.variances, variancesMAP_ref, 1e-4)
assert equals(gmm.weights, weightsMAP_ref, 1e-4)
+
def test_gmm_test():
# Tests a GMMMachine by computing scores against a model and compare to
@@ -236,12 +232,12 @@ def test_gmm_test():
# Test against the model
score_mean_ref = -1.50379e+06
score = 0.
- for v in ar: score += gmm.forward(v)
+ for v in ar: score += gmm(v)
score /= len(ar)
# Compare current results to torch3vision
assert abs(score-score_mean_ref)/score_mean_ref<1e-4
-"""
+
def test_custom_trainer():