def __init__(self, primary_classifier, variant_labels):
self._variant_labels = variant_labels
self._variant_models = {}
for label in variant_labels:
model = SimpleGaussianModel()
# KJB - this guy shouldn't have to know so much about models -
# maybe do some kind of cloning from models in the classifier?
model.set_model(primary_classifier.num_features, 'diagonal')
self._variant_models[label] = model
self._primary = primary_classifier
self._variant_classifier = None
def make_model_samplers(means, vars):
"""
>>> SimpleGaussianModel.seed(0)
>>> tuple(int(128 * sampler()) for sampler in text_utils.make_model_samplers((0, 1), (1, 0.5)))
(-23, 130)
>>> tuple(int(128 * sampler()) for sampler in text_utils.make_model_samplers((0, 1, 2), (1, 0.5, 2)))
(89, 119, 511)
"""
assert len(means) == len(vars)
num_classes = len(means)
models = tuple(
SimpleGaussianModel(1, SimpleGaussianModel.DIAGONAL_COVARIANCE)
for i in xrange(num_classes))
for model, mean, var in izip(models, means, vars):
model.set_model((mean, ), (var, ))
samplers = tuple(model.sample for model in models)
assert len(samplers) == num_classes
return samplers
def read_smm(stream, params, _):
covariance_type, num_components, dimension = params
v, smm_means = stream.read_array("means",
rtype=float,
dim=1,
shape=(dimension, ))
if covariance_type is GaussianMixtureModel.FULL_COVARIANCE:
var_dim = 2
var_shape = (dimension, dimension)
else:
assert (covariance_type is GaussianMixtureModel.DIAGONAL_COVARIANCE)
var_dim = 1
var_shape = (dimension, )
v, smm_vars = stream.read_array("vars",
rtype=float,
dim=var_dim,
shape=var_shape)
ret = SimpleGaussianModel(dimension, covariance_type)
ret.set_model(smm_means, smm_vars)
return ret
def make_data_generator(dimension):
# Data generator setup and data generation
target_means = ((1, 1), (2, 2), (3, 3))
target_vars = ((0.1, 0.1), (0.2, 0.2), (0.3, 0.3))
target_durations = (2, 6, 6)
assert len(target_means) == len(target_vars) == len(target_durations)
num_generators = len(target_means)
generators = [
SimpleGaussianModel(dimension, SimpleGaussianModel.DIAGONAL_COVARIANCE)
for i in xrange(num_generators)
]
for (m, tm, tv) in izip(generators, target_means, target_vars):
m.set_model(tm, tv)
SimpleGaussianModel.seed(0)
def obs_generator():
while True:
yield [
m.sample() for m, d in izip(generators, target_durations)
for i in xrange(d)
]
return obs_generator()
def __init__(self, labels, dimension):
super(SimpleClassifier, self).__init__(labels, dimension)
for label in labels:
m = SimpleGaussianModel(dimension,
SimpleGaussianModel.DIAGONAL_COVARIANCE)
self._models[label] = m
def __init__(self, labels, nfeatures):
self.labels = list(labels)
self.nfeatures = nfeatures
self.models = tuple(SimpleGaussianModel(nfeatures, GaussianModelBase.DIAGONAL_COVARIANCE) for _ in self.labels)
self.samples_seen = [0] * len(self.models)
labels = True, False ncomps = 7, 3 nfeatures = numceps # mfcc, with c0: gathered from about 60,000 frames of 'train' data from Ken and Hugh skyping true_means_prime = N.array((-5.5522, -1.0517, 1.0240, 3.1609, 0.5628, -122.5789), dtype=N.float32) true_vars_prime = N.array((26.2238, 26.4064, 59.7242, 35.1180, 47.2471, 3967.2240), dtype=N.float32) false_means_prime = N.array((-9.4634, -5.3991, -4.2773, 1.7494, -0.0822, -228.6211), dtype=N.float32) false_vars_prime = N.array((3.0097, 6.0277, 8.3711, 10.7198, 13.4285, 456.7074), dtype=N.float32) # mfcc, no c0: 20,000 frames of Hugh talking true_means_prime = N.array((-4.8087, 3.9863, -0.5217, 1.3076, 0.7514, -4.6497), dtype=N.float32) true_vars_prime = N.array((26.8496, 32.6631, 32.3662, 24.2963, 36.2244, 34.1555), dtype=N.float32) false_means_prime = N.array((-6.8806, -1.3424, -3.8147, 0.4520, 0.7129, -3.1560), dtype=N.float32) false_vars_prime = N.array((2.7468, 6.2286, 7.4355, 10.1530, 13.3865, 15.9309), dtype=N.float32) true_prime = SimpleGaussianModel(nfeatures, GaussianModelBase.DIAGONAL_COVARIANCE) true_prime.set_model(true_means_prime, true_vars_prime) false_prime = SimpleGaussianModel(nfeatures, GaussianModelBase.DIAGONAL_COVARIANCE) false_prime.set_model(false_means_prime, false_vars_prime) primer = (true_prime, false_prime) GaussianMixtureModel.seed(0) gmm_mgr0 = GmmMgr(ncomps, nfeatures, GaussianModelBase.DIAGONAL_COVARIANCE, primer) gmm_mgr1 = GmmMgr(ncomps, nfeatures, GaussianModelBase.DIAGONAL_COVARIANCE, primer) classify0 = AdaptingGmmClassifier(gmm_mgr0, izip(labels, count())) classify1 = AdaptingGmmClassifier(gmm_mgr1, izip(labels, count())) classify0.set_relevance(333) classify1.set_relevance(333) classify0.set_num_em_iterations(2) classify1.set_num_em_iterations(2)
