def test1():
print '============== test1 ============'
dimension = 3
target0 = make_target(dimension, 2, (0.75, 0.25), ((1, 1, 1), (2, 3, 4)), ((1, 1, 1), (0.5, 0.5, 1)))
target1 = make_target(dimension, 2, (0.5, 0.5), ((-1, -1, -1), (-2, -3, -4)), ((1, 1, 1), (0.5, 0.5, 1)))
target2 = make_target(dimension, 2, (0.1, 0.9), ((1, 1, -2), (3, 3, 5)), ((1, 1, 1), (0.5, 0.5, 1)))
print target0
print target1
print target2
GaussianModelBase.seed(0)
labels = ('A', 'B', 'C')
ncomps = (1, 2, 2)
sources = dict((('A', target0), ('B', target1), ('C', target2)))
GaussianMixtureModel.seed(0)
gmm_mgr = GmmMgr(ncomps, dimension, GaussianModelBase.DIAGONAL_COVARIANCE)
c0 = AdaptingGmmClassifier(gmm_mgr, izip(labels, count()))
print
print c0
result = list()
proc0 = AdaptingGmmClassProcessor(c0, result.append)
# Prime things a little bit to try to get a good start
c0.set_relevance(0.001)
c0.set_num_em_iterations(2)
for i in xrange(1):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
proc0.process((label, data))
# Now adapt on more data
c0.set_relevance(10)
c0.set_num_em_iterations(2)
for i in xrange(10):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
proc0.process((label, data))
print
print c0
print
print len(result)
# XXX Win32 gets values off in the last 2-3 hex digits. I'm not sure how to account for this in a
# logref test, so I'm disabling this printing for now.
# for training_label, scores in result[-10:]:
# print training_label, tuple(((label, float_to_readable_string(score)) for score, label in scores))
correct = tuple(label for label, scores in result)
guessed = tuple(scores[0][1] for l, scores in result)
print len(correct), len(guessed)
ind = [c == g for (c, g) in izip(correct, guessed)]
print ind.count(True)
print ind.count(True) / len(correct)
def test1(num_obs, num_passes):
dimension = 2
# Data generator setup
target_means = (1,1)
target_vars = (0.1,0.1)
generator = SimpleGaussianModel(dimension, SimpleGaussianModel.DIAGONAL_COVARIANCE)
generator.set_model(target_means, target_vars)
SimpleGaussianModel.seed(0)
GaussianMixtureModel.seed(0)
# Gmm setup
num_mixtures = 2
gmm0 = make_gmm(dimension, num_mixtures)
gmm1 = make_gmm(dimension, num_mixtures)
mm = GmmMgr((gmm1,))
# Hmm setup
hmm0 = Hmm(1, log_domain=True)
# A transition probability matrix with a p=1/2 exit for the real state.
# The entry state feeds into the real state with p=1.
trans = array(((0.0, 1.0, 0.0),
(0.0, 0.5, 0.5),
(0.0, 0.0, 0.0)))
hmm0.build_model(mm, (0,), 1, 1, trans)
print hmm0.to_string(True)
print gmm0
# Try some adaptation. Note that we are feeding the entire data set as one stream
# to the Hmm adaption call.
data = [generator.sample() for i in xrange(num_obs)]
for p in xrange(num_passes):
mm.set_adaptation_state("INITIALIZING")
mm.clear_all_accumulators()
hmm0.begin_adapt("STANDALONE")
mm.set_adaptation_state("ACCUMULATING")
hmm0.adapt_one_sequence(data)
mm.set_adaptation_state("APPLYING")
hmm0.end_adapt()
mm.apply_all_accumulators()
mm.set_adaptation_state("NOT_ADAPTING")
gmm0.adapt(data, max_iters = num_passes)
print hmm0.to_string(True)
print gmm0
def test0():
print '============== test0 ============'
dimension = 3
target0 = make_target(dimension, 2, (0.75, 0.25), ((1, 1, 1), (2, 3, 4)),
((1, 1, 1), (0.5, 0.5, 1)))
target1 = make_target(dimension, 2, (0.5, 0.5),
((-1, -1, -1), (-2, -3, -4)),
((1, 1, 1), (0.5, 0.5, 1)))
target2 = make_target(dimension, 2, (0.1, 0.9), ((1, 1, -2), (3, 3, 5)),
((1, 1, 1), (0.5, 0.5, 1)))
print target0
print target1
print target2
GaussianModelBase.seed(0)
labels = ('A', 'B', 'C')
ncomps = (1, 2, 2)
sources = dict((('A', target0), ('B', target1), ('C', target2)))
GaussianMixtureModel.seed(0)
gmm_mgr = GmmMgr(ncomps, dimension, GaussianModelBase.DIAGONAL_COVARIANCE)
c0 = AdaptingGmmClassifier(gmm_mgr, izip(labels, count()))
print
print c0
# Prime things a little bit to try to get a good start
c0.set_relevance(0.001)
for i in xrange(1):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
c0.adapt_one_class(label, data)
# Now adapt on more data
c0.set_relevance(10)
for i in xrange(10):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
c0.adapt_one_class(label, data)
print
print c0
print
def test0():
print '============== test0 ============'
dimension = 3
target0 = make_target(dimension, 2, (0.75, 0.25), ((1, 1, 1), (2, 3, 4)), ((1, 1, 1), (0.5, 0.5, 1)))
target1 = make_target(dimension, 2, (0.5, 0.5), ((-1, -1, -1), (-2, -3, -4)), ((1, 1, 1), (0.5, 0.5, 1)))
target2 = make_target(dimension, 2, (0.1, 0.9), ((1, 1, -2), (3, 3, 5)), ((1, 1, 1), (0.5, 0.5, 1)))
print target0
print target1
print target2
GaussianModelBase.seed(0)
labels = ('A', 'B', 'C')
ncomps = (1, 2, 2)
sources = dict((('A', target0), ('B', target1), ('C', target2)))
GaussianMixtureModel.seed(0)
gmm_mgr = GmmMgr(ncomps, dimension, GaussianModelBase.DIAGONAL_COVARIANCE)
c0 = AdaptingGmmClassifier(gmm_mgr, izip(labels, count()))
print
print c0
# Prime things a little bit to try to get a good start
c0.set_relevance(0.001)
for i in xrange(1):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
c0.adapt_one_class(label, data)
# Now adapt on more data
c0.set_relevance(10)
for i in xrange(10):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
c0.adapt_one_class(label, data)
print
print c0
print
def test0(num_obs, num_passes):
dimension = 2
# Data generator setup
target_means = (1,1)
target_vars = (0.1,0.1)
generator = SimpleGaussianModel(dimension, SimpleGaussianModel.DIAGONAL_COVARIANCE)
generator.set_model(target_means, target_vars)
SimpleGaussianModel.seed(0)
GaussianMixtureModel.seed(0)
mm = GmmMgr(dimension)
# Hmm setup
hmm0 = Hmm(0, log_domain=True)
# A transition probability matrix with no real state.
# The entry state feeds into the exit state with p=1.
trans = array(((0.0, 1.0),
(0.0, 0.0)))
hmm0.build_model(mm, (), 1, 1, trans)
print hmm0.to_string(True)
# Try some adaptation. Note that we are feeding the entire data set as one stream
# to the Hmm adaption call.
data = [generator.sample() for i in xrange(num_obs)]
for p in xrange(num_passes):
mm.set_adaptation_state("INITIALIZING")
mm.clear_all_accumulators()
hmm0.begin_adapt("STANDALONE")
mm.set_adaptation_state("ACCUMULATING")
with DebugPrint("hmm_gxfs", "hmm_aos") if False else DebugPrint():
hmm0.adapt_one_sequence(data)
mm.set_adaptation_state("APPLYING")
hmm0.end_adapt()
mm.apply_all_accumulators()
mm.set_adaptation_state("NOT_ADAPTING")
print hmm0.to_string(True)
def test1():
print '============== test1 ============'
dimension = 3
target0 = make_target(dimension, 2, (0.75, 0.25), ((1, 1, 1), (2, 3, 4)),
((1, 1, 1), (0.5, 0.5, 1)))
target1 = make_target(dimension, 2, (0.5, 0.5),
((-1, -1, -1), (-2, -3, -4)),
((1, 1, 1), (0.5, 0.5, 1)))
target2 = make_target(dimension, 2, (0.1, 0.9), ((1, 1, -2), (3, 3, 5)),
((1, 1, 1), (0.5, 0.5, 1)))
print target0
print target1
print target2
GaussianModelBase.seed(0)
labels = ('A', 'B', 'C')
ncomps = (1, 2, 2)
sources = dict((('A', target0), ('B', target1), ('C', target2)))
GaussianMixtureModel.seed(0)
gmm_mgr = GmmMgr(ncomps, dimension, GaussianModelBase.DIAGONAL_COVARIANCE)
c0 = AdaptingGmmClassifier(gmm_mgr, izip(labels, count()))
print
print c0
result = list()
proc0 = AdaptingGmmClassProcessor(c0, result.append)
# Prime things a little bit to try to get a good start
c0.set_relevance(0.001)
c0.set_num_em_iterations(2)
for i in xrange(1):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
proc0.process((label, data))
# Now adapt on more data
c0.set_relevance(10)
c0.set_num_em_iterations(2)
for i in xrange(10):
for label in labels:
target = sources[label]
data = (target.sample() for i in xrange(100))
proc0.process((label, data))
print
print c0
print
print len(result)
# XXX Win32 gets values off in the last 2-3 hex digits. I'm not sure how to account for this in a
# logref test, so I'm disabling this printing for now.
# for training_label, scores in result[-10:]:
# print training_label, tuple(((label, float_to_readable_string(score)) for score, label in scores))
correct = tuple(label for label, scores in result)
guessed = tuple(scores[0][1] for l, scores in result)
print len(correct), len(guessed)
ind = [c == g for (c, g) in izip(correct, guessed)]
print ind.count(True)
print ind.count(True) / len(correct)
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) classifier0 = AdaptingGmmClassProcessor(classify0) classifier1 = AdaptingGmmClassProcessor(classify1) gaussian_trainer = SimpleGaussianTrainer(labels, nfeatures) trainer = FunctionProcessor(gaussian_trainer) # audio.mic, fftmag, endpointer, mfcc0, square, mfcc1, classifier0, classifier1, trainer
