def test_kmeans_a():
# Trains a KMeansMachine
# This files contains draws from two 1D Gaussian distributions:
# * 100 samples from N(-10,1)
# * 100 samples from N(10,1)
data = bob.io.base.load(datafile("samplesFrom2G_f64.hdf5", __name__, path="../data/"))
machine = KMeansMachine(2, 1)
trainer = KMeansTrainer()
#trainer.train(machine, data)
bob.learn.em.train(trainer,machine,data)
[variances, weights] = machine.get_variances_and_weights_for_each_cluster(data)
variances_b = numpy.ndarray(shape=(2,1), dtype=numpy.float64)
weights_b = numpy.ndarray(shape=(2,), dtype=numpy.float64)
machine.__get_variances_and_weights_for_each_cluster_init__(variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_acc__(data, variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_fin__(variances_b, weights_b)
m1 = machine.get_mean(0)
m2 = machine.get_mean(1)
## Check means [-10,10] / variances [1,1] / weights [0.5,0.5]
if(m1<m2): means=numpy.array(([m1[0],m2[0]]), 'float64')
else: means=numpy.array(([m2[0],m1[0]]), 'float64')
assert equals(means, numpy.array([-10.,10.]), 2e-1)
assert equals(variances, numpy.array([1.,1.]), 2e-1)
assert equals(weights, numpy.array([0.5,0.5]), 1e-3)
assert equals(variances, variances_b, 1e-8)
assert equals(weights, weights_b, 1e-8)
def test_kmeans_a():
# Trains a KMeansMachine
# This files contains draws from two 1D Gaussian distributions:
# * 100 samples from N(-10,1)
# * 100 samples from N(10,1)
data = bob.io.base.load(datafile("samplesFrom2G_f64.hdf5", __name__, path="../data/"))
machine = KMeansMachine(2, 1)
trainer = KMeansTrainer()
# trainer.train(machine, data)
bob.learn.em.train(trainer, machine, data)
[variances, weights] = machine.get_variances_and_weights_for_each_cluster(data)
variances_b = numpy.ndarray(shape=(2, 1), dtype=numpy.float64)
weights_b = numpy.ndarray(shape=(2,), dtype=numpy.float64)
machine.__get_variances_and_weights_for_each_cluster_init__(variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_acc__(data, variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_fin__(variances_b, weights_b)
m1 = machine.get_mean(0)
m2 = machine.get_mean(1)
## Check means [-10,10] / variances [1,1] / weights [0.5,0.5]
if (m1 < m2):
means = numpy.array(([m1[0], m2[0]]), 'float64')
else:
means = numpy.array(([m2[0], m1[0]]), 'float64')
assert equals(means, numpy.array([-10., 10.]), 2e-1)
assert equals(variances, numpy.array([1., 1.]), 2e-1)
assert equals(weights, numpy.array([0.5, 0.5]), 1e-3)
assert equals(variances, variances_b, 1e-8)
assert equals(weights, weights_b, 1e-8)
def test_kmeans_b():
# Trains a KMeansMachine
(arStd,std) = NormalizeStdArray(datafile("faithful.torch3.hdf5", __name__, path="../data/"))
machine = KMeansMachine(2, 2)
trainer = KMeansTrainer()
#trainer.seed = 1337
bob.learn.em.train(trainer,machine, arStd, convergence_threshold=0.001)
[variances, weights] = machine.get_variances_and_weights_for_each_cluster(arStd)
means = numpy.array(machine.means)
variances = numpy.array(variances)
multiplyVectorsByFactors(means, std)
multiplyVectorsByFactors(variances, std ** 2)
gmmWeights = bob.io.base.load(datafile('gmm.init_weights.hdf5', __name__, path="../data/"))
gmmMeans = bob.io.base.load(datafile('gmm.init_means.hdf5', __name__, path="../data/"))
gmmVariances = bob.io.base.load(datafile('gmm.init_variances.hdf5', __name__, path="../data/"))
if (means[0, 0] < means[1, 0]):
means = flipRows(means)
variances = flipRows(variances)
weights = flipRows(weights)
assert equals(means, gmmMeans, 1e-3)
assert equals(weights, gmmWeights, 1e-3)
assert equals(variances, gmmVariances, 1e-3)
# Check that there is no duplicate means during initialization
machine = KMeansMachine(2, 1)
trainer = KMeansTrainer()
trainer.initialization_method = 'RANDOM_NO_DUPLICATE'
data = numpy.array([[1.], [1.], [1.], [1.], [1.], [1.], [2.], [3.]])
bob.learn.em.train(trainer, machine, data)
assert (numpy.isnan(machine.means).any()) == False
def test_kmeans_b():
# Trains a KMeansMachine
(arStd, std) = NormalizeStdArray(datafile("faithful.torch3.hdf5", __name__, path="../data/"))
machine = KMeansMachine(2, 2)
trainer = KMeansTrainer()
# trainer.seed = 1337
bob.learn.em.train(trainer, machine, arStd, convergence_threshold=0.001)
[variances, weights] = machine.get_variances_and_weights_for_each_cluster(arStd)
means = numpy.array(machine.means)
variances = numpy.array(variances)
multiplyVectorsByFactors(means, std)
multiplyVectorsByFactors(variances, std ** 2)
gmmWeights = bob.io.base.load(datafile('gmm.init_weights.hdf5', __name__, path="../data/"))
gmmMeans = bob.io.base.load(datafile('gmm.init_means.hdf5', __name__, path="../data/"))
gmmVariances = bob.io.base.load(datafile('gmm.init_variances.hdf5', __name__, path="../data/"))
if (means[0, 0] < means[1, 0]):
means = flipRows(means)
variances = flipRows(variances)
weights = flipRows(weights)
assert equals(means, gmmMeans, 1e-3)
assert equals(weights, gmmWeights, 1e-3)
assert equals(variances, gmmVariances, 1e-3)
# Check that there is no duplicate means during initialization
machine = KMeansMachine(2, 1)
trainer = KMeansTrainer()
trainer.initialization_method = 'RANDOM_NO_DUPLICATE'
data = numpy.array([[1.], [1.], [1.], [1.], [1.], [1.], [2.], [3.]])
bob.learn.em.train(trainer, machine, data)
assert (numpy.isnan(machine.means).any()) == False