def acc(self, task_id):
mix_file = util.cache_path(self.ubm)
align_file = util.cache_path(self.alignment[task_id])
feat_file = util.cache_path(self.features[task_id])
allo_file = util.cache_path(self.allophones)
logging.info("Reading mixture file from '%s'..." % mix_file)
gmm = sc.MixtureSet(mix_file)
logging.info("Read %d means and %d covariances of dimension %d" %
(gmm.nMeans, gmm.nCovs, gmm.dim))
ubm = convert_gmm(gmm)
ivm = IVectorMachine(ubm, self.dim)
ivm.variance_threshold = 1e-5
gs = GMMStats(gmm.nMeans, gmm.dim)
logging.info(
"Opening alignment cache '%s' with allophones from '%s'; ignoring '%s'"
% (align_file, allo_file, ",".join(self.allophones_to_ignore)))
aligncache = sc.FileArchive(align_file)
aligncache.setAllophones(allo_file)
cache = sc.FileArchive(feat_file)
for a in cache.ft.keys():
if a.endswith(".attribs"):
continue
logging.info("Reading '%s'..." % a)
time, data = cache.read(a, "feat")
align = aligncache.read(a, "align")
if len(align) < 1:
logging.warning("No data for segment: '%s' in alignment." % a)
continue
allos = []
for (t, i, s, w) in align:
allos.append(aligncache.allophones[i])
allos = list(aligncache.allophones[i] for (t, i, s, w) in align)
T = len(
list(
filter(lambda al: al not in self.allophones_to_ignore,
allos)))
feat = np.ndarray((T, len(data[0])))
k = 0
for t in range(len(data)):
(_, allo, state, weight) = align[t]
if aligncache.allophones[
allo] not in self.allophones_to_ignore:
feat[k, :] = data[t]
k += 1
ivm.ubm.acc_statistics(feat, gs)
logging.info("Writing Gaussian statistics to '%s'" %
self.single_accu_caches[task_id].get_path())
gs.save(HDF5File(self.single_accu_caches[task_id].get_path(), "w"))
def test_GMMStats():
# Test a GMMStats
# Initializes a GMMStats
n_gaussians = 2
n_features = 3
gs = GMMStats(n_gaussians, n_features)
log_likelihood = -3.0
T = 57
n = np.array([4.37, 5.31], "float64")
sumpx = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], "float64")
sumpxx = np.array([[10.0, 20.0, 30.0], [40.0, 50.0, 60.0]], "float64")
gs.log_likelihood = log_likelihood
gs.t = T
gs.n = n
gs.sum_px = sumpx
gs.sum_pxx = sumpxx
np.testing.assert_equal(gs.log_likelihood, log_likelihood)
np.testing.assert_equal(gs.t, T)
np.testing.assert_equal(gs.n, n)
np.testing.assert_equal(gs.sum_px, sumpx)
np.testing.assert_equal(gs.sum_pxx, sumpxx)
np.testing.assert_equal(gs.shape, (n_gaussians, n_features))
# Saves and reads from file using `from_hdf5`
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(HDF5File(filename, "w"))
gs_loaded = GMMStats.from_hdf5(HDF5File(filename, "r"))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
assert type(gs_loaded.n_gaussians) is np.int64
assert type(gs_loaded.n_features) is np.int64
assert type(gs_loaded.log_likelihood) is np.float64
# Saves and load from file using `load`
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=HDF5File(filename, "w"))
gs_loaded = GMMStats(n_gaussians, n_features)
gs_loaded.load(HDF5File(filename, "r"))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
# Makes them different
gs_loaded.t = 58
assert (gs == gs_loaded) is False
assert gs != gs_loaded
assert not (gs.is_similar_to(gs_loaded))
# Accumulates from another GMMStats
gs2 = GMMStats(n_gaussians, n_features)
gs2.log_likelihood = log_likelihood
gs2.t = T
gs2.n = n.copy()
gs2.sum_px = sumpx.copy()
gs2.sum_pxx = sumpxx.copy()
gs2 += gs
np.testing.assert_equal(gs2.log_likelihood, 2 * log_likelihood)
np.testing.assert_equal(gs2.t, 2 * T)
np.testing.assert_almost_equal(gs2.n, 2 * n, decimal=8)
np.testing.assert_almost_equal(gs2.sum_px, 2 * sumpx, decimal=8)
np.testing.assert_almost_equal(gs2.sum_pxx, 2 * sumpxx, decimal=8)
# Re-init and checks for zeros
gs_loaded.init_fields()
np.testing.assert_equal(gs_loaded.log_likelihood, 0)
np.testing.assert_equal(gs_loaded.t, 0)
np.testing.assert_equal(gs_loaded.n, np.zeros((n_gaussians, )))
np.testing.assert_equal(gs_loaded.sum_px,
np.zeros((n_gaussians, n_features)))
np.testing.assert_equal(gs_loaded.sum_pxx,
np.zeros((n_gaussians, n_features)))
# Resize and checks size
assert gs_loaded.shape == (n_gaussians, n_features)
gs_loaded.resize(4, 5)
assert gs_loaded.shape == (4, 5)
assert gs_loaded.sum_px.shape[0] == 4
assert gs_loaded.sum_px.shape[1] == 5
# Clean-up
os.unlink(filename)
def test_GMMStats():
# Test a GMMStats
# Initializes a GMMStats
gs = GMMStats(2, 3)
log_likelihood = -3.
T = 57
n = numpy.array([4.37, 5.31], 'float64')
sumpx = numpy.array([[1., 2., 3.], [4., 5., 6.]], 'float64')
sumpxx = numpy.array([[10., 20., 30.], [40., 50., 60.]], 'float64')
gs.log_likelihood = log_likelihood
gs.t = T
gs.n = n
gs.sum_px = sumpx
gs.sum_pxx = sumpxx
assert gs.log_likelihood == log_likelihood
assert gs.t == T
assert (gs.n == n).all()
assert (gs.sum_px == sumpx).all()
assert (gs.sum_pxx == sumpxx).all()
assert gs.shape == (2, 3)
# Saves and reads from file
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats(bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
# Saves and reads from file using the keyword argument
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats(bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
# Saves and load from file using the keyword argument
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats()
gs_loaded.load(bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
# Saves and load from file using the keyword argument
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats()
gs_loaded.load(hdf5=bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded) is False
assert gs.is_similar_to(gs_loaded)
# Makes them different
gs_loaded.t = 58
assert (gs == gs_loaded) is False
assert gs != gs_loaded
assert (gs.is_similar_to(gs_loaded)) is False
# Accumulates from another GMMStats
gs2 = GMMStats(2, 3)
gs2.log_likelihood = log_likelihood
gs2.t = T
gs2.n = n
gs2.sum_px = sumpx
gs2.sum_pxx = sumpxx
gs2 += gs
eps = 1e-8
assert gs2.log_likelihood == 2 * log_likelihood
assert gs2.t == 2 * T
assert numpy.allclose(gs2.n, 2 * n, eps)
assert numpy.allclose(gs2.sum_px, 2 * sumpx, eps)
assert numpy.allclose(gs2.sum_pxx, 2 * sumpxx, eps)
# Reinit and checks for zeros
gs_loaded.init()
assert gs_loaded.log_likelihood == 0
assert gs_loaded.t == 0
assert (gs_loaded.n == 0).all()
assert (gs_loaded.sum_px == 0).all()
assert (gs_loaded.sum_pxx == 0).all()
# Resize and checks size
assert gs_loaded.shape == (2, 3)
gs_loaded.resize(4, 5)
assert gs_loaded.shape == (4, 5)
assert gs_loaded.sum_px.shape[0] == 4
assert gs_loaded.sum_px.shape[1] == 5
# Clean-up
os.unlink(filename)
def test_GMMStats():
# Test a GMMStats
# Initializes a GMMStats
gs = GMMStats(2,3)
log_likelihood = -3.
T = 57
n = numpy.array([4.37, 5.31], 'float64')
sumpx = numpy.array([[1., 2., 3.], [4., 5., 6.]], 'float64')
sumpxx = numpy.array([[10., 20., 30.], [40., 50., 60.]], 'float64')
gs.log_likelihood = log_likelihood
gs.t = T
gs.n = n
gs.sum_px = sumpx
gs.sum_pxx = sumpxx
assert gs.log_likelihood == log_likelihood
assert gs.t == T
assert (gs.n == n).all()
assert (gs.sum_px == sumpx).all()
assert (gs.sum_pxx == sumpxx).all()
assert gs.shape==(2,3)
# Saves and reads from file
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats(bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded ) is False
assert gs.is_similar_to(gs_loaded)
# Saves and reads from file using the keyword argument
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats(bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded ) is False
assert gs.is_similar_to(gs_loaded)
# Saves and load from file using the keyword argument
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats()
gs_loaded.load(bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded ) is False
assert gs.is_similar_to(gs_loaded)
# Saves and load from file using the keyword argument
filename = str(tempfile.mkstemp(".hdf5")[1])
gs.save(hdf5=bob.io.base.HDF5File(filename, 'w'))
gs_loaded = GMMStats()
gs_loaded.load(hdf5=bob.io.base.HDF5File(filename))
assert gs == gs_loaded
assert (gs != gs_loaded ) is False
assert gs.is_similar_to(gs_loaded)
# Makes them different
gs_loaded.t = 58
assert (gs == gs_loaded ) is False
assert gs != gs_loaded
assert (gs.is_similar_to(gs_loaded)) is False
# Accumulates from another GMMStats
gs2 = GMMStats(2,3)
gs2.log_likelihood = log_likelihood
gs2.t = T
gs2.n = n
gs2.sum_px = sumpx
gs2.sum_pxx = sumpxx
gs2 += gs
eps = 1e-8
assert gs2.log_likelihood == 2*log_likelihood
assert gs2.t == 2*T
assert numpy.allclose(gs2.n, 2*n, eps)
assert numpy.allclose(gs2.sum_px, 2*sumpx, eps)
assert numpy.allclose(gs2.sum_pxx, 2*sumpxx, eps)
# Reinit and checks for zeros
gs_loaded.init()
assert gs_loaded.log_likelihood == 0
assert gs_loaded.t == 0
assert (gs_loaded.n == 0).all()
assert (gs_loaded.sum_px == 0).all()
assert (gs_loaded.sum_pxx == 0).all()
# Resize and checks size
assert gs_loaded.shape==(2,3)
gs_loaded.resize(4,5)
assert gs_loaded.shape==(4,5)
assert gs_loaded.sum_px.shape[0] == 4
assert gs_loaded.sum_px.shape[1] == 5
# Clean-up
os.unlink(filename)