def test_machine():
# Ubm
ubm = GMMMachine(2, 3)
ubm.weights = numpy.array([0.4, 0.6])
ubm.means = numpy.array([[1., 7, 4], [4, 5, 3]])
ubm.variances = numpy.array([[0.5, 1., 1.5], [1., 1.5, 2.]])
# Defines GMMStats
gs = GMMStats(2, 3)
log_likelihood = -3.
T = 1
n = numpy.array([0.4, 0.6], numpy.float64)
sumpx = numpy.array([[1., 2., 3.], [2., 4., 3.]], numpy.float64)
sumpxx = numpy.array([[10., 20., 30.], [40., 50., 60.]], numpy.float64)
gs.log_likelihood = log_likelihood
gs.t = T
gs.n = n
gs.sum_px = sumpx
gs.sum_pxx = sumpxx
# IVector (Python)
m = IVectorMachinePy(ubm, 2)
t = numpy.array([[1., 2], [4, 1], [0, 3], [5, 8], [7, 10], [11, 1]])
m.set_t(t)
sigma = numpy.array([1., 2., 1., 3., 2., 4.])
m.set_sigma(sigma)
wij_ref = numpy.array([-0.04213415, 0.21463343
]) # Reference from original Chris implementation
wij = m.project(gs)
assert numpy.allclose(wij_ref, wij, 1e-5)
# IVector (C++)
mc = IVectorMachine(ubm, 2)
mc.t = t
mc.sigma = sigma
wij_ref = numpy.array([-0.04213415, 0.21463343
]) # Reference from original Chris implementation
wij = mc.project(gs)
assert numpy.allclose(wij_ref, wij, 1e-5)
def test_JFAMachine():
eps = 1e-10
# Creates a UBM
ubm = GMMMachine(2, 3)
ubm.weights = np.array([0.4, 0.6], "float64")
ubm.means = np.array([[1, 6, 2], [4, 3, 2]], "float64")
ubm.variances = np.array([[1, 2, 1], [2, 1, 2]], "float64")
# Defines GMMStats
gs = GMMStats(2, 3)
gs.log_likelihood = -3.0
gs.t = 1
gs.n = np.array([0.4, 0.6], "float64")
gs.sum_px = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], "float64")
gs.sum_pxx = np.array([[10.0, 20.0, 30.0], [40.0, 50.0, 60.0]], "float64")
# Creates a JFAMachine
m = JFAMachine(2, 2, em_iterations=10, ubm=ubm)
m.U = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12]],
"float64")
m.V = np.array([[6, 5], [4, 3], [2, 1], [1, 2], [3, 4], [5, 6]], "float64")
m.D = np.array([0, 1, 0, 1, 0, 1], "float64")
# Preparing the model
y = np.array([1, 2], "float64")
z = np.array([3, 4, 1, 2, 0, 1], "float64")
model = [y, z]
score_ref = -2.111577181208289
score = m.score(model, gs)
np.testing.assert_allclose(score, score_ref, atol=eps)
# Scoring with numpy array
np.random.seed(0)
X = np.random.normal(loc=0.0, scale=1.0, size=(50, 3))
score_ref = 2.028009315286946
score = m.score_using_array(model, X)
np.testing.assert_allclose(score, score_ref, atol=eps)
def test_ISVMachine():
eps = 1e-10
# Creates a UBM
ubm = GMMMachine(2, 3)
ubm.weights = np.array([0.4, 0.6], "float64")
ubm.means = np.array([[1, 6, 2], [4, 3, 2]], "float64")
ubm.variances = np.array([[1, 2, 1], [2, 1, 2]], "float64")
# Creates a ISVMachine
isv_machine = ISVMachine(ubm=ubm, r_U=2, em_iterations=10)
isv_machine.U = np.array(
[[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12]], "float64")
# base.v = np.array([[0], [0], [0], [0], [0], [0]], 'float64')
isv_machine.D = np.array([0, 1, 0, 1, 0, 1], "float64")
# Defines GMMStats
gs = GMMStats(2, 3)
gs.log_likelihood = -3.0
gs.t = 1
gs.n = np.array([0.4, 0.6], "float64")
gs.sum_px = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], "float64")
gs.sum_pxx = np.array([[10.0, 20.0, 30.0], [40.0, 50.0, 60.0]], "float64")
# Enrolled model
latent_z = np.array([3, 4, 1, 2, 0, 1], "float64")
score = isv_machine.score(latent_z, gs)
score_ref = -3.280498193082100
np.testing.assert_allclose(score, score_ref, atol=eps)
# Scoring with numpy array
np.random.seed(0)
X = np.random.normal(loc=0.0, scale=1.0, size=(50, 3))
score_ref = -1.2343813195374242
score = isv_machine.score_using_array(latent_z, X)
np.testing.assert_allclose(score, score_ref, atol=eps)
def test_LinearScoring():
ubm = GMMMachine(2, 2)
ubm.weights = numpy.array([0.5, 0.5], 'float64')
ubm.means = numpy.array([[3, 70], [4, 72]], 'float64')
ubm.variances = numpy.array([[1, 10], [2, 5]], 'float64')
ubm.variance_thresholds = numpy.array([[0, 0], [0, 0]], 'float64')
model1 = GMMMachine(2, 2)
model1.weights = numpy.array([0.5, 0.5], 'float64')
model1.means = numpy.array([[1, 2], [3, 4]], 'float64')
model1.variances = numpy.array([[9, 10], [11, 12]], 'float64')
model1.variance_thresholds = numpy.array([[0, 0], [0, 0]], 'float64')
model2 = GMMMachine(2, 2)
model2.weights = numpy.array([0.5, 0.5], 'float64')
model2.means = numpy.array([[5, 6], [7, 8]], 'float64')
model2.variances = numpy.array([[13, 14], [15, 16]], 'float64')
model2.variance_thresholds = numpy.array([[0, 0], [0, 0]], 'float64')
stats1 = GMMStats(2, 2)
stats1.sum_px = numpy.array([[1, 2], [3, 4]], 'float64')
stats1.n = numpy.array([1, 2], 'float64')
stats1.t = 1 + 2
stats2 = GMMStats(2, 2)
stats2.sum_px = numpy.array([[5, 6], [7, 8]], 'float64')
stats2.n = numpy.array([3, 4], 'float64')
stats2.t = 3 + 4
stats3 = GMMStats(2, 2)
stats3.sum_px = numpy.array([[5, 6], [7, 3]], 'float64')
stats3.n = numpy.array([3, 4], 'float64')
stats3.t = 3 + 4
test_channeloffset = [
numpy.array([9, 8, 7, 6], 'float64'),
numpy.array([5, 4, 3, 2], 'float64'),
numpy.array([1, 0, 1, 2], 'float64')
]
# Reference scores (from Idiap internal matlab implementation)
ref_scores_00 = numpy.array(
[[2372.9, 5207.7, 5275.7], [2215.7, 4868.1, 4932.1]], 'float64')
ref_scores_01 = numpy.array(
[[790.9666666666667, 743.9571428571428, 753.6714285714285],
[738.5666666666667, 695.4428571428572, 704.5857142857144]], 'float64')
ref_scores_10 = numpy.array(
[[2615.5, 5434.1, 5392.5], [2381.5, 4999.3, 5022.5]], 'float64')
ref_scores_11 = numpy.array(
[[871.8333333333332, 776.3000000000001, 770.3571428571427],
[793.8333333333333, 714.1857142857143, 717.5000000000000]], 'float64')
# 1/ Use GMMMachines
# 1/a/ Without test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3])
assert (abs(scores - ref_scores_00) < 1e-7).all()
# 1/b/ Without test_channelOffset, with frame-length normalisation
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3],
[], True)
assert (abs(scores - ref_scores_01) < 1e-7).all()
#scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], (), True)
#assert (abs(scores - ref_scores_01) < 1e-7).all()
#scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], None, True)
#assert (abs(scores - ref_scores_01) < 1e-7).all()
# 1/c/ With test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3],
test_channeloffset)
assert (abs(scores - ref_scores_10) < 1e-7).all()
# 1/d/ With test_channelOffset, with frame-length normalisation
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3],
test_channeloffset, True)
assert (abs(scores - ref_scores_11) < 1e-7).all()
# 2/ Use mean/variance supervectors
# 2/a/ Without test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1.mean_supervector, model2.mean_supervector],
ubm.mean_supervector, ubm.variance_supervector,
[stats1, stats2, stats3])
assert (abs(scores - ref_scores_00) < 1e-7).all()
# 2/b/ Without test_channelOffset, with frame-length normalisation
scores = linear_scoring([model1.mean_supervector, model2.mean_supervector],
ubm.mean_supervector, ubm.variance_supervector,
[stats1, stats2, stats3], [], True)
assert (abs(scores - ref_scores_01) < 1e-7).all()
# 2/c/ With test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1.mean_supervector, model2.mean_supervector],
ubm.mean_supervector, ubm.variance_supervector,
[stats1, stats2, stats3], test_channeloffset)
assert (abs(scores - ref_scores_10) < 1e-7).all()
# 2/d/ With test_channelOffset, with frame-length normalisation
scores = linear_scoring([model1.mean_supervector, model2.mean_supervector],
ubm.mean_supervector, ubm.variance_supervector,
[stats1, stats2, stats3], test_channeloffset, True)
assert (abs(scores - ref_scores_11) < 1e-7).all()
# 3/ Using single model/sample
# 3/a/ without frame-length normalisation
score = linear_scoring(model1.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats1,
test_channeloffset[0])
assert abs(score - ref_scores_10[0, 0]) < 1e-7
score = linear_scoring(model1.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats2,
test_channeloffset[1])
assert abs(score - ref_scores_10[0, 1]) < 1e-7
score = linear_scoring(model1.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats3,
test_channeloffset[2])
assert abs(score - ref_scores_10[0, 2]) < 1e-7
score = linear_scoring(model2.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats1,
test_channeloffset[0])
assert abs(score - ref_scores_10[1, 0]) < 1e-7
score = linear_scoring(model2.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats2,
test_channeloffset[1])
assert abs(score - ref_scores_10[1, 1]) < 1e-7
score = linear_scoring(model2.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats3,
test_channeloffset[2])
assert abs(score - ref_scores_10[1, 2]) < 1e-7
# 3/b/ without frame-length normalisation
score = linear_scoring(model1.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats1,
test_channeloffset[0], True)
assert abs(score - ref_scores_11[0, 0]) < 1e-7
score = linear_scoring(model1.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats2,
test_channeloffset[1], True)
assert abs(score - ref_scores_11[0, 1]) < 1e-7
score = linear_scoring(model1.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats3,
test_channeloffset[2], True)
assert abs(score - ref_scores_11[0, 2]) < 1e-7
score = linear_scoring(model2.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats1,
test_channeloffset[0], True)
assert abs(score - ref_scores_11[1, 0]) < 1e-7
score = linear_scoring(model2.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats2,
test_channeloffset[1], True)
assert abs(score - ref_scores_11[1, 1]) < 1e-7
score = linear_scoring(model2.mean_supervector, ubm.mean_supervector,
ubm.variance_supervector, stats3,
test_channeloffset[2], True)
assert abs(score - ref_scores_11[1, 2]) < 1e-7
def test_LinearScoring():
ubm = GMMMachine(n_gaussians=2)
ubm.weights = np.array([0.5, 0.5], "float64")
ubm.means = np.array([[3, 70], [4, 72]], "float64")
ubm.variances = np.array([[1, 10], [2, 5]], "float64")
ubm.variance_thresholds = np.array([[0, 0], [0, 0]], "float64")
model1 = GMMMachine(n_gaussians=2)
model1.weights = np.array([0.5, 0.5], "float64")
model1.means = np.array([[1, 2], [3, 4]], "float64")
model1.variances = np.array([[9, 10], [11, 12]], "float64")
model1.variance_thresholds = np.array([[0, 0], [0, 0]], "float64")
model2 = GMMMachine(n_gaussians=2)
model2.weights = np.array([0.5, 0.5], "float64")
model2.means = np.array([[5, 6], [7, 8]], "float64")
model2.variances = np.array([[13, 14], [15, 16]], "float64")
model2.variance_thresholds = np.array([[0, 0], [0, 0]], "float64")
stats1 = GMMStats(2, 2)
stats1.sum_px = np.array([[1, 2], [3, 4]], "float64")
stats1.n = np.array([1, 2], "float64")
stats1.t = 1 + 2
stats2 = GMMStats(2, 2)
stats2.sum_px = np.array([[5, 6], [7, 8]], "float64")
stats2.n = np.array([3, 4], "float64")
stats2.t = 3 + 4
stats3 = GMMStats(2, 2)
stats3.sum_px = np.array([[5, 6], [7, 3]], "float64")
stats3.n = np.array([3, 4], "float64")
stats3.t = 3 + 4
test_channeloffset = [
np.array([[9, 8], [7, 6]], "float64"),
np.array([[5, 4], [3, 2]], "float64"),
np.array([[1, 0], [1, 2]], "float64"),
]
# Reference scores (from Idiap internal matlab implementation)
ref_scores_00 = np.array(
[[2372.9, 5207.7, 5275.7], [2215.7, 4868.1, 4932.1]], "float64")
ref_scores_01 = np.array(
[
[790.9666666666667, 743.9571428571428, 753.6714285714285],
[738.5666666666667, 695.4428571428572, 704.5857142857144],
],
"float64",
)
ref_scores_10 = np.array(
[[2615.5, 5434.1, 5392.5], [2381.5, 4999.3, 5022.5]], "float64")
ref_scores_11 = np.array(
[
[871.8333333333332, 776.3000000000001, 770.3571428571427],
[793.8333333333333, 714.1857142857143, 717.5000000000000],
],
"float64",
)
# 1/ Use GMMMachines
# 1/a/ Without test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3])
np.testing.assert_almost_equal(scores, ref_scores_00, decimal=7)
# 1/b/ Without test_channelOffset, with frame-length normalisation
scores = linear_scoring(
[model1, model2],
ubm,
[stats1, stats2, stats3],
frame_length_normalization=True,
)
np.testing.assert_almost_equal(scores, ref_scores_01, decimal=7)
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], 0,
True)
np.testing.assert_almost_equal(scores, ref_scores_01, decimal=7)
# 1/c/ With test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3],
test_channeloffset)
np.testing.assert_almost_equal(scores, ref_scores_10, decimal=7)
# 1/d/ With test_channelOffset, with frame-length normalisation
scores = linear_scoring(
[model1, model2],
ubm,
[stats1, stats2, stats3],
test_channeloffset,
frame_length_normalization=True,
)
np.testing.assert_almost_equal(scores, ref_scores_11, decimal=7)
# 2/ Use means instead of models
# 2/a/ Without test_channelOffset, without frame-length normalisation
scores = linear_scoring([model1.means, model2.means], ubm,
[stats1, stats2, stats3])
assert (abs(scores - ref_scores_00) < 1e-7).all()
# 2/b/ Without test_channelOffset, with frame-length normalisation
scores = linear_scoring(
[model1.means, model2.means],
ubm,
[stats1, stats2, stats3],
frame_length_normalization=True,
)
assert (abs(scores - ref_scores_01) < 1e-7).all()
# 2/c/ With test_channelOffset, without frame-length normalisation
scores = linear_scoring(
[model1.means, model2.means],
ubm,
[stats1, stats2, stats3],
test_channeloffset,
)
assert (abs(scores - ref_scores_10) < 1e-7).all()
# 2/d/ With test_channelOffset, with frame-length normalisation
scores = linear_scoring(
[model1.means, model2.means],
ubm,
[stats1, stats2, stats3],
test_channeloffset,
frame_length_normalization=True,
)
assert (abs(scores - ref_scores_11) < 1e-7).all()
# 3/ Using single model/sample
# 3/a/ without frame-length normalisation
score = linear_scoring(model1.means, ubm, stats1, test_channeloffset[0])
np.testing.assert_almost_equal(score, ref_scores_10[0, 0], decimal=7)
score = linear_scoring(model1.means, ubm, stats2, test_channeloffset[1])
np.testing.assert_almost_equal(score, ref_scores_10[0, 1], decimal=7)
score = linear_scoring(model1.means, ubm, stats3, test_channeloffset[2])
np.testing.assert_almost_equal(score, ref_scores_10[0, 2], decimal=7)
score = linear_scoring(model2.means, ubm, stats1, test_channeloffset[0])
np.testing.assert_almost_equal(score, ref_scores_10[1, 0], decimal=7)
score = linear_scoring(model2.means, ubm, stats2, test_channeloffset[1])
np.testing.assert_almost_equal(score, ref_scores_10[1, 1], decimal=7)
score = linear_scoring(model2.means, ubm, stats3, test_channeloffset[2])
np.testing.assert_almost_equal(score, ref_scores_10[1, 2], decimal=7)
# 3/b/ with frame-length normalisation
score = linear_scoring(model1.means, ubm, stats1, test_channeloffset[0],
True)
np.testing.assert_almost_equal(score, ref_scores_11[0, 0], decimal=7)
score = linear_scoring(model1.means, ubm, stats2, test_channeloffset[1],
True)
np.testing.assert_almost_equal(score, ref_scores_11[0, 1], decimal=7)
score = linear_scoring(model1.means, ubm, stats3, test_channeloffset[2],
True)
np.testing.assert_almost_equal(score, ref_scores_11[0, 2], decimal=7)
score = linear_scoring(model2.means, ubm, stats1, test_channeloffset[0],
True)
np.testing.assert_almost_equal(score, ref_scores_11[1, 0], decimal=7)
score = linear_scoring(model2.means, ubm, stats2, test_channeloffset[1],
True)
np.testing.assert_almost_equal(score, ref_scores_11[1, 1], decimal=7)
score = linear_scoring(model2.means, ubm, stats3, test_channeloffset[2],
True)
np.testing.assert_almost_equal(score, ref_scores_11[1, 2], decimal=7)
def test_ISVMachine():
# Creates a UBM
weights = numpy.array([0.4, 0.6], 'float64')
means = numpy.array([[1, 6, 2], [4, 3, 2]], 'float64')
variances = numpy.array([[1, 2, 1], [2, 1, 2]], 'float64')
ubm = GMMMachine(2,3)
ubm.weights = weights
ubm.means = means
ubm.variances = variances
# Creates a ISVBaseMachine
U = numpy.array([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12]], 'float64')
#V = numpy.array([[0], [0], [0], [0], [0], [0]], 'float64')
d = numpy.array([0, 1, 0, 1, 0, 1], 'float64')
base = ISVBase(ubm,2)
base.u = U
#base.v = V
base.d = d
# Creates a JFAMachine
z = numpy.array([3,4,1,2,0,1], 'float64')
m = ISVMachine(base)
m.z = z
n_gaussians,dim,ru = m.shape
supervector_length = m.supervector_length
assert n_gaussians == 2
assert dim == 3
assert supervector_length == 6
assert ru == 2
assert (m.z == z).all()
# Saves and loads
filename = str(tempfile.mkstemp(".hdf5")[1])
m.save(bob.io.base.HDF5File(filename, 'w'))
m_loaded = ISVMachine(bob.io.base.HDF5File(filename))
m_loaded.isv_base = base
assert m == m_loaded
assert (m != m_loaded) is False
assert m.is_similar_to(m_loaded)
# Copy constructor
mc = ISVMachine(m)
assert m == mc
# Variant
mv = ISVMachine(base)
# Checks for correctness
#mv.isv_base = base
m.z = z
n_gaussians,dim,ru = m.shape
supervector_length = m.supervector_length
assert n_gaussians == 2
assert dim == 3
assert supervector_length == 6
assert ru == 2
assert (m.z == z).all()
# Defines GMMStats
gs = GMMStats(2,3)
log_likelihood = -3.
T = 1
n = numpy.array([0.4, 0.6], '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
# Forward GMMStats and check estimated value of the x speaker factor
eps = 1e-10
x_ref = numpy.array([0.291042849767692, 0.310273618998444], 'float64')
score_ref = -3.280498193082100
score = m(gs)
assert numpy.allclose(m.x, x_ref, eps)
assert abs(score_ref-score) < eps
# Check using alternate forward() method
supervector_length = m.supervector_length
Ux = numpy.ndarray(shape=(supervector_length,), dtype=numpy.float64)
m.estimate_ux(gs, Ux)
score = m.forward_ux(gs, Ux)
assert abs(score_ref-score) < eps
# x and Ux
x = numpy.ndarray((2,), numpy.float64)
m.estimate_x(gs, x)
n_gaussians,dim,_ = m.shape
x_py = estimate_x(n_gaussians, dim, ubm.mean_supervector, ubm.variance_supervector, U, n, sumpx)
assert numpy.allclose(x, x_py, eps)
ux = numpy.ndarray((6,), numpy.float64)
m.estimate_ux(gs, ux)
n_gaussians,dim,_ = m.shape
ux_py = estimate_ux(n_gaussians, dim, ubm.mean_supervector, ubm.variance_supervector, U, n, sumpx)
assert numpy.allclose(ux, ux_py, eps)
assert numpy.allclose(m.x, x, eps)
score = m.forward_ux(gs, ux)
assert abs(score_ref-score) < eps
# Clean-up
os.unlink(filename)
def test_JFAMachine():
# Creates a UBM
weights = numpy.array([0.4, 0.6], 'float64')
means = numpy.array([[1, 6, 2], [4, 3, 2]], 'float64')
variances = numpy.array([[1, 2, 1], [2, 1, 2]], 'float64')
ubm = GMMMachine(2,3)
ubm.weights = weights
ubm.means = means
ubm.variances = variances
# Creates a JFABase
U = numpy.array([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12]], 'float64')
V = numpy.array([[6, 5], [4, 3], [2, 1], [1, 2], [3, 4], [5, 6]], 'float64')
d = numpy.array([0, 1, 0, 1, 0, 1], 'float64')
base = JFABase(ubm,2,2)
base.u = U
base.v = V
base.d = d
# Creates a JFAMachine
y = numpy.array([1,2], 'float64')
z = numpy.array([3,4,1,2,0,1], 'float64')
m = JFAMachine(base)
m.y = y
m.z = z
n_gaussians,dim,ru,rv = m.shape
supervector_length = m.supervector_length
assert n_gaussians == 2
assert dim == 3
assert supervector_length == 6
assert ru == 2
assert rv == 2
assert (m.y == y).all()
assert (m.z == z).all()
# Saves and loads
filename = str(tempfile.mkstemp(".hdf5")[1])
m.save(bob.io.base.HDF5File(filename, 'w'))
m_loaded = JFAMachine(bob.io.base.HDF5File(filename))
m_loaded.jfa_base = base
assert m == m_loaded
assert (m != m_loaded) is False
assert m.is_similar_to(m_loaded)
# Copy constructor
mc = JFAMachine(m)
assert m == mc
# Variant
#mv = JFAMachine()
# Checks for correctness
#mv.jfa_base = base
#m.y = y
#m.z = z
#assert m.dim_c == 2
#assert m.dim_d == 3
#assert m.dim_cd == 6
#assert m.dim_ru == 2
#assert m.dim_rv == 2
#assert (m.y == y).all()
#assert (m.z == z).all()
# Defines GMMStats
gs = GMMStats(2,3)
log_likelihood = -3.
T = 1
n = numpy.array([0.4, 0.6], '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
# Forward GMMStats and check estimated value of the x speaker factor
eps = 1e-10
x_ref = numpy.array([0.291042849767692, 0.310273618998444], 'float64')
score_ref = -2.111577181208289
score = m.log_likelihood(gs)
assert numpy.allclose(m.x, x_ref, eps)
assert abs(score_ref-score) < eps
# x and Ux
x = numpy.ndarray((2,), numpy.float64)
m.estimate_x(gs, x)
n_gaussians, dim,_,_ = m.shape
x_py = estimate_x(n_gaussians, dim, ubm.mean_supervector, ubm.variance_supervector, U, n, sumpx)
assert numpy.allclose(x, x_py, eps)
ux = numpy.ndarray((6,), numpy.float64)
m.estimate_ux(gs, ux)
n_gaussians, dim,_,_ = m.shape
ux_py = estimate_ux(n_gaussians, dim, ubm.mean_supervector, ubm.variance_supervector, U, n, sumpx)
assert numpy.allclose(ux, ux_py, eps)
assert numpy.allclose(m.x, x, eps)
score = m.forward_ux(gs, ux)
assert abs(score_ref-score) < eps
# 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_LinearScoring(): ubm = GMMMachine(2, 2) ubm.weights = numpy.array([0.5, 0.5], 'float64') ubm.means = numpy.array([[3, 70], [4, 72]], 'float64') ubm.variances = numpy.array([[1, 10], [2, 5]], 'float64') ubm.variance_thresholds = numpy.array([[0, 0], [0, 0]], 'float64') model1 = GMMMachine(2, 2) model1.weights = numpy.array([0.5, 0.5], 'float64') model1.means = numpy.array([[1, 2], [3, 4]], 'float64') model1.variances = numpy.array([[9, 10], [11, 12]], 'float64') model1.variance_thresholds = numpy.array([[0, 0], [0, 0]], 'float64') model2 = GMMMachine(2, 2) model2.weights = numpy.array([0.5, 0.5], 'float64') model2.means = numpy.array([[5, 6], [7, 8]], 'float64') model2.variances = numpy.array([[13, 14], [15, 16]], 'float64') model2.variance_thresholds = numpy.array([[0, 0], [0, 0]], 'float64') stats1 = GMMStats(2, 2) stats1.sum_px = numpy.array([[1, 2], [3, 4]], 'float64') stats1.n = numpy.array([1, 2], 'float64') stats1.t = 1+2 stats2 = GMMStats(2, 2) stats2.sum_px = numpy.array([[5, 6], [7, 8]], 'float64') stats2.n = numpy.array([3, 4], 'float64') stats2.t = 3+4 stats3 = GMMStats(2, 2) stats3.sum_px = numpy.array([[5, 6], [7, 3]], 'float64') stats3.n = numpy.array([3, 4], 'float64') stats3.t = 3+4 test_channeloffset = [numpy.array([9, 8, 7, 6], 'float64'), numpy.array([5, 4, 3, 2], 'float64'), numpy.array([1, 0, 1, 2], 'float64')] # Reference scores (from Idiap internal matlab implementation) ref_scores_00 = numpy.array([[2372.9, 5207.7, 5275.7], [2215.7, 4868.1, 4932.1]], 'float64') ref_scores_01 = numpy.array( [[790.9666666666667, 743.9571428571428, 753.6714285714285], [738.5666666666667, 695.4428571428572, 704.5857142857144]], 'float64') ref_scores_10 = numpy.array([[2615.5, 5434.1, 5392.5], [2381.5, 4999.3, 5022.5]], 'float64') ref_scores_11 = numpy.array([[871.8333333333332, 776.3000000000001, 770.3571428571427], [793.8333333333333, 714.1857142857143, 717.5000000000000]], 'float64') # 1/ Use GMMMachines # 1/a/ Without test_channelOffset, without frame-length normalisation scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3]) assert (abs(scores - ref_scores_00) < 1e-7).all() # 1/b/ Without test_channelOffset, with frame-length normalisation scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], [], True) assert (abs(scores - ref_scores_01) < 1e-7).all() #scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], (), True) #assert (abs(scores - ref_scores_01) < 1e-7).all() #scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], None, True) #assert (abs(scores - ref_scores_01) < 1e-7).all() # 1/c/ With test_channelOffset, without frame-length normalisation scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], test_channeloffset) assert (abs(scores - ref_scores_10) < 1e-7).all() # 1/d/ With test_channelOffset, with frame-length normalisation scores = linear_scoring([model1, model2], ubm, [stats1, stats2, stats3], test_channeloffset, True) assert (abs(scores - ref_scores_11) < 1e-7).all() # 2/ Use mean/variance supervectors # 2/a/ Without test_channelOffset, without frame-length normalisation scores = linear_scoring([model1.mean_supervector, model2.mean_supervector], ubm.mean_supervector, ubm.variance_supervector, [stats1, stats2, stats3]) assert (abs(scores - ref_scores_00) < 1e-7).all() # 2/b/ Without test_channelOffset, with frame-length normalisation scores = linear_scoring([model1.mean_supervector, model2.mean_supervector], ubm.mean_supervector, ubm.variance_supervector, [stats1, stats2, stats3], [], True) assert (abs(scores - ref_scores_01) < 1e-7).all() # 2/c/ With test_channelOffset, without frame-length normalisation scores = linear_scoring([model1.mean_supervector, model2.mean_supervector], ubm.mean_supervector, ubm.variance_supervector, [stats1, stats2, stats3], test_channeloffset) assert (abs(scores - ref_scores_10) < 1e-7).all() # 2/d/ With test_channelOffset, with frame-length normalisation scores = linear_scoring([model1.mean_supervector, model2.mean_supervector], ubm.mean_supervector, ubm.variance_supervector, [stats1, stats2, stats3], test_channeloffset, True) assert (abs(scores - ref_scores_11) < 1e-7).all() # 3/ Using single model/sample # 3/a/ without frame-length normalisation score = linear_scoring(model1.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats1, test_channeloffset[0]) assert abs(score - ref_scores_10[0,0]) < 1e-7 score = linear_scoring(model1.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats2, test_channeloffset[1]) assert abs(score - ref_scores_10[0,1]) < 1e-7 score = linear_scoring(model1.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats3, test_channeloffset[2]) assert abs(score - ref_scores_10[0,2]) < 1e-7 score = linear_scoring(model2.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats1, test_channeloffset[0]) assert abs(score - ref_scores_10[1,0]) < 1e-7 score = linear_scoring(model2.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats2, test_channeloffset[1]) assert abs(score - ref_scores_10[1,1]) < 1e-7 score = linear_scoring(model2.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats3, test_channeloffset[2]) assert abs(score - ref_scores_10[1,2]) < 1e-7 # 3/b/ without frame-length normalisation score = linear_scoring(model1.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats1, test_channeloffset[0], True) assert abs(score - ref_scores_11[0,0]) < 1e-7 score = linear_scoring(model1.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats2, test_channeloffset[1], True) assert abs(score - ref_scores_11[0,1]) < 1e-7 score = linear_scoring(model1.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats3, test_channeloffset[2], True) assert abs(score - ref_scores_11[0,2]) < 1e-7 score = linear_scoring(model2.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats1, test_channeloffset[0], True) assert abs(score - ref_scores_11[1,0]) < 1e-7 score = linear_scoring(model2.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats2, test_channeloffset[1], True) assert abs(score - ref_scores_11[1,1]) < 1e-7 score = linear_scoring(model2.mean_supervector, ubm.mean_supervector, ubm.variance_supervector, stats3, test_channeloffset[2], True) assert abs(score - ref_scores_11[1,2]) < 1e-7
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_trainer_update_sigma():
# Ubm
dim_c = 2
dim_d = 3
ubm = GMMMachine(dim_c,dim_d)
ubm.weights = numpy.array([0.4,0.6])
ubm.means = numpy.array([[1.,7,4],[4,5,3]])
ubm.variances = numpy.array([[0.5,1.,1.5],[1.,1.5,2.]])
# Defines GMMStats
gs1 = GMMStats(dim_c,dim_d)
log_likelihood1 = -3.
T1 = 1
n1 = numpy.array([0.4, 0.6], numpy.float64)
sumpx1 = numpy.array([[1., 2., 3.], [2., 4., 3.]], numpy.float64)
sumpxx1 = numpy.array([[10., 20., 30.], [40., 50., 60.]], numpy.float64)
gs1.log_likelihood = log_likelihood1
gs1.t = T1
gs1.n = n1
gs1.sum_px = sumpx1
gs1.sum_pxx = sumpxx1
gs2 = GMMStats(dim_c,dim_d)
log_likelihood2 = -4.
T2 = 1
n2 = numpy.array([0.2, 0.8], numpy.float64)
sumpx2 = numpy.array([[2., 1., 3.], [3., 4.1, 3.2]], numpy.float64)
sumpxx2 = numpy.array([[12., 15., 25.], [39., 51., 62.]], numpy.float64)
gs2.log_likelihood = log_likelihood2
gs2.t = T2
gs2.n = n2
gs2.sum_px = sumpx2
gs2.sum_pxx = sumpxx2
data = [gs1, gs2]
# Reference values
acc_Nij_Sigma_wij2_ref1 = {0: numpy.array([[ 0.03202305, -0.02947769], [-0.02947769, 0.0561132 ]]),
1: numpy.array([[ 0.07953279, -0.07829414], [-0.07829414, 0.13814242]])}
acc_Fnorm_Sigma_wij_ref1 = {0: numpy.array([[-0.29622691, 0.61411796], [ 0.09391764, -0.27955961], [-0.39014455, 0.89367757]]),
1: numpy.array([[ 0.04695882, -0.13977981], [-0.05718673, 0.24159665], [-0.17098161, 0.47326585]])}
acc_Snorm_ref1 = numpy.array([16.6, 22.4, 16.6, 61.4, 55., 97.4])
N_ref1 = numpy.array([0.6, 1.4])
t_ref1 = numpy.array([[ 1.59543739, 11.78239235], [ -3.20130371, -6.66379081], [ 4.79674111, 18.44618316],
[ -0.91765407, -1.5319461 ], [ 2.26805901, 3.03434944], [ 2.76600031, 4.9935962 ]])
sigma_ref1 = numpy.array([ 16.39472121, 34.72955353, 3.3108037, 43.73496916, 38.85472445, 68.22116903])
acc_Nij_Sigma_wij2_ref2 = {0: numpy.array([[ 0.50807426, -0.11907756], [-0.11907756, 0.12336544]]),
1: numpy.array([[ 1.18602399, -0.2835859 ], [-0.2835859 , 0.39440498]])}
acc_Fnorm_Sigma_wij_ref2 = {0: numpy.array([[ 0.07221453, 1.1189786 ], [-0.08681275, -0.35396112], [ 0.15902728, 1.47293972]]),
1: numpy.array([[-0.04340637, -0.17698056], [ 0.10662127, 0.21484933],[ 0.13116645, 0.64474271]])}
acc_Snorm_ref2 = numpy.array([16.6, 22.4, 16.6, 61.4, 55., 97.4])
N_ref2 = numpy.array([0.6, 1.4])
t_ref2 = numpy.array([[ 2.93105054, 11.89961223], [ -1.08988119, -3.92120757], [ 4.02093173, 15.82081981],
[ -0.17376634, -0.57366984], [ 0.26585634, 0.73589952], [ 0.60557877, 2.07014704]])
sigma_ref2 = numpy.array([5.12154025e+00, 3.48623823e+01, 1.00000000e-05, 4.37792350e+01, 3.91525332e+01, 6.85613258e+01])
acc_Nij_Sigma_wij2_ref = [acc_Nij_Sigma_wij2_ref1, acc_Nij_Sigma_wij2_ref2]
acc_Fnorm_Sigma_wij_ref = [acc_Fnorm_Sigma_wij_ref1, acc_Fnorm_Sigma_wij_ref2]
acc_Snorm_ref = [acc_Snorm_ref1, acc_Snorm_ref2]
N_ref = [N_ref1, N_ref2]
t_ref = [t_ref1, t_ref2]
sigma_ref = [sigma_ref1, sigma_ref2]
# Python implementation
# Machine
m = IVectorMachine(ubm, 2)
t = numpy.array([[1.,2],[4,1],[0,3],[5,8],[7,10],[11,1]])
sigma = numpy.array([1.,2.,1.,3.,2.,4.])
# Initialization
trainer = IVectorTrainerPy(sigma_update=True)
trainer.initialize(m, data)
m.t = t
m.sigma = sigma
for it in range(2):
# E-Step
trainer.e_step(m, data)
for k in acc_Nij_Sigma_wij2_ref[it]:
assert numpy.allclose(acc_Nij_Sigma_wij2_ref[it][k], trainer.m_acc_Nij_Sigma_wij2[k], 1e-5)
for k in acc_Fnorm_Sigma_wij_ref[it]:
assert numpy.allclose(acc_Fnorm_Sigma_wij_ref[it][k], trainer.m_acc_Fnorm_Sigma_wij[k], 1e-5)
assert numpy.allclose(acc_Snorm_ref[it], trainer.m_acc_Snorm, 1e-5)
assert numpy.allclose(N_ref[it], trainer.m_N, 1e-5)
# M-Step
trainer.m_step(m, data)
assert numpy.allclose(t_ref[it], m.t, 1e-5)
assert numpy.allclose(sigma_ref[it], m.sigma, 1e-5)
# C++ implementation
# Machine
m = IVectorMachine(ubm, 2)
m.variance_threshold = 1e-5
# Initialization
trainer = IVectorTrainer(update_sigma=True)
trainer.initialize(m)
m.t = t
m.sigma = sigma
for it in range(2):
# E-Step
trainer.e_step(m, data)
for k in acc_Nij_Sigma_wij2_ref[it]:
assert numpy.allclose(acc_Nij_Sigma_wij2_ref[it][k], trainer.acc_nij_wij2[k], 1e-5)
for k in acc_Fnorm_Sigma_wij_ref[it]:
assert numpy.allclose(acc_Fnorm_Sigma_wij_ref[it][k], trainer.acc_fnormij_wij[k], 1e-5)
assert numpy.allclose(acc_Snorm_ref[it].reshape(dim_c,dim_d), trainer.acc_snormij, 1e-5)
assert numpy.allclose(N_ref[it], trainer.acc_nij, 1e-5)
# M-Step
trainer.m_step(m)
assert numpy.allclose(t_ref[it], m.t, 1e-5)
assert numpy.allclose(sigma_ref[it], m.sigma, 1e-5)
def test_trainer_nosigma():
# Ubm
ubm = GMMMachine(2,3)
ubm.weights = numpy.array([0.4,0.6])
ubm.means = numpy.array([[1.,7,4],[4,5,3]])
ubm.variances = numpy.array([[0.5,1.,1.5],[1.,1.5,2.]])
# Defines GMMStats
gs1 = GMMStats(2,3)
log_likelihood1 = -3.
T1 = 1
n1 = numpy.array([0.4, 0.6], numpy.float64)
sumpx1 = numpy.array([[1., 2., 3.], [2., 4., 3.]], numpy.float64)
sumpxx1 = numpy.array([[10., 20., 30.], [40., 50., 60.]], numpy.float64)
gs1.log_likelihood = log_likelihood1
gs1.t = T1
gs1.n = n1
gs1.sum_px = sumpx1
gs1.sum_pxx = sumpxx1
gs2 = GMMStats(2,3)
log_likelihood2 = -4.
T2 = 1
n2 = numpy.array([0.2, 0.8], numpy.float64)
sumpx2 = numpy.array([[2., 1., 3.], [3., 4.1, 3.2]], numpy.float64)
sumpxx2 = numpy.array([[12., 15., 25.], [39., 51., 62.]], numpy.float64)
gs2.log_likelihood = log_likelihood2
gs2.t = T2
gs2.n = n2
gs2.sum_px = sumpx2
gs2.sum_pxx = sumpxx2
data = [gs1, gs2]
acc_Nij_Sigma_wij2_ref1 = {0: numpy.array([[ 0.03202305, -0.02947769], [-0.02947769, 0.0561132 ]]),
1: numpy.array([[ 0.07953279, -0.07829414], [-0.07829414, 0.13814242]])}
acc_Fnorm_Sigma_wij_ref1 = {0: numpy.array([[-0.29622691, 0.61411796], [ 0.09391764, -0.27955961], [-0.39014455, 0.89367757]]),
1: numpy.array([[ 0.04695882, -0.13977981], [-0.05718673, 0.24159665], [-0.17098161, 0.47326585]])}
acc_Snorm_ref1 = numpy.array([16.6, 22.4, 16.6, 61.4, 55., 97.4])
N_ref1 = numpy.array([0.6, 1.4])
t_ref1 = numpy.array([[ 1.59543739, 11.78239235], [ -3.20130371, -6.66379081], [ 4.79674111, 18.44618316],
[ -0.91765407, -1.5319461 ], [ 2.26805901, 3.03434944], [ 2.76600031, 4.9935962 ]])
acc_Nij_Sigma_wij2_ref2 = {0: numpy.array([[ 0.37558389, -0.15405228], [-0.15405228, 0.1421269 ]]),
1: numpy.array([[ 1.02076081, -0.57683953], [-0.57683953, 0.53912239]])}
acc_Fnorm_Sigma_wij_ref2 = {0: numpy.array([[-1.1261668 , 1.46496753], [-0.03579289, -0.37875811], [-1.09037391, 1.84372565]]),
1: numpy.array([[-0.01789645, -0.18937906], [ 0.35221084, 0.15854126], [-0.10004552, 0.72559036]])}
acc_Snorm_ref2 = numpy.array([16.6, 22.4, 16.6, 61.4, 55., 97.4])
N_ref2 = numpy.array([0.6, 1.4])
t_ref2 = numpy.array([[ 2.2133685, 12.70654597], [ -2.13959381, -4.98404887], [ 4.35296231, 17.69059484],
[ -0.54644055, -0.93594252], [ 1.29308324, 1.67762053], [ 1.67583072, 3.13894546]])
acc_Nij_Sigma_wij2_ref = [acc_Nij_Sigma_wij2_ref1, acc_Nij_Sigma_wij2_ref2]
acc_Fnorm_Sigma_wij_ref = [acc_Fnorm_Sigma_wij_ref1, acc_Fnorm_Sigma_wij_ref2]
acc_Snorm_ref = [acc_Snorm_ref1, acc_Snorm_ref2]
N_ref = [N_ref1, N_ref2]
t_ref = [t_ref1, t_ref2]
# Python implementation
# Machine
m = IVectorMachine(ubm, 2)
t = numpy.array([[1.,2],[4,1],[0,3],[5,8],[7,10],[11,1]])
sigma = numpy.array([1.,2.,1.,3.,2.,4.])
# Initialization
trainer = IVectorTrainerPy()
trainer.initialize(m, data)
m.t = t
m.sigma = sigma
for it in range(2):
# E-Step
trainer.e_step(m, data)
for k in acc_Nij_Sigma_wij2_ref[it]:
assert numpy.allclose(acc_Nij_Sigma_wij2_ref[it][k], trainer.m_acc_Nij_Sigma_wij2[k], 1e-5)
for k in acc_Fnorm_Sigma_wij_ref[it]:
assert numpy.allclose(acc_Fnorm_Sigma_wij_ref[it][k], trainer.m_acc_Fnorm_Sigma_wij[k], 1e-5)
assert numpy.allclose(acc_Snorm_ref[it], trainer.m_acc_Snorm, 1e-5)
assert numpy.allclose(N_ref[it], trainer.m_N, 1e-5)
# M-Step
trainer.m_step(m, data)
assert numpy.allclose(t_ref[it], m.t, 1e-5)
# C++ implementation
# Machine
m = IVectorMachine(ubm, 2)
# Initialization
trainer = IVectorTrainer()
trainer.initialize(m)
m.t = t
m.sigma = sigma
for it in range(2):
# E-Step
trainer.e_step(m, data)
for k in acc_Nij_Sigma_wij2_ref[it]:
assert numpy.allclose(acc_Nij_Sigma_wij2_ref[it][k], trainer.acc_nij_wij2[k], 1e-5)
for k in acc_Fnorm_Sigma_wij_ref[it]:
assert numpy.allclose(acc_Fnorm_Sigma_wij_ref[it][k], trainer.acc_fnormij_wij[k], 1e-5)
# M-Step
trainer.m_step(m)
assert numpy.allclose(t_ref[it], m.t, 1e-5)
#testing exceptions
nose.tools.assert_raises(RuntimeError, trainer.e_step, m, [1,2,2])
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)