def test_gmm_test():
# Tests a GMMMachine by computing scores against a model and comparing to a reference
ar = load_array(resource_filename("bob.learn.em", "data/dataforMAP.hdf5"))
# Initialize GMMMachine
n_gaussians = 5
gmm = GMMMachine(n_gaussians)
gmm.means = load_array(
resource_filename("bob.learn.em", "data/meansAfterML.hdf5"))
gmm.variances = load_array(
resource_filename("bob.learn.em", "data/variancesAfterML.hdf5"))
gmm.weights = load_array(
resource_filename("bob.learn.em", "data/weightsAfterML.hdf5"))
threshold = 0.001
gmm.variance_thresholds = threshold
# Test against the model
score_mean_ref = -1.50379e06
for transform in (to_numpy, to_dask_array):
ar = transform(ar)
score = gmm.log_likelihood(ar).sum()
score /= len(ar)
# Compare current results to torch3vision
assert abs(score - score_mean_ref) / score_mean_ref < 1e-4
def test_GMMMachine_single_ll_vs_multiple():
np.random.seed(3) # FIXING A SEED
data = np.random.rand(
100, 50
) # Doesn't matter if it is random. The average of 1D array (in python) MUST output the same result for the 2D array (in C++)
gmm = GMMMachine(n_gaussians=2)
gmm.weights = load_array(
resource_filename("bob.learn.em", "data/weights.hdf5"))
gmm.means = load_array(resource_filename("bob.learn.em",
"data/means.hdf5"))
gmm.variances = load_array(
resource_filename("bob.learn.em", "data/variances.hdf5"))
ll = 0
for i in range(data.shape[0]):
ll += gmm.log_likelihood(data[i, :])
ll /= data.shape[0]
assert np.isclose(ll, gmm.log_likelihood(data).mean())
def test_likelihood():
data = np.array([[1, 1, 1], [-1, 0, 0], [0, 0, 1], [2, 2, 2]])
n_gaussians = 3
machine = GMMMachine(n_gaussians)
machine.means = np.repeat([[0], [1], [-1]], 3, 1)
machine.variances = np.ones_like(machine.means)
for transform in (to_numpy, to_dask_array):
data = transform(data)
log_likelihood = machine.log_likelihood(data)
expected_ll = np.array([
-3.6519900964986527,
-3.83151883210222,
-3.83151883210222,
-5.344374066745753,
])
np.testing.assert_almost_equal(log_likelihood, expected_ll)
def test_likelihood_weight():
data = np.array([[1, 1, 1], [-1, 0, 0], [0, 0, 1], [2, 2, 2]])
n_gaussians = 3
machine = GMMMachine(n_gaussians)
machine.means = np.repeat([[0], [1], [-1]], 3, 1)
machine.variances = np.ones_like(machine.means)
machine.weights = [0.6, 0.1, 0.3]
for transform in (to_numpy, to_dask_array):
data = transform(data)
log_likelihood = machine.log_likelihood(data)
expected_ll = np.array([
-4.206596356117164,
-3.492325679996329,
-3.634745457950943,
-6.49485678536014,
])
np.testing.assert_almost_equal(log_likelihood, expected_ll)
def test_GMMMachine_ll_computation():
"""Test a GMMMachine (log-likelihood computation)"""
data = load_array(resource_filename("bob.learn.em", "data/data.hdf5"))
gmm = GMMMachine(n_gaussians=2)
gmm.weights = load_array(
resource_filename("bob.learn.em", "data/weights.hdf5"))
gmm.means = load_array(resource_filename("bob.learn.em",
"data/means.hdf5"))
gmm.variances = load_array(
resource_filename("bob.learn.em", "data/variances.hdf5"))
# Compare the log-likelihood with the one obtained using Chris Matlab implementation
matlab_ll_ref = -2.361583051672024e02
np.testing.assert_almost_equal(gmm.log_likelihood(data),
matlab_ll_ref,
decimal=10)
def test_likelihood_variance():
data = np.array([[1, 1, 1], [-1, 0, 0], [0, 0, 1], [2, 2, 2]])
n_gaussians = 3
machine = GMMMachine(n_gaussians)
machine.means = np.repeat([[0], [1], [-1]], 3, 1)
machine.variances = np.array([
[1.1, 1.2, 0.8],
[0.2, 0.4, 0.5],
[1, 1, 1],
])
for transform in (to_numpy, to_dask_array):
data = transform(data)
log_likelihood = machine.log_likelihood(data)
expected_ll = np.array([
-2.202846959440514,
-3.8699524542323793,
-4.229029034375473,
-6.940892214952679,
])
np.testing.assert_almost_equal(log_likelihood, expected_ll)
