def gmm_em(dataList, nmix, final_niter, ds_factor):
dataList = load_data(dataList)
nfiles = len(dataList)
gm, gv = comp_gm_gv(dataList)
#niter = [1,2,4,4,4,4,6,6,10,10,15]
#niter[int(np.log2(nmix))] = final_niter
niter = np.ones(10, dtype=np.int32)
model = GaussianMixture(1, 'diag', verbose=0, max_iter=100)
data = np.concatenate(dataList, axis=1).T
mix = 1
while mix <= nmix:
if mix >= nmix // 2:
ds_factor = 1
print('\nRe-estimating the GMM hyperparameters for %d components ...' %
mix)
for i in range(niter[int(np.log2(mix))]):
print('EM iter#: %d \t' % i, end='')
model.fit(data)
w = model.weights_
sigma = model.covariances_
sigma = apply_var_floors(w, sigma, 1)
model.precisions_ = 1 / sigma
model.covariances = sigma
llk, _ = model._estimate_log_prob_resp(data)
print('[llk = %.2f]' % np.mean(llk))
if mix < nmix:
model = mixup(model)
mix *= 2
pass
def test_log_responsibilities(self):
"""
Test the log responsibilities with the help of Sklearn.
"""
N = 16384
S = 2048
D = 128
means = torch.randn(S, D)
covs = torch.rand(S)
x = torch.randn(N, D)
prior = torch.rand(S)
prior /= prior.sum()
mixture = GaussianMixture(S, covariance_type='spherical')
mixture.means_ = means.numpy()
mixture.precisions_cholesky_ = np.sqrt(1 / covs.numpy())
mixture.weights_ = prior.numpy()
# pylint: disable=protected-access
_, expected = mixture._estimate_log_prob_resp(x.numpy())
expected = torch.from_numpy(expected)
probs = log_normal(x, means, covs, 'spherical')
predicted = log_responsibilities(probs, prior)
self.assertTrue(
torch.allclose(expected, predicted, atol=1e-03, rtol=1e-05))
def test__estimate_log_prob_resp_spherical_shared_compression(self):
rs = np.random.RandomState(11)
cov_type = 'spherical'
gmm = GaussianMixture(n_components=3,
num_feat_full=5,
num_feat_comp=3,
num_feat_shared=3,
num_samp=4,
transform=None,
mask=None,
D_indices=None,
covariance_type=cov_type,
random_state=rs)
gmm.fit_sparsifier(X=self.td.X)
means = rs.rand(gmm.n_components, gmm.num_feat_full)
covariances = rs.rand(gmm.n_components)
weights = rs.rand(gmm.n_components)
weights /= weights.sum()
log_prob_test, log_resp_test, log_prob_norm_test = gmm._estimate_log_prob_resp(
weights, means, covariances, cov_type)
# find skl's values, pretty ugly to do.
precisions = _compute_precision_cholesky(covariances, cov_type)
gmm_skl = GMSKL(n_components=3, covariance_type=cov_type)
# we need the mask to be shared so that we can use mask[0] on all means
gmm_skl.means_ = means[:, gmm.mask[0]]
gmm_skl.precisions_cholesky_ = precisions
gmm_skl.weights_ = weights
gmm_skl.covariance_type_ = cov_type
log_prob_norm_true, log_resp_true = gmm_skl._estimate_log_prob_resp(
gmm.RHDX)
# if anything is bad later this overwrite with mean seems suspect:
log_prob_norm_true = log_prob_norm_true.mean()
# now get the log_prob from another function
log_prob_true = _estimate_log_gaussian_prob(gmm.RHDX, gmm_skl.means_,
precisions, cov_type)
# run the tests
self.assertArrayEqual(log_prob_test, log_prob_true)
self.assertArrayEqual(log_prob_norm_true, log_prob_norm_test)
self.assertArrayEqual(log_resp_true, log_resp_test)
def test__estimate_log_prob_resp_diagonal_no_compression(self):
cov_type = 'diag'
gmm = GaussianMixture(n_components=3,
num_feat_full=5,
num_feat_comp=5,
num_feat_shared=5,
num_samp=4,
transform=None,
mask=None,
D_indices=None,
covariance_type=cov_type)
gmm.fit_sparsifier(X=self.td.X)
means = np.random.rand(gmm.n_components, gmm.num_feat_comp)
covariances = np.random.rand(gmm.n_components, gmm.num_feat_comp)
weights = np.random.rand(gmm.n_components)
weights /= weights.sum()
log_prob_test, log_resp_test, log_prob_norm_test = gmm._estimate_log_prob_resp(
weights, means, covariances, cov_type)
# find skl's values, pretty ugly to do.
precisions = _compute_precision_cholesky(covariances, cov_type)
gmm_skl = GMSKL(n_components=3, covariance_type=cov_type)
gmm_skl.means_ = means
gmm_skl.precisions_cholesky_ = precisions
gmm_skl.weights_ = weights
gmm_skl.covariance_type_ = cov_type
log_prob_norm_true, log_resp_true = gmm_skl._estimate_log_prob_resp(
self.td.X)
# if anything is bad later this overwrite with mean seems suspect:
log_prob_norm_true = log_prob_norm_true.mean()
# now get the log_prob from another function
log_prob_true = _estimate_log_gaussian_prob(self.td.X, means,
precisions, cov_type)
# run the tests
self.assertArrayEqual(log_prob_test, log_prob_true)
self.assertArrayEqual(log_prob_norm_true, log_prob_norm_test)
self.assertArrayEqual(log_resp_true, log_resp_test)
