Skip to content
Snippets Groups Projects
Commit 6541b440 authored by Yannick DAYER's avatar Yannick DAYER
Browse files

[refactor] Cleaning reference comments from c++

parent 0e5c7756
No related branches found
No related tags found
1 merge request!60Port of I-Vector to python
Hide whitespace changes
Inline Side-by-side
bob/learn/em/ivector.py
+ 10
− 109
View file @ 6541b440
......@@ -78,27 +78,6 @@ class IVectorStats:
def compute_tct_sigmac_inv(T: np.ndarray, sigma: np.ndarray) -> np.ndarray:
"""Computes T_{c}^{T}.sigma_{c}^{-1}"""
# C++ to port to python:
#
# for (int c=0; c<C; ++c)
# {
# blitz::Array<double,2> Tct_sigmacInv = m_cache_Tct_sigmacInv(c, rall, rall);
# blitz::Array<double,2> Tc = m_T(blitz::Range(c*D,(c+1)*D-1), rall);
# blitz::Array<double,2> Tct = Tc.transpose(1,0);
# blitz::Array<double,1> sigma_c = m_sigma(blitz::Range(c*D,(c+1)*D-1));
# Tct_sigmacInv = Tct(i,j) / sigma_c(j);
# }
# Python version:
# Tct_sigmacInv = np.zeros(shape=(c,d,t))
# for c in range(dim_c):
# Tc = T[c]
# Tct = Tc.transpose(1, 0)
# sigma_c = sigma[c]
# Tct_sigmacInv[c] = T[c].t / sigma[c]
# Vectorized version:
# TT_sigma_inv (c,t,d) = T.T (c,t,d) / sigma (c,1,d)
Tct_sigmacInv = T.transpose(0, 2, 1) / sigma[:, None, :]
......@@ -108,18 +87,8 @@ def compute_tct_sigmac_inv(T: np.ndarray, sigma: np.ndarray) -> np.ndarray:
def compute_tct_sigmac_inv_tc(T: np.ndarray, sigma: np.ndarray) -> np.ndarray:
"""Computes T_{c}^{T}.sigma_{c}^{-1}.T_{c}"""
# for (int c=0; c<C; ++c)
# {
# blitz::Array<double,2> Tc = m_T(blitz::Range(c*D,(c+1)*D-1), rall);
# blitz::Array<double,2> Tct_sigmacInv = m_cache_Tct_sigmacInv(c, rall, rall);
# blitz::Array<double,2> Tct_sigmacInv_Tc = m_cache_Tct_sigmacInv_Tc(c, rall, rall);
# bob::math::prod(Tct_sigmacInv, Tc, Tct_sigmacInv_Tc);
# }
Tct_sigmacInv_Tc = np.zeros(shape=(T.shape[0], T.shape[-1], T.shape[-1]))
# Python version:
tct_sigmac_inv = compute_tct_sigmac_inv(T, sigma)
for c in range(T.shape[0]): # TODO Vectorize
# (c,t,t) = (c,t,d) @ (c,d,t)
......@@ -132,14 +101,6 @@ def compute_tct_sigmac_inv_tc(T: np.ndarray, sigma: np.ndarray) -> np.ndarray:
def compute_id_tt_sigma_inv_t(
stats: GMMStats, T: np.ndarray, sigma: np.ndarray
) -> np.ndarray:
# void bob::learn::em::IVectorMachine::computeIdTtSigmaInvT(
# const bob::learn::em::GMMStats& gs, blitz::Array<double,2>& output) const
# {
# blitz::Range rall = blitz::Range::all();
# bob::math::eye(output);
# for (int c=0; c<(int)getNGaussians(); ++c)
# output += gs.n(c) * m_cache_Tct_sigmacInv_Tc(c, rall, rall);
# }
dim_t = T.shape[-1]
output = np.eye(dim_t, dim_t)
tct_sigmac_inv_tc = compute_tct_sigmac_inv_tc(T, sigma)
......@@ -159,22 +120,6 @@ def compute_tt_sigma_inv_fnorm(
Returns an array of shape (t,)
"""
# void bob::learn::em::IVectorMachine::computeTtSigmaInvFnorm(
# const bob::learn::em::GMMStats& gs, blitz::Array<double,1>& output) const
# {
# // Computes \f$T^{T} \Sigma^{-1} \sum_{c=1}^{C} (F_c - N_c ubmmean_{c})\f$
# blitz::Range rall = blitz::Range::all();
# output = 0;
# for (int c=0; c<(int)getNGaussians(); ++c)
# {
# m_tmp_d = gs.sumPx(c,rall) - gs.n(c) * m_ubm->getGaussian(c)->getMean();
# blitz::Array<double,2> Tct_sigmacInv = m_cache_Tct_sigmacInv(c, rall, rall);
# bob::math::prod(Tct_sigmacInv, m_tmp_d, m_tmp_t2);
# output += m_tmp_t2;
# }
# }
output = np.zeros(shape=T.shape[-1])
tct_sigmac_inv = compute_tct_sigmac_inv(T, sigma) # (c,t,d)
fnorm = stats.sum_px - stats.n[:, None] * ubm_means # (c,d)
......@@ -224,9 +169,6 @@ class IVectorMachine(BaseEstimator):
self.convergence_threshold = convergence_threshold
self.max_iterations = max_iterations
self.update_sigma = update_sigma
# TODO: add params
# self.compute_likelihood = compute_likelihood
# self.variance_floor = variance_floor
self.dim_c = self.ubm.n_gaussians
self.dim_d = self.ubm.means.shape[-1]
self.variance_floor = variance_floor
......@@ -253,21 +195,6 @@ class IVectorMachine(BaseEstimator):
sample, self.T, self.sigma
) # self.compute_Id_TtSigmaInvT(data[n]), # shape: (t,t)
# Fnorm = np.zeros(
# shape=(
# self.dim_c,
# self.dim_d,
# ),
# dtype=float,
# )
# Snorm = np.zeros(
# shape=(
# self.dim_c,
# self.dim_d,
# ),
# dtype=float,
# )
# Latent variables
I_TtSigmaInvNT_inv = np.linalg.inv(I_TtSigmaInvNT) # shape: (t,t)
sigma_w_ij = np.dot(
......@@ -278,18 +205,6 @@ class IVectorMachine(BaseEstimator):
) # shape: (t,t)
# Compute normalized statistics
# for c in range(self.dim_c): # TODO Vectorize
# Fc = Fij[c, :]
# Sc = Sij[c, :]
# mc = self.ubm.means[c]
# Fc_mc = Fc * mc
# Nc_mc_mcT = Nij[c] * mc * mc
# Fnorm[c] = Fc - Nij[c] * mc
# Snorm[c] = Sc - (2 * Fc_mc) + Nc_mc_mcT
Fnorm = Fij - Nij[:, None] * self.ubm.means
Snorm = (
Sij
......@@ -304,12 +219,8 @@ class IVectorMachine(BaseEstimator):
stats.nij_sigma_wij2[c] += (
Nij[c] * sigma_w_ij2
) # (dim_t, dim_t)
# stats.nij_sigma_wij2 += Nij[:, None] * sigma_w_ij2 # (c, t, t) # TODO Not working
# stats.nij_sigma_wij2 += Nij[:, None] * sigma_w_ij2 # (c, t, t) # TODO Vectorized v. Not working
stats.nij += Nij
# for c in range(self.dim_c): # TODO Vectorize
# stats.fnorm_sigma_wij[c] += np.outer(
# Fnorm[c], sigma_w_ij # (c,d) x (t,)
# ) # (dim_d, dim_t)
stats.fnorm_sigma_wij += np.matmul(
Fnorm[:, :, None], sigma_w_ij[None, :]
) # (c,d,t)
......@@ -318,16 +229,6 @@ class IVectorMachine(BaseEstimator):
def m_step(self, stats: IVectorStats) -> None:
"""Updates the Machine with the maximization step of the e-m algorithm."""
A = stats.nij_sigma_wij2
# self.T = np.zeros(
# shape=(self.dim_c, self.dim_d, self.dim_t),
# dtype=np.float64,
# )
# if self.update_sigma:
# self.sigma = np.zeros(
# shape=stats.snormij.shape, dtype=np.float64
# )
for c in range(self.dim_c): # TODO Vectorize
# T update
A = stats.nij_sigma_wij2[c].transpose()
......@@ -356,7 +257,7 @@ class IVectorMachine(BaseEstimator):
``max_iterations`` is reached.
"""
t_old = 0
# t_old = 0
for step in range(self.max_iterations):
logger.debug(f"IVector step {step+1}.")
# E-step
......@@ -364,14 +265,14 @@ class IVectorMachine(BaseEstimator):
# M-step
self.m_step(stats)
# Convergence
if step > 0:
if np.linalg.norm(stats.t - t_old) < self.convergence_threshold:
logger.info(f"Converged after {step+1} steps.")
logger.debug(
f"t_diff: {stats.t - t_old} (Convergence threshold: {self.convergence_threshold})"
)
break
t_old = stats.t
# if step > 0:
# if np.linalg.norm(stats.t - t_old) < self.convergence_threshold:
# logger.info(f"Converged after {step+1} steps.")
# logger.debug(
# f"t_diff: {stats.t - t_old} (Convergence threshold: {self.convergence_threshold})"
# )
# break
# t_old = stats.t
else:
logger.info(f"Did not converge after {step+1} steps.")
return self
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment