Searched refs:p_dynamic_callables (Results 1 – 3 of 3) sorted by relevance
| /dports/science/py-GPy/GPy-1.10.0/GPy/models/ |
| H A D | state_space_main.py | 1202 cls._kalman_prediction_step_SVD(k, prev_mean ,P_upd, p_dynamic_callables,
1207 cls._kalman_prediction_step(k, prev_mean ,P[k,:,:], p_dynamic_callables,
1834 p_P_prev_step, p_dynamic_callables): argument
1870 A = p_dynamic_callables.Ak(k,p_m,p_P) # state transition matrix (or Jacobian)
1893 def rts_smoother(cls,state_dim, p_dynamic_callables, filter_means, argument
1949 filter_covars[k,:,:], p_dynamic_callables,
3055 cls._kalman_prediction_step_SVD(k, prev_mean ,P_upd, p_dynamic_callables,
3060 cls._kalman_prediction_step(k, prev_mean ,P[k,:,:], p_dynamic_callables,
3121 p_dynamic_callables=None, X=None, F=None,L=None,Qc=None): argument
3162 if p_dynamic_callables is None: # make this object from scratch
[all …]
|
| H A D | state_space_cython.pyx | 548 Dynamic_Callables_Cython p_dynamic_callables, argument
618 …cdef np.ndarray[DTYPE_t, ndim=2] A = p_dynamic_callables.Ak(k,p_m,Prev_cov) # state transition mat…
619 …cdef np.ndarray[DTYPE_t, ndim=2] Q = p_dynamic_callables.Qk(k) # state noise matrx. This is necess…
620 cdef np.ndarray[DTYPE_t, ndim=2] Q_sr = p_dynamic_callables.Q_srk(k)
622 cdef np.ndarray[DTYPE_t, ndim=2] m_pred = p_dynamic_callables.f_a(k, p_m, A) # predicted mean
655 dA_all_params = p_dynamic_callables.dAk(k) # derivatives of A wrt parameters
656 dQ_all_params = p_dynamic_callables.dQk(k) # derivatives of Q wrt parameters
912 … _cont_discr_kalman_filter_raw_Cython(int state_dim, Dynamic_Callables_Cython p_dynamic_callables, argument
967 _kalman_prediction_step_SVD_Cython(k, prev_mean ,P_upd, p_dynamic_callables,
1001 return (M, P, log_likelihood, grad_log_likelihood, p_dynamic_callables.reset(False))
|
| H A D | state_space_model.py | 257 p_dynamic_callables=SmootherMatrObject, X=X, F=F,L=L,Qc=Qc)
|