apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-08 03:22:38 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

[sparse GP] fallback for other inference methods for missing_data

Browse source
This commit is contained in:
Max Zwiessele 2014-10-17 17:32:51 +01:00
parent ac224c0dbd
commit b94ebc2aa2
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
GPy/core/sparse_gp.py
View file

@ -110,7 +110,10 @@ class SparseGP(GP):
like them into this dictionary for inner use of the indices inside the
algorithm.
"""
posterior, log_marginal_likelihood, grad_dict = self.inference_method.inference(kern, X, Z, likelihood, Y, Y_metadata, Lm=Lm, dL_dKmm=None)
try:
posterior, log_marginal_likelihood, grad_dict = self.inference_method.inference(kern, X, Z, likelihood, Y, Y_metadata, Lm=Lm, dL_dKmm=None)
except:
posterior, log_marginal_likelihood, grad_dict = self.inference_method.inference(kern, X, Z, likelihood, Y, Y_metadata)
current_values = {}
likelihood.update_gradients(grad_dict['dL_dthetaL'])
current_values['likgrad'] = likelihood.gradient.copy()