[Question] Access the ELBO loss for bgplvm

SheffieldML / GPy

Gaussian processes framework in python

BSD 3-Clause "New" or "Revised" License

2.04k stars 562 forks source link

Open vr308 opened 3 years ago

vr308 commented 3 years ago

Hi,

I am wondering if there was a way to access the trace of the ELBO loss (objective) for the Bayesian GPLVM model?

model = BayesianGPLVM(Y_train, input_dim=12, num_inducing=20 ,init='PCA')
model.optimize(max_iters=1000)

model.optimize() doesn't return anything and I don't see such a helper method for the post trained model but perhaps there is a way to access it?

Thanks!

lawrennd commented 3 years ago

I think it should just be model.log_likelihood()