Hi, We are trying to perform prior predictive sampling with a custom distribution that we built. The code is like this: with pm.Model() as ddm_pymc: v = pm.Uniform("v", lower=-10.0, upper=10.0) a = pm.HalfNormal("a", sigma=2.0) z = pm.Uniform("z", lower=0.01, upper=0.99) t = pm.Uni…

That’s not a very useful error message. By default PyTensor looks for some multivariate parameter to try and guess the support shape. I think we should disable that default and raise an informative message. You need to override the _supp_shape_from_params method. In your case it’s pretty simple jus…

`pm.sample_prior_predictive()` fails with incorrect size info passed to the `rng_fn` function of the RandomVariable

Questions v5

ricardoV94 July 14, 2023, 5:36pm 4

Multivariate variables can have scalar parameters, so it shouldn’t be an issue.

Topic		Replies	Views
Sample_prior_predictive() failing based solely on `samples` parameter Questions	9	999	March 22, 2019
Sample_prior_predictive failing with shape argument Questions	7	506	May 10, 2021
Sample_prior_predictive bug, gives wrong shape for dependent variable? Questions	2	458	July 29, 2019
Error with sample_prior_predictive Questions	2	610	November 4, 2018
Shape error when sampling more than one value Questions	13	1907	December 20, 2018

`pm.sample_prior_predictive()` fails with incorrect size info passed to the `rng_fn` function of the RandomVariable

Related topics