Problem in the Dependent density regression example

Questions
1

Hi,

I tried to run the Dependent density regression example using PyMC3 (version 3.4.1):
https://docs.pymc.io/notebooks/dependent_density_regression.html

And when running

PP_SAMPLES = 5000

lidar_pp_x = np.linspace(std_range.min() - 0.05, std_range.max() + 0.05, 100)
x_lidar.set_value(lidar_pp_x[:, np.newaxis])

with model:
    pp_trace = pm.sample_ppc(trace, PP_SAMPLES, random_seed=SEED)

I get

ValueError: cannot reshape array of size 8840000 into shape (221,20)

2

Thanks for reporting. I think this is a bug: https://github.com/pymc-devs/pymc3/issues/2954

3

now, I do that again .when
pp_trace = pm.sample_posterior_predictive(trace, PP_SAMPLES, random_seed=SEED)

I encount a problem :ValueError: probabilities do not sum to 1

my version is PyMC3 v3.8

ps:when I set PP_SAMPLES = 1800， it can run through !