numpyro
numpyro copied to clipboard
pyro-ppl
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
I ran across this issue when trying to evaluate the `log_prob` of the guide at the positions from and HMC chain, to do this the positions need to be flattened...
# Description I miss truncated power law distribution in NumPyro alot. I have implemented them on side for my own use. I was thinking if we could add them to...
This PR addresses [this issue](https://github.com/pyro-ppl/numpyro/issues/1845#issuecomment-2284569263), improving the docs for how the `Predictive` class is expected to function. In particular, I try to make it more clear that the observations should...
Hi! I have seen Pyro has a CodeCov (https://about.codecov.io/) badge, and I think this is a handy tool, not only to see how is the test coverage but also on...
Hello, It wasn't clear to me until I dug into some strange behaviour that the `Predictive` method requires setting `obs` to `None`. I see now that the examples do it,...
This fixes issue #1834 for `MixedHMC` sampling with `DiscreteUniform` distribution sampling outside the support without using the `enumerate_support`.
When calling `numpyro.render_model(model, filename=my_path)` I was expecting the generated file to be saved in `my_path`. But it does not. Reading the source code, it seems that it deliberately use `filename.stem`...
Hello, I noticed that samples have value outside the support for `DiscreteUniform` distribution. Here is a simple reproducible example: ```python import jax.random import numpyro import numpyro.distributions as dist from numpyro.infer...
Hi everyone, I'm working on an ODE based model (solver from diffrax) for respiratory viruses fitted on past seasons of data. At the moment, we occasionally have maximum iteration fails...
