Bad performance Bayesian Convolutional Neural Network - Misc. - Pyro ...
Apr 28, 2025 · Hello Pyro community, I’m trying to build a Bayesian CNN for MNIST classification using Pyro, but despite seeing the ELBO loss decrease to around 10 during training, the model’s predictive …
Pyro Discussion Forum
Aug 14, 2025 · Forum For Pyro Developers
numpyro - Pyro Discussion Forum
Jun 3, 2019 · Forum For Pyro Developers
Help post，shape problem - Pyro Discussion Forum
Apr 25, 2025 · with pyro.plate("data", x.size(0)): pyro.sample("obs", dist.Normal(mu, sigma), obs=y.squeeze(-1),infer={"scale": annealing_factor}) #obs，真实数据+噪声
GPU available but slow compared to CPU on BNN example - numpyro
Nov 25, 2021 · Well, It is a VI + NeuraReparametrisation to perform a NUTS. Currently, we have found that the job runs 100% on CPU while GPU memory is activated. it’s as if the CPU was going back …
Reducing MCMC memory usage - numpyro - Pyro Discussion Forum
Oct 15, 2023 · I am running NUTS/MCMC (on multiple CPU cores) for a quite large dataset (400k samples) for 4 chains x 2000 steps. mcmc.run actually ran until the end, but then died with an out-of …
Implementation & normalizing flow in matrix normal distribution
Nov 1, 2024 · Hi, I’m working on a model where the likelihood follows a matrix normal distribution, X ~ MN_{n,p} (M, U, V). I’m using conjugate priors: M ~ MN U ~ Inverse Wishart V ~ Inverse Wishart As …
Multiple Sample Sites/ Infer Discrete - Pyro Discussion Forum
Sep 6, 2022 · Thanks, @fehiepsi – following that pattern (trace and replay) has been working for me. I do have one continuing problem. I’d like a class probability (and ideally a distribution), not just a class …
Extra sampling site in manual guide compared to model - numpyro
Mar 12, 2025 · i see. this would appear to be a bug/unsupported feature. if you like, you can make a feature request on github (please include a code snippet and stack trace). however, in the short term …
Mixture model with discrete data in Numpyro - Pyro Discussion Forum
Mar 6, 2024 · Hi. Apologies for the rather long post. I am trying to modify the code from the Gaussian mixture model tutorial (I have also pulled bits of code from various other posts on this forum and …