大家一起来完善官方教程汉化版 - Pyro Discussion Forum
Apr 13, 2020 · 要做一些高斯过程相关的研究，刚接触pyro， 浏览了你的Introduction部分，能在翻译原教程的基础上加入概率图和重点提炼等以帮助理解，着实不错，当然这也是我个人觉得汉 …
Bad performance Bayesian Convolutional Neural Network - Misc.
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 …
Pyro Discussion Forum
Aug 18, 2025 · Forum For Pyro Developers
Stochastic Block Model using Pyro - Pyro Discussion Forum
Nov 30, 2020 · Initially, Pyro seemed to provide all that and above all a very detailed documentation with many examples. However, for above stated reasons, the implementation …
Model and guide shapes disagree at site - Pyro Discussion Forum
May 1, 2019 · Model and guide shapes disagree at site ‘z_2’: torch.Size ( [2, 2]) vs torch.Size ( [2]) Anyone has the clue, why the shapes disagree at some point? Here is the z_t sample site …
Learning rate scheduling in numpyro - Pyro Discussion Forum
Sep 18, 2023 · pyro provides access to the pytorch schedulers, and the pyro ClippedAdam also has a specific learning rate decay parameter. I can not find anything of the sort in numpyro, …
Multi GPU num_samples - Pyro Discussion Forum
Jan 10, 2021 · Hello I was wondering if it’s possible to parallelize the number of particles used to estimate the ELBO over multiple GPUs (i.e. num_particles=40, and if we have 4 GPUs, then …
Moving MCMC from CPU to GPU - Pyro Discussion Forum
May 9, 2022 · Hi all, I’ve read a few posts on the forum about how to use GPU for MCMC: Transfer SVI, NUTS and MCMC to GPU (Cuda), How to move MCMC run on GPU to CPU …
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 …
SVI doesn't change parameters - Pyro Discussion Forum
Nov 7, 2018 · Usually you’d use fixed “prior” parameters in the model and learnable “posterior” parameters in the guide, and only the learnable parameters would require pyro.param …