sbi

sbi copied to clipboard

Allow import of `NeuralPosteriorEnsemble` from sbi.utils

19

Hello, See the question at the end of the post concerning the use of multi observations (ie. amortized). I'm playing with the use case exposed in the [The flexible interface...

jecampagne

log_prob fails for Restricted Prior when sampling with SIR

8

I am trying to use a restricted prior as a proposal and when creating it with the parameter SIR the process_prior function fails because it cannot calculate the log prob....

rmehta1987

resume_training no longer working

1

AssertionError: You have already trained this neural network. After you had trained the network,

michaeldeistler

Use custom dataloader for training

5

Hello, is there a straightforward way to use custom pytorch `DataLoader` for training, instead of the `append_simulations` method? I didn't find this information in the documentation. This will allow us...

h3jia

Crash with SNPE "mdn" after multi-rounds: NaN/Inf present in posterior eval.

2

Hi, I experience this Nan/Inf crash (sorry but it was after a long rounds run) ``` Round[5]: density_estimator training Using SNPE-C with atomic loss Training neural network. Epochs trained: 17Traceback...

jecampagne

Amortizedsample

3

michaeldeistler

1005 implement l c2st metric

14

## What does this implement/fix? Explain your changes L-C2ST(-NF) diagnostic: class, tutorial and tests. ## Does this close any currently open issues? Fixes #1005 ## Any relevant code examples, logs,...

JuliaLinhart

Use conventional commits and commit linter?

1

For previous releases we crafted the `CHANGELOG.md` by hand. For the upcoming release this is a lot of work. So I looked into automated tools and came across: - https://www.conventionalcommits.org/en/v1.0.0/...

janfb

Base estimator class

1

## What does this implement/fix? Explain your changes Implements an abstract base class for estimators, which has: - `input_shape` - `condition_shape` - abstract loss function. ## Does this close any...

manuelgloeckler

998 improving abc methods for trial based data using statistical distances

2

## What does this implement/fix? Explain your changes Adding an approximation of the squared 2-Wasserstein distance based on Sinkhorn iterations as an additional statistical distance to the available metrics. Furthermore,...

theogruner