Frequently asked questions

Can the algorithms deal with invalid data, e.g. NaN or inf?

What should I do when my ‘posterior samples are outside of the prior support’ in SNPE?

When using multiple workers, I get a pickling error. Can I still use multiprocessing?

Can I use the GPU for training the density estimator?

How should I save and load objects in sbi?

Can I stop neural network training and resume it later?

How can I use a prior that is not defined in PyTorch?