networks

A rich collection of neural network architectures for use in Approximators.

Examples

>>> import bayesflow as bf
>>> approximator = bf.ContinuousApproximator(
...     inference_network=bf.networks.CouplingFlow(),
...     summary_network=bf.networks.DeepSet(),
... )

Modules

inference	Generative neural networks for approximating conditional distributions.
summary	Neural networks for learning maximally informative compressions of data modalities such as images, timeseries, sets and combinations thereof.
subnets	Reusable network components.
defaults	Frozen default configuration dicts for inference network subnets and solvers.