summary

Neural networks for learning maximally informative compressions of data modalities such as images, timeseries, sets and combinations thereof.

Classes

ConvolutionalNetwork(*args, **kwargs)	A convolutional summary network with residual blocks.
DeepSet(*args, **kwargs)	(SN) Implements a deep set encoder introduced in [1, 2] for learning permutation-invariant representations of set-based data, as generated by exchangeable models.
FusionNetwork(*args, **kwargs)	(SN) Wraps multiple summary networks (backbones) to learn summary statistics from multi-modal data.
FusionTransformer(*args, **kwargs)	Fusion transformer summary network for time series.
RecurrentNetwork(*args, **kwargs)	Recurrent summary network for time series.
SetTransformer(*args, **kwargs)	Set transformer summary network.
SummaryNetwork(*args, **kwargs)	Abstract base class for all summary networks in BayesFlow.
TimeSeriesNetwork(*args, **kwargs)	(SN) Implements a LSTNet Architecture as described in [1], with addition tweaks for performance and stability.
TimeSeriesTransformer(*args, **kwargs)	Transformer summary network for time series.