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] 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)	(SN) Implements a more flexible version of the TimeSeriesTransformer that applies a series of self-attention layers followed by cross-attention between the representation and a learnable template summarized via a recurrent net.
SetTransformer(*args, **kwargs)	(SN) Implements the set transformer architecture from [1] which ultimately represents a learnable permutation-invariant function.
SummaryNetwork(*args, **kwargs)	Abstract base class for all summary networks in BayesFlow.
TimeSeriesNetwork(*args, **kwargs)	(SN) Implements a LSTNet Architecture as described in [1]
TimeSeriesTransformer(*args, **kwargs)	(SN) Creates a regular transformer coupled with Time2Vec embeddings of time used to flexibly compress time series.