core.nn.nsf.create_nsf_model

core.nn.nsf.create_nsf_model(
    input_dim,
    context_dim,
    num_flow_steps,
    base_transform_kwargs,
    embedding_net_builder=None,
    embedding_kwargs=None,
)

Build NSF model. This models the posterior distribution p(y|x).

The model consists of * a base distribution (StandardNormal, dim(y)) * a sequence of transforms, each conditioned on x

:param input_dim: int, dimensionality of y :param context_dim: int, dimensionality of the (embedded) context :param num_flow_steps: int, number of sequential transforms :param base_transform_kwargs: dict, hyperparameters for transform steps :param embedding_net_builder: Callable=None, build function for embedding network TODO :param embedding_kwargs: dict=None, hyperparameters for embedding network :return: Flow the NSF (posterior model)