nessai.flows.nsf
================

.. py:module:: nessai.flows.nsf

.. autoapi-nested-parse::

   Implementation of Neural Spline Flows.

   ..
       !! processed by numpydoc !!


Classes
-------

.. autoapisummary::

   nessai.flows.nsf.NeuralSplineFlow


Module Contents
---------------

.. py:class:: NeuralSplineFlow(features, hidden_features, num_layers, num_blocks_per_layer, num_bins=8, context_features=None, activation=F.relu, dropout_probability=0.0, batch_norm_within_layers=False, batch_norm_between_layers=False, apply_unconditional_transform=False, linear_transform='permutation', tails='linear', tail_bound=5.0, distribution=None, **kwargs)

   Bases: :py:obj:`nessai.flows.base.NFlow`


   
   Implementation of Neural Spline Flow

   See: https://arxiv.org/abs/1906.04032

   :Parameters:

       **features** : int
           Number of features (dimensions) in the data space

       **hidden_features** : int
           Number of neurons per layer in each neural network

       **num_layers** : int
           Number of coupling transformations

       **num_blocks_per_layer** : int
           Number of layers (or blocks for resnet) per neural network for
           each coupling transform

       **num_bins** : int, optional (8)
           Number of bins to use for each spline

       **context_features** : int, optional
           Number of context (conditional) parameters.

       **activation** : function
           Activation function implemented in torch

       **dropout_probability** : float, optional (0.0)
           Dropout probability used in each layer of the neural network

       **batch_norm_within_layers** : bool, optional (False)
           Enable or disable batch norm within the neural network for each coupling
           transform

       **batch_norm_between_layers** : bool, optional (False)
           Enable or disable batch norm between coupling transforms

       **linear_transform** : {'permutation', 'lu', 'svd'}
           Linear transform to use between coupling layers. Not recommended when
           using a custom mask.

       **distribution** : :obj: `glasflow.nflows.distributions.Distribution`
           Distribution for the latent space.

       **kwargs** : dict
           Additional kwargs parsed to the spline constructor, e.g. `tails` or
           `tail_bound`. See nflows for details














   ..
       !! processed by numpydoc !!