nessai.flows.realnvp
====================

.. py:module:: nessai.flows.realnvp

.. autoapi-nested-parse::

   Implementation of Real Non Volume Preserving flows.

   ..
       !! processed by numpydoc !!


Classes
-------

.. autoapisummary::

   nessai.flows.realnvp.RealNVP


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

.. py:class:: RealNVP(features, hidden_features, num_layers, num_blocks_per_layer, mask=None, context_features=None, net='resnet', use_volume_preserving=False, activation=F.relu, dropout_probability=0.0, batch_norm_within_layers=False, batch_norm_between_layers=True, linear_transform='lu', pre_transform=None, pre_transform_kwargs=None, actnorm=False, distribution=None, **kwargs)

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


   
   Implementation of RealNVP.

   This class modifies ``SimpleRealNVP`` from nflows to allows for a custom
   mask to be parsed as a numpy array and allows for MLP to be used
   instead of a ResNet

   > L. Dinh et al., Density estimation using Real NVP, ICLR 2017.

   :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

       **mask** : array_like, optional
           Custom mask to use between coupling transforms. Can either be
           a single array with the same length as the number of features or
           and two-dimensional array of shape (# features, # num_layers).
           Must use -1 and 1 to indicate no updated and updated.

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

       **net** : {'resnet', 'mlp'}
           Type of neural network to use

       **use_volume_preserving** : bool, optional (False)
           Use volume preserving flows which use only addition and no scaling

       **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', None}
           Linear transform to use between coupling layers. Not recommended when
           using a custom mask.

       **pre_transform** : str
           Linear transform to use before the first transform.

       **pre_transform_kwargs** : dict
           Keyword arguments to pass to the transform class used for the pre-
           transform.

       **actnorm** : bool
           Include activation normalisation as described in arXiv:1807.03039.
           Batch norm between layers must be disabled if using this option.

       **kwargs**
           Keyword arguments are passed to the coupling class.














   ..
       !! processed by numpydoc !!