layers

Fill in a module description here

EncoderRNN

 EncoderRNN (d_z:int, enc_hidden_size:int, use_recurrent_dropout=False,
             r_dropout_prob=0.0, use_layer_norm=False,
             layer_norm_learnable=False, lstm_impl='builtin')

Encoder module

This consists of a bidirectional LSTM

source

BivariateGaussianMixture

 BivariateGaussianMixture (pi_logits:torch.Tensor, mu_x:torch.Tensor,
                           mu_y:torch.Tensor, sigma_x:torch.Tensor,
                           sigma_y:torch.Tensor, rho_xy:torch.Tensor)

Bi-variate Gaussian mixture

The mixture is represented by \(\Pi\) and \(\mathcal{N}(\mu_{x}, \mu_{y}, \sigma_{x}, \sigma_{y}, ho_{xy})\). This class adjusts temperatures and creates the categorical and Gaussian distributions from the parameters.

source

DecoderRNN

 DecoderRNN (d_z:int, dec_hidden_size:int, n_distributions:int,
             use_recurrent_dropout=False, r_dropout_prob=0.0,
             use_layer_norm=False, layer_norm_learnable=False,
             lstm_impl='builtin')

Base class for all neural network modules.

Your models should also subclass this class.

Modules can also contain other Modules, allowing to nest them in a tree structure. You can assign the submodules as regular attributes::

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        return F.relu(self.conv2(x))

Submodules assigned in this way will be registered, and will have their parameters converted too when you call :meth:to, etc.

.. note:: As per the example above, an __init__() call to the parent class must be made before assignment on the child.

:ivar training: Boolean represents whether this module is in training or evaluation mode. :vartype training: bool

source

ReconstructionLoss

 ReconstructionLoss (*args, **kwargs)

Reconstruction Loss

source

KLDivLoss

 KLDivLoss (*args, **kwargs)

This calculates the KL divergence between a given normal distribution and \(\mathcal{N}(0, 1)\)