timesead.models.generative.tadgan
=================================

.. py:module:: timesead.models.generative.tadgan


Classes
-------

.. autoapisummary::

   timesead.models.generative.tadgan.TADGANEncoder
   timesead.models.generative.tadgan.TADGANGenerator
   timesead.models.generative.tadgan.TADGANDiscriminatorX
   timesead.models.generative.tadgan.TADGANDiscriminatorZ
   timesead.models.generative.tadgan.TADGAN
   timesead.models.generative.tadgan.TADGANGeneratorLoss
   timesead.models.generative.tadgan.TADGANTrainer
   timesead.models.generative.tadgan.TADGANAnomalyDetector


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

.. py:class:: TADGANEncoder(input_size: int, window_size: int, lstm_hidden_size: int = 100, latent_size: int = 20)

   Bases: :py:obj:`torch.nn.Module`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing them to be nested 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) -> None:
               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 also have their
   parameters converted 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

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: lstm


   .. py:attribute:: linear


   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor


.. py:class:: TADGANGenerator(window_size: int, output_size: int, latent_size: int = 20, lstm_hidden_size: int = 64, dropout: float = 0.2)

   Bases: :py:obj:`torch.nn.Module`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing them to be nested 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) -> None:
               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 also have their
   parameters converted 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

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: linear1


   .. py:attribute:: lstm1


   .. py:attribute:: upsample


   .. py:attribute:: lstm2


   .. py:attribute:: linear2


   .. py:attribute:: final_activation


   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor


.. py:class:: TADGANDiscriminatorX(input_size: int, window_size: int, conv_filters: int = 64, conv_kernel_size: int = 5, dropout: float = 0.25)

   Bases: :py:obj:`torch.nn.Module`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing them to be nested 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) -> None:
               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 also have their
   parameters converted 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

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: conv1


   .. py:attribute:: conv2


   .. py:attribute:: conv3


   .. py:attribute:: conv4


   .. py:attribute:: dropout


   .. py:attribute:: leakyrelu


   .. py:attribute:: classification


   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor


.. py:class:: TADGANDiscriminatorZ(latent_size: int, hidden_size: int = 20, dropout: float = 0.2)

   Bases: :py:obj:`torch.nn.Module`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing them to be nested 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) -> None:
               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 also have their
   parameters converted 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

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: linear1


   .. py:attribute:: linear2


   .. py:attribute:: dropout


   .. py:attribute:: leakyrelu


   .. py:attribute:: classification


   .. py:method:: forward(x: torch.Tensor) -> torch.Tensor


.. py:class:: TADGAN(input_size: int, window_size: int, latent_size: int = 20, enc_lstm_hidden_size: int = 100, gen_lstm_hidden_size: int = 64, disc_conv_filters: int = 64, disc_conv_kernel_size: int = 5, disc_z_hidden_size: int = 20, gen_dropout: float = 0.2, disc_dropout: float = 0.25, disc_z_dropout: float = 0.2)

   Bases: :py:obj:`timesead.models.BaseModel`


   Base class for all neural network modules.

   Your models should also subclass this class.

   Modules can also contain other Modules, allowing them to be nested 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) -> None:
               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 also have their
   parameters converted 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

   Initialize internal Module state, shared by both nn.Module and ScriptModule.


   .. py:attribute:: encoder


   .. py:attribute:: generator


   .. py:attribute:: discriminatorx


   .. py:attribute:: discriminatorz


   .. py:attribute:: gan


   .. py:attribute:: inverse_gan


   .. py:attribute:: latent_size
      :value: 20



   .. py:method:: grouped_parameters() -> Tuple[Iterator[torch.nn.Parameter], Ellipsis]


   .. py:method:: forward(inputs: Tuple[torch.Tensor, Ellipsis]) -> Tuple[torch.Tensor, Ellipsis]


.. py:class:: TADGANGeneratorLoss(reconstruction_coeff: float = 10)

   Bases: :py:obj:`timesead.models.common.WassersteinGeneratorLoss`


   .. py:attribute:: rec_coeff
      :value: 10



   .. py:attribute:: rec_loss


   .. py:method:: forward(predictions: Tuple[torch.Tensor, Ellipsis], targets: Tuple[torch.Tensor, Ellipsis], *args, **kwargs) -> torch.Tensor


.. py:class:: TADGANTrainer(*args, disc_iterations: int = 5, **kwargs)

   Bases: :py:obj:`timesead.optim.trainer.Trainer`


   .. py:attribute:: disc_iterations
      :value: 5



   .. py:method:: validate_batch(network: TADGAN, val_metrics: Dict[str, Callable], b_inputs: Tuple[torch.Tensor, Ellipsis], b_targets: Tuple[torch.Tensor, Ellipsis], *args, **kwargs) -> Dict[str, float]


   .. py:method:: train_batch(network: TADGAN, losses: List[timesead.optim.loss.Loss], optimizers: List[torch.optim.Optimizer], epoch: int, num_epochs: int, b_inputs: Tuple[torch.Tensor, Ellipsis], b_targets: Tuple[torch.Tensor, Ellipsis]) -> List[float]


.. py:class:: TADGANAnomalyDetector(model: TADGAN, alpha: float = 0.5)

   Bases: :py:obj:`timesead.models.common.AnomalyDetector`


   .. py:attribute:: model


   .. py:attribute:: alpha
      :value: 0.5



   .. py:method:: fit(dataset: torch.utils.data.DataLoader) -> None


   .. py:method:: compute_online_anomaly_score(inputs: Tuple[torch.Tensor, Ellipsis]) -> torch.Tensor


   .. py:method:: compute_offline_anomaly_score(inputs: Tuple[torch.Tensor, Ellipsis]) -> torch.Tensor
      :abstractmethod:



   .. py:method:: format_online_targets(targets: Tuple[torch.Tensor, Ellipsis]) -> torch.Tensor