timesead.optim.loss

Abstract class implementing the general interface of a loss.

Classes

Loss

Base class for all neural network modules.

TorchLossWrapper

Base class for all neural network modules.

LogCoshLoss

Base class for all neural network modules.

Module Contents

class timesead.optim.loss.Loss(size_average=None, reduce=None, reduction: str = 'mean')

Bases: torch.nn.modules.loss._Loss, abc.ABC

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 to(), etc.

Note

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

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

reduction (str)

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

abstract forward(predictions: Tuple[torch.Tensor, Ellipsis], targets: Tuple[torch.Tensor, Ellipsis], *args, **kwargs) → torch.Tensor | Tuple[torch.Tensor]
Parameters:
Return type:

Union[torch.Tensor, Tuple[torch.Tensor]]

class timesead.optim.loss.TorchLossWrapper(torch_loss: torch.nn.modules.loss._Loss, size_average=None, reduce=None, reduction: str = 'mean')

Bases: Loss

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 to(), etc.

Note

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

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

  • torch_loss (torch.nn.modules.loss._Loss)

  • reduction (str)

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

torch_loss
forward(predictions: Tuple[torch.Tensor, Ellipsis], targets: Tuple[torch.Tensor, Ellipsis], *args, **kwargs) → torch.Tensor
Parameters:
Return type:

torch.Tensor

class timesead.optim.loss.LogCoshLoss(size_average=None, reduce=None, reduction: str = 'mean')

Bases: Loss

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 to(), etc.

Note

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

Variables:

training (bool) – Boolean represents whether this module is in training or evaluation mode.

Parameters:

reduction (str)

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

logcosh(x: torch.Tensor) → torch.Tensor
Parameters:

x (torch.Tensor)

Return type:

torch.Tensor

forward(predictions: Tuple[torch.Tensor, Ellipsis], targets: Tuple[torch.Tensor, Ellipsis], *args, **kwargs) → torch.Tensor | Tuple[torch.Tensor]
Parameters:
Return type:

Union[torch.Tensor, Tuple[torch.Tensor]]