timesead.models.common.gan

Classes

GAN

Base class for all neural network modules.

GANDiscriminatorLoss

Base class for all neural network modules.

GANGeneratorLoss

Base class for all neural network modules.

GANGeneratorLossMod

Base class for all neural network modules.

WassersteinDiscriminatorLoss

Base class for all neural network modules.

WassersteinGeneratorLoss

Base class for all neural network modules.

Functions

random_weighted_average(→ torch.Tensor)

Module Contents

class timesead.models.common.gan.GAN(generator: torch.nn.Module, discriminator: torch.nn.Module)

Bases: 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 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:

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

generator
discriminator
forward(inputs: Tuple[torch.Tensor, Ellipsis]) → Tuple[torch.Tensor, Ellipsis]
Parameters:

inputs (Tuple[torch.Tensor, Ellipsis])

Return type:

Tuple[torch.Tensor, Ellipsis]

class timesead.models.common.gan.GANDiscriminatorLoss

Bases: timesead.optim.loss.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.

This is the original GAN loss, i.e., - E[log(D(x))] - E[log(1 - D(G(z)))]

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

torch.Tensor

class timesead.models.common.gan.GANGeneratorLoss

Bases: timesead.optim.loss.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.

This is the original GAN loss, i.e., E[log(1 - D(G(z)))]

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

torch.Tensor

class timesead.models.common.gan.GANGeneratorLossMod

Bases: timesead.optim.loss.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.

This is a modified version of original GAN loss, i.e., -E[log(D(G(z)))]

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

torch.Tensor

timesead.models.common.gan.random_weighted_average(input1: torch.Tensor, input2: torch.Tensor) → torch.Tensor
Parameters:
Return type:

torch.Tensor

class timesead.models.common.gan.WassersteinDiscriminatorLoss(gan: GAN = None, gradient_penalty: float = 10)

Bases: timesead.optim.loss.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:

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

gradient_penalty_coeff = 10
gan = None
static gradient_penalty(discriminator, real_input: torch.Tensor, fake_input: torch.Tensor) → torch.Tensor
Parameters:
Return type:

torch.Tensor

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

torch.Tensor

class timesead.models.common.gan.WassersteinGeneratorLoss

Bases: timesead.optim.loss.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.

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

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

torch.Tensor