`mmagic.models.editors.deblurganv2.deblurganv2_discriminator`¶

Module Contents¶

Classes¶

`NLayerDiscriminator`	Defines the PatchGAN discriminator with the specified arguments.
`DicsriminatorTail`	Base class for all neural network modules.
`MultiScaleDiscriminator`	Defines the MultiScale PatchGAN discriminator with the specified
`DoubleGan`	Get a discriminator with a patch gan and a full gan.
`PatchGan`	A patch gan discriminator with the specified arguments.
`MultiScale`	A multiscale patch gan discriminator with the specified arguments.
`DeblurGanV2Discriminator`	Defines the discriminator for DeblurGanv2 with the specified arguments..

Functions¶

get_fullD(norm_layer)

Get a full gan discriminator.

Attributes¶

backbone_list

mmagic.models.editors.deblurganv2.deblurganv2_discriminator.backbone_list = ['DoubleGan', 'MultiScale', 'NoGan', 'PatchGan'][source]¶

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.NLayerDiscriminator(input_nc=3, ndf=64, n_layers=3, norm_layer=nn.BatchNorm2d, use_sigmoid=False, use_parallel=True)[source]¶

Bases: torch.nn.Module

Defines the PatchGAN discriminator with the specified arguments.

forward(input)[source]¶

Forward function.

Parameters: input (torch.Tensor) – You can directly input a torch.Tensor.
Returns: torch.tensor will be returned.
Return type: torch.Tensor

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.DicsriminatorTail(nf_mult, n_layers, ndf=64, norm_layer=nn.BatchNorm2d, use_parallel=True)[source]¶

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 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 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.

forward(input)[source]¶

Forward function.

Parameters: input (torch.Tensor) – You can directly input a torch.Tensor.
Returns: torch.tensor will be returned.
Return type: torch.Tensor

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.MultiScaleDiscriminator(input_nc=3, ndf=64, norm_layer=nn.BatchNorm2d, use_parallel=True)[source]¶

Bases: torch.nn.Module

Defines the MultiScale PatchGAN discriminator with the specified arguments.

forward(input)[source]¶

Forward function.

Parameters: input (torch.Tensor) – You can directly input a torch.Tensor.
Returns: torch.tensor will be returned.
Return type: torch.Tensor

mmagic.models.editors.deblurganv2.deblurganv2_discriminator.get_fullD(norm_layer)[source]¶

Get a full gan discriminator.

Parameters: norm_layer (Str) – norm type

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.DoubleGan(norm_layer='instance', d_layers=3)[source]¶

Bases: torch.nn.Module

Get a discriminator with a patch gan and a full gan.

forward(x)[source]¶

Forward function.

Parameters: x (torch.Tensor) – You can directly input a torch.Tensor.
Returns: List(torch.tensor) will be returned.
Return type: List(torch.Tensor)

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.PatchGan(norm_layer='instance', d_layers=3)[source]¶

Bases: torch.nn.Module

A patch gan discriminator with the specified arguments.

forward(x)[source]¶

Forward function.

Parameters: x (torch.Tensor) – You can directly input a torch.Tensor.
Returns: torch.tensor will be returned.
Return type: torch.Tensor

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.MultiScale(norm_layer='instance', d_layers=3)[source]¶

Bases: torch.nn.Module

A multiscale patch gan discriminator with the specified arguments.

forward(x)[source]¶

Forward function.

Parameters: x (torch.Tensor) – You can directly input a torch.Tensor.
Returns: torch.tensor will be returned.
Return type: torch.Tensor

class mmagic.models.editors.deblurganv2.deblurganv2_discriminator.DeblurGanV2Discriminator[source]¶

Defines the discriminator for DeblurGanv2 with the specified arguments..

Parameters: model (Str) – Type of the discriminator model

mmagic.models.editors.deblurganv2.deblurganv2_discriminator¶

Module Contents¶

Classes¶

Functions¶

Attributes¶

`mmagic.models.editors.deblurganv2.deblurganv2_discriminator`¶