Skip to content

bob.learn.pytorch
bob.learn.pytorch
Commit e4a7d224 authored by Tiago de Freitas Pereira's avatar Tiago de Freitas Pereira
Browse files
Options

[black]

parent c83fd608
Pipeline #46610 passed with stage
    in 14 minutes and 1 second
    Expand all Hide whitespace changes
    Inline Side-by-side
    Showing with 3549 additions and 2745 deletions
    bob/__init__.py
    View file @ e4a7d224
    # see https://docs.python.org/3/library/pkgutil.html
    from pkgutil import extend_path
    __path__ = extend_path(__path__, __name__)
    bob/learn/__init__.py
    View file @ e4a7d224
    # see https://docs.python.org/3/library/pkgutil.html
    from pkgutil import extend_path
    __path__ = extend_path(__path__, __name__)
    bob/learn/pytorch/__init__.py
    View file @ e4a7d224
    # gets sphinx autodoc done right - don't remove it
    def __appropriate__(*args):
    """Says object was actually declared here, an not on the import module.
    """Says object was actually declared here, an not on the import module.
    Parameters:
    ......@@ -11,8 +10,10 @@ def __appropriate__(*args):
    <https://github.com/sphinx-doc/sphinx/issues/3048>`
    """
    for obj in args: obj.__module__ = __name__
    for obj in args:
    obj.__module__ = __name__
    __appropriate__()
    __all__ = [_ for _ in dir() if not _.startswith('_')]
    __all__ = [_ for _ in dir() if not _.startswith("_")]
    bob/learn/pytorch/architectures/CASIANet.py
    View file @ e4a7d224
    import torch
    from .utils import make_conv_layers
    CASIA_CONFIG = [32, 64, 'M', 64, 128, 'M', 96, 192, 'M', 128, 256, 'M', 160, 320]
    CASIA_CONFIG = [32, 64, "M", 64, 128, "M", 96, 192, "M", 128, 256, "M", 160, 320]
    class CASIANet(torch.nn.Module):
    """ The class defining the CASIA-Net CNN model.
    """ The class defining the CASIA-Net CNN model.
    This class implements the CNN described in:
    "Learning Face Representation From Scratch", D. Yi, Z. Lei, S. Liao and S.z. Li, 2014
    ......@@ -22,10 +23,10 @@ class CASIANet(torch.nn.Module):
    classifier: :py:class:`torch.nn.Module`
    The output of the last linear (logits)
    """
    """
    def __init__(self, num_cls, drop_rate=0.5):
    """ Init method
    def __init__(self, num_cls, drop_rate=0.5):
    """ Init method
    Parameters
    ----------
    ......@@ -35,16 +36,16 @@ class CASIANet(torch.nn.Module):
    The probability for dropout.
    """
    super(CASIANet, self).__init__()
    self.num_classes = num_cls
    self.drop_rate = float(drop_rate)
    self.conv = make_conv_layers(CASIA_CONFIG)
    self.avgpool = torch.nn.AvgPool2d(8)
    self.classifier = torch.nn.Linear(320, self.num_classes)
    def forward(self, x):
    """ Propagate data through the network
    super(CASIANet, self).__init__()
    self.num_classes = num_cls
    self.drop_rate = float(drop_rate)
    self.conv = make_conv_layers(CASIA_CONFIG)
    self.avgpool = torch.nn.AvgPool2d(8)
    self.classifier = torch.nn.Linear(320, self.num_classes)
    def forward(self, x):
    """ Propagate data through the network
    Parameters
    ----------
    ......@@ -58,9 +59,9 @@ class CASIANet(torch.nn.Module):
    """
    x = self.conv(x)
    x = self.avgpool(x)
    x = x.view(x.size(0), -1)
    x = torch.nn.functional.dropout(x, p = self.drop_rate, training=self.training)
    out = self.classifier(x)
    return out, x # x for feature
    x = self.conv(x)
    x = self.avgpool(x)
    x = x.view(x.size(0), -1)
    x = torch.nn.functional.dropout(x, p=self.drop_rate, training=self.training)
    out = self.classifier(x)
    return out, x # x for feature
    bob/learn/pytorch/architectures/CNN8.py
    View file @ e4a7d224
    ......@@ -8,10 +8,11 @@ import torch.nn.functional as F
    from .utils import make_conv_layers
    CNN8_CONFIG = [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M']
    CNN8_CONFIG = [64, 64, "M", 128, 128, "M", 256, 256, "M", 512, 512, "M"]
    class CNN8(nn.Module):
    """ The class defining the CNN8 model.
    """ The class defining the CNN8 model.
    Attributes
    ----------
    ......@@ -26,10 +27,10 @@ class CNN8(nn.Module):
    classifier: :py:class:`torch.nn.Module`
    The output of the last linear (logits)
    """
    """
    def __init__(self, num_cls, drop_rate=0.5):
    """ Init method
    def __init__(self, num_cls, drop_rate=0.5):
    """ Init method
    Parameters
    ----------
    ......@@ -39,16 +40,16 @@ class CNN8(nn.Module):
    The probability for dropout.
    """
    super(CNN8, self).__init__()
    self.num_classes = num_cls
    self.drop_rate = float(drop_rate)
    self.conv = make_conv_layers(CNN8_CONFIG)
    self.avgpool = nn.AvgPool2d(8)
    self.classifier = nn.Linear(512, self.num_classes)
    def forward(self, x):
    """ Propagate data through the network
    super(CNN8, self).__init__()
    self.num_classes = num_cls
    self.drop_rate = float(drop_rate)
    self.conv = make_conv_layers(CNN8_CONFIG)
    self.avgpool = nn.AvgPool2d(8)
    self.classifier = nn.Linear(512, self.num_classes)
    def forward(self, x):
    """ Propagate data through the network
    Parameters
    ----------
    ......@@ -62,10 +63,9 @@ class CNN8(nn.Module):
    """
    x = self.conv(x)
    x = self.avgpool(x)
    x = x.view(x.size(0), -1)
    x = F.dropout(x, p = self.drop_rate, training=self.training)
    out = self.classifier(x)
    return out, x # x for feature
    x = self.conv(x)
    x = self.avgpool(x)
    x = x.view(x.size(0), -1)
    x = F.dropout(x, p=self.drop_rate, training=self.training)
    out = self.classifier(x)
    return out, x # x for feature
    bob/learn/pytorch/architectures/ConditionalGAN.py
    View file @ e4a7d224
    ......@@ -4,8 +4,9 @@
    import torch
    import torch.nn as nn
    class ConditionalGAN_generator(nn.Module):
    """ Class implementating the conditional GAN generator
    """ Class implementating the conditional GAN generator
    This network is introduced in the following publication:
    Mehdi Mirza, Simon Osindero: "Conditional Generative Adversarial Nets"
    ......@@ -18,8 +19,9 @@ class ConditionalGAN_generator(nn.Module):
    The sequential container
    """
    def __init__(self, noise_dim, conditional_dim, channels=3, ngpu=1):
    """Init function
    def __init__(self, noise_dim, conditional_dim, channels=3, ngpu=1):
    """Init function
    Parameters
    ----------
    ......@@ -33,38 +35,40 @@ class ConditionalGAN_generator(nn.Module):
    The number of available GPU devices
    """
    super(ConditionalGAN_generator, self).__init__()
    self.ngpu = ngpu
    self.conditional_dim = conditional_dim
    # output dimension
    ngf = 64
    self.main = nn.Sequential(
    # input is Z, going into a convolution
    nn.ConvTranspose2d((noise_dim + conditional_dim), ngf * 8, 4, 1, 0, bias=False),
    nn.BatchNorm2d(ngf * 8),
    nn.ReLU(True),
    # state size. (ngf*8) x 4 x 4
    nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 4),
    nn.ReLU(True),
    # state size. (ngf*4) x 8 x 8
    nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 2),
    nn.ReLU(True),
    # state size. (ngf*2) x 16 x 16
    nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf),
    nn.ReLU(True),
    # state size. (ngf) x 32 x 32
    nn.ConvTranspose2d(ngf, channels, 4, 2, 1, bias=False),
    nn.Tanh()
    # state size. (nc) x 64 x 64
    )
    def forward(self, z, y):
    """Forward function
    super(ConditionalGAN_generator, self).__init__()
    self.ngpu = ngpu
    self.conditional_dim = conditional_dim
    # output dimension
    ngf = 64
    self.main = nn.Sequential(
    # input is Z, going into a convolution
    nn.ConvTranspose2d(
    (noise_dim + conditional_dim), ngf * 8, 4, 1, 0, bias=False
    ),
    nn.BatchNorm2d(ngf * 8),
    nn.ReLU(True),
    # state size. (ngf*8) x 4 x 4
    nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 4),
    nn.ReLU(True),
    # state size. (ngf*4) x 8 x 8
    nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 2),
    nn.ReLU(True),
    # state size. (ngf*2) x 16 x 16
    nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf),
    nn.ReLU(True),
    # state size. (ngf) x 32 x 32
    nn.ConvTranspose2d(ngf, channels, 4, 2, 1, bias=False),
    nn.Tanh()
    # state size. (nc) x 64 x 64
    )
    def forward(self, z, y):
    """Forward function
    Parameters
    ----------
    ......@@ -79,19 +83,19 @@ class ConditionalGAN_generator(nn.Module):
    the output of the generator (i.e. an image)
    """
    generator_input = torch.cat((z, y), 1)
    #if isinstance(generator_input.data, torch.cuda.FloatTensor) and self.ngpu > 1:
    # output = nn.parallel.data_parallel(self.main, generator_input, range(self.ngpu))
    #else:
    # output = self.main(generator_input)
    # let's assume that we will never face the case where more than a GPU is used ...
    output = self.main(generator_input)
    return output
    generator_input = torch.cat((z, y), 1)
    # if isinstance(generator_input.data, torch.cuda.FloatTensor) and self.ngpu > 1:
    # output = nn.parallel.data_parallel(self.main, generator_input, range(self.ngpu))
    # else:
    # output = self.main(generator_input)
    # let's assume that we will never face the case where more than a GPU is used ...
    output = self.main(generator_input)
    return output
    class ConditionalGAN_discriminator(nn.Module):
    """ Class implementating the conditional GAN discriminator
    """ Class implementating the conditional GAN discriminator
    Attributes
    ----------
    ......@@ -104,9 +108,10 @@ class ConditionalGAN_discriminator(nn.Module):
    main : :py:class:`torch.nn.Sequential`
    The sequential container
    """
    def __init__(self, conditional_dim, channels=3, ngpu=1):
    """Init function
    """
    def __init__(self, conditional_dim, channels=3, ngpu=1):
    """Init function
    Parameters
    ----------
    ......@@ -118,36 +123,35 @@ class ConditionalGAN_discriminator(nn.Module):
    The number of available GPU devices
    """
    super(ConditionalGAN_discriminator, self).__init__()
    self.conditional_dim = conditional_dim
    self.ngpu = ngpu
    # input dimension
    ndf = 64
    self.main = nn.Sequential(
    # input is (nc) x 64 x 64
    nn.Conv2d((channels + conditional_dim), ndf, 4, 2, 1, bias=False),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf) x 32 x 32
    nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 2),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*2) x 16 x 16
    nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 4),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*4) x 8 x 8
    nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 8),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*8) x 4 x 4
    nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
    nn.Sigmoid()
    )
    def forward(self, images, y):
    """Forward function
    super(ConditionalGAN_discriminator, self).__init__()
    self.conditional_dim = conditional_dim
    self.ngpu = ngpu
    # input dimension
    ndf = 64
    self.main = nn.Sequential(
    # input is (nc) x 64 x 64
    nn.Conv2d((channels + conditional_dim), ndf, 4, 2, 1, bias=False),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf) x 32 x 32
    nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 2),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*2) x 16 x 16
    nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 4),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*4) x 8 x 8
    nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 8),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*8) x 4 x 4
    nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
    nn.Sigmoid(),
    )
    def forward(self, images, y):
    """Forward function
    Parameters
    ----------
    ......@@ -161,12 +165,12 @@ class ConditionalGAN_discriminator(nn.Module):
    :py:class:`torch.Tensor`
    the output of the discriminator
    """
    input_discriminator = torch.cat((images, y), 1)
    #if isinstance(input_discriminator.data, torch.cuda.FloatTensor) and self.ngpu > 1:
    # output = nn.parallel.data_parallel(self.main, input_discriminator, range(self.ngpu))
    #else:
    # output = self.main(input_discriminator)
    # let's assume that we will never face the case where more than a GPU is used ...
    output = self.main(input_discriminator)
    return output.view(-1, 1).squeeze(1)
    input_discriminator = torch.cat((images, y), 1)
    # if isinstance(input_discriminator.data, torch.cuda.FloatTensor) and self.ngpu > 1:
    # output = nn.parallel.data_parallel(self.main, input_discriminator, range(self.ngpu))
    # else:
    # output = self.main(input_discriminator)
    # let's assume that we will never face the case where more than a GPU is used ...
    output = self.main(input_discriminator)
    return output.view(-1, 1).squeeze(1)
    bob/learn/pytorch/architectures/ConvAutoencoder.py
    View file @ e4a7d224
    ......@@ -3,8 +3,9 @@
    from torch import nn
    class ConvAutoencoder(nn.Module):
    """
    """
    A class defining a simple convolutional autoencoder.
    Attributes
    ......@@ -13,8 +14,9 @@ class ConvAutoencoder(nn.Module):
    returns the encoder output if true, the reconstructed image otherwise.
    """
    def __init__(self, return_latent_embedding=False):
    """
    def __init__(self, return_latent_embedding=False):
    """
    Init function
    Parameters
    ......@@ -22,36 +24,40 @@ class ConvAutoencoder(nn.Module):
    return_latent_embedding : bool
    returns the encoder output if true, the reconstructed image otherwise.
    """
    super(ConvAutoencoder, self).__init__()
    self.return_latent_embedding = return_latent_embedding
    self.encoder = nn.Sequential(nn.Conv2d(3, 16, 5, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    nn.Conv2d(16, 16, 5, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    nn.Conv2d(16, 16, 3, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    nn.Conv2d(16, 16, 3, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2))
    super(ConvAutoencoder, self).__init__()
    self.return_latent_embedding = return_latent_embedding
    self.encoder = nn.Sequential(
    nn.Conv2d(3, 16, 5, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    nn.Conv2d(16, 16, 5, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    nn.Conv2d(16, 16, 3, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    nn.Conv2d(16, 16, 3, padding=2),
    nn.ReLU(True),
    nn.MaxPool2d(2),
    )
    self.decoder = nn.Sequential(nn.ConvTranspose2d(16, 16, 3, stride=2, padding=1),
    nn.ReLU(True),
    nn.ConvTranspose2d(16, 16, 3, stride=2, padding=1),
    nn.ReLU(True),
    nn.ConvTranspose2d(16, 16, 5, stride=2, padding=2),
    nn.ReLU(True),
    nn.ConvTranspose2d(16, 3, 5, stride=2, padding=2),
    nn.ReLU(True),
    nn.ConvTranspose2d(3, 3, 2, stride=1, padding=1),
    nn.Tanh())
    self.decoder = nn.Sequential(
    nn.ConvTranspose2d(16, 16, 3, stride=2, padding=1),
    nn.ReLU(True),
    nn.ConvTranspose2d(16, 16, 3, stride=2, padding=1),
    nn.ReLU(True),
    nn.ConvTranspose2d(16, 16, 5, stride=2, padding=2),
    nn.ReLU(True),
    nn.ConvTranspose2d(16, 3, 5, stride=2, padding=2),
    nn.ReLU(True),
    nn.ConvTranspose2d(3, 3, 2, stride=1, padding=1),
    nn.Tanh(),
    )
    def forward(self, x):
    """ Propagate data through the network
    def forward(self, x):
    """ Propagate data through the network
    Parameters
    ----------
    ......@@ -64,8 +70,8 @@ class ConvAutoencoder(nn.Module):
    either the encoder output or the reconstructed image
    """
    x = self.encoder(x)
    if self.return_latent_embedding:
    return x
    x = self.decoder(x)
    return x
    x = self.encoder(x)
    if self.return_latent_embedding:
    return x
    x = self.decoder(x)
    return x
    bob/learn/pytorch/architectures/DCGAN.py
    View file @ e4a7d224
    <
    ......@@ -6,7 +6,7 @@ import torch.nn as nn
    class DCGAN_generator(nn.Module):
    """ Class implementating the generator part of the Deeply Convolutional GAN
    """ Class implementating the generator part of the Deeply Convolutional GAN
    This network is introduced in the following publication:
    Alec Radford, Luke Metz, Soumith Chintala: "Unsupervised Representation
    ......@@ -21,8 +21,9 @@ class DCGAN_generator(nn.Module):
    The number of available GPU devices
    """
    def __init__(self, ngpu):
    """Init function
    def __init__(self, ngpu):
    """Init function
    Parameters
    ----------
    ......@@ -30,39 +31,39 @@ class DCGAN_generator(nn.Module):
    The number of available GPU devices
    """
    super(DCGAN_generator, self).__init__()
    self.ngpu = ngpu
    # just to test - will soon be args
    nz = 100 # noise dimension
    ngf = 64 # number of features map on the first layer
    nc = 3 # number of channels
    self.main = nn.Sequential(
    # input is Z, going into a convolution
    nn.ConvTranspose2d( nz, ngf * 8, 4, 1, 0, bias=False),
    nn.BatchNorm2d(ngf * 8),
    nn.ReLU(True),
    # state size. (ngf*8) x 4 x 4
    nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 4),
    nn.ReLU(True),
    # state size. (ngf*4) x 8 x 8
    nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 2),
    nn.ReLU(True),
    # state size. (ngf*2) x 16 x 16
    nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf),
    nn.ReLU(True),
    # state size. (ngf) x 32 x 32
    nn.ConvTranspose2d( ngf, nc, 4, 2, 1, bias=False),
    nn.Tanh()
    # state size. (nc) x 64 x 64
    )
    def forward(self, input):
    """Forward function
    super(DCGAN_generator, self).__init__()
    self.ngpu = ngpu
    # just to test - will soon be args
    nz = 100 # noise dimension
    ngf = 64 # number of features map on the first layer
    nc = 3 # number of channels
    self.main = nn.Sequential(
    # input is Z, going into a convolution
    nn.ConvTranspose2d(nz, ngf * 8, 4, 1, 0, bias=False),
    nn.BatchNorm2d(ngf * 8),
    nn.ReLU(True),
    # state size. (ngf*8) x 4 x 4
    nn.ConvTranspose2d(ngf * 8, ngf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 4),
    nn.ReLU(True),
    # state size. (ngf*4) x 8 x 8
    nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf * 2),
    nn.ReLU(True),
    # state size. (ngf*2) x 16 x 16
    nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ngf),
    nn.ReLU(True),
    # state size. (ngf) x 32 x 32
    nn.ConvTranspose2d(ngf, nc, 4, 2, 1, bias=False),
    nn.Tanh()
    # state size. (nc) x 64 x 64
    )
    def forward(self, input):
    """Forward function
    Parameters
    ----------
    ......@@ -74,18 +75,18 @@ class DCGAN_generator(nn.Module):
    the output of the generator (i.e. an image)
    """
    #if isinstance(input.data, torch.cuda.FloatTensor) and self.ngpu > 1:
    # output = nn.parallel.data_parallel(self.main, input, range(self.ngpu))
    #else:
    # output = self.main(input)
    # let's assume that we will never face the case where more than a GPU is used ...
    output = self.main(input)
    return output
    # if isinstance(input.data, torch.cuda.FloatTensor) and self.ngpu > 1:
    # output = nn.parallel.data_parallel(self.main, input, range(self.ngpu))
    # else:
    # output = self.main(input)
    # let's assume that we will never face the case where more than a GPU is used ...
    output = self.main(input)
    return output
    class DCGAN_discriminator(nn.Module):
    """ Class implementating the discriminator part of the Deeply Convolutional GAN
    """ Class implementating the discriminator part of the Deeply Convolutional GAN
    This network is introduced in the following publication:
    Alec Radford, Luke Metz, Soumith Chintala: "Unsupervised Representation
    ......@@ -100,8 +101,9 @@ class DCGAN_discriminator(nn.Module):
    The number of available GPU devices
    """
    def __init__(self, ngpu):
    """Init function
    def __init__(self, ngpu):
    """Init function
    Parameters
    ----------
    ......@@ -109,37 +111,36 @@ class DCGAN_discriminator(nn.Module):
    The number of available GPU devices
    """
    super(DCGAN_discriminator, self).__init__()
    self.ngpu = ngpu
    # just to test - will soon be args
    ndf = 64
    nc = 3
    self.main = nn.Sequential(
    # input is (nc) x 64 x 64
    nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf) x 32 x 32
    nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 2),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*2) x 16 x 16
    nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 4),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*4) x 8 x 8
    nn.Conv2d(ndf * 4, ndf * 8, 4, 2, 1, bias=False),
    nn.BatchNorm2d(ndf * 8),
    nn.LeakyReLU(0.2, inplace=True),
    # state size. (ndf*8) x 4 x 4
    nn.Conv2d(ndf * 8, 1, 4, 1, 0, bias=False),
    nn.Sigmoid()
    )
    def forward(self, input):
    """Forward function