"""
Implementation of WGAN-GP for image size 32.
"""
import torch
import torch.nn as nn
from torch_mimicry.nets.wgan_gp import wgan_gp_base
from torch_mimicry.nets.wgan_gp.wgan_gp_resblocks import DBlockOptimized, DBlock, GBlock
[docs]class WGANGPGenerator32(wgan_gp_base.WGANGPBaseGenerator):
r"""
ResNet backbone generator for WGAN-GP.
Attributes:
nz (int): Noise dimension for upsampling.
ngf (int): Variable controlling generator feature map sizes.
bottom_width (int): Starting width for upsampling generator output to an image.
loss_type (str): Name of loss to use for GAN loss.
"""
def __init__(self, nz=128, ngf=256, bottom_width=4, **kwargs):
super().__init__(nz=nz, ngf=ngf, bottom_width=bottom_width, **kwargs)
# Build the layers
self.l1 = nn.Linear(self.nz, (self.bottom_width**2) * self.ngf)
self.block2 = GBlock(self.ngf, self.ngf, upsample=True)
self.block3 = GBlock(self.ngf, self.ngf, upsample=True)
self.block4 = GBlock(self.ngf, self.ngf, upsample=True)
self.b5 = nn.BatchNorm2d(self.ngf)
self.c5 = nn.Conv2d(self.ngf, 3, 3, 1, padding=1)
self.activation = nn.ReLU(True)
# Initialise the weights
nn.init.xavier_uniform_(self.l1.weight.data, 1.0)
[docs] def forward(self, x):
r"""
Feedforwards a batch of noise vectors into a batch of fake images.
Args:
x (Tensor): A batch of noise vectors of shape (N, nz).
Returns:
Tensor: A batch of fake images of shape (N, C, H, W).
"""
h = self.l1(x)
h = h.view(x.shape[0], -1, self.bottom_width, self.bottom_width)
h = self.block2(h)
h = self.block3(h)
h = self.block4(h)
h = self.b5(h)
h = self.activation(h)
h = torch.tanh(self.c5(h))
return h
[docs]class WGANGPDiscriminator32(wgan_gp_base.WGANGPBaseDiscriminator):
r"""
ResNet backbone discriminator for WGAN-GP.
Attributes:
ndf (int): Variable controlling discriminator feature map sizes.
loss_type (str): Name of loss to use for GAN loss.
gp_scale (float): Lamda parameter for gradient penalty.
"""
def __init__(self, ndf=128, **kwargs):
super().__init__(ndf=ndf, **kwargs)
# Build layers
self.block1 = DBlockOptimized(3, self.ndf)
self.block2 = DBlock(self.ndf, self.ndf, downsample=True)
self.block3 = DBlock(self.ndf, self.ndf, downsample=False)
self.block4 = DBlock(self.ndf, self.ndf, downsample=False)
self.l5 = nn.Linear(self.ndf, 1)
self.activation = nn.ReLU(True)
# Initialise the weights
nn.init.xavier_uniform_(self.l5.weight.data, 1.0)
[docs] def forward(self, x):
r"""
Feedforwards a batch of real/fake images and produces a batch of GAN logits.
Args:
x (Tensor): A batch of images of shape (N, C, H, W).
Returns:
Tensor: A batch of GAN logits of shape (N, 1).
"""
h = x
h = self.block1(h)
h = self.block2(h)
h = self.block3(h)
h = self.block4(h)
h = self.activation(h)
# Global average pooling
h = torch.mean(h, dim=(2, 3)) # WGAN uses mean pooling
output = self.l5(h)
return output