sketch_models.py

import functools
import torch
import torch.nn as nn


norm_layer = nn.InstanceNorm2d

class ResidualBlock(nn.Module):
    def __init__(self, in_features):
        super(ResidualBlock, self).__init__()

        conv_block = [
            nn.ReflectionPad2d(1),
            nn.Conv2d(in_features, in_features, 3),
            norm_layer(in_features),
            nn.ReLU(inplace=True),
            nn.ReflectionPad2d(1),
            nn.Conv2d(in_features, in_features, 3),
            norm_layer(in_features)
        ]

        self.conv_block = nn.Sequential(*conv_block)

    def forward(self, x):
        return x + self.conv_block(x)

class UnetSkipConnectionBlock(nn.Module):
    """Defines the Unet submodule with skip connection.
        X -------------------identity----------------------
        |-- downsampling -- |submodule| -- upsampling --|
    """

    def __init__(self, outer_nc, inner_nc, input_nc=None,
                 submodule=None, outermost=False, innermost=False, norm_layer=nn.BatchNorm2d, use_dropout=False):
        """Construct a Unet submodule with skip connections.
        Parameters:
            outer_nc (int) -- the number of filters in the outer conv layer
            inner_nc (int) -- the number of filters in the inner conv layer
            input_nc (int) -- the number of channels in input images/features
            submodule (UnetSkipConnectionBlock) -- previously defined submodules
            outermost (bool)    -- if this module is the outermost module
            innermost (bool)    -- if this module is the innermost module
            norm_layer          -- normalization layer
            use_dropout (bool)  -- if use dropout layers.
        """
        super(UnetSkipConnectionBlock, self).__init__()
        self.outermost = outermost
        if type(norm_layer) == functools.partial:
            use_bias = norm_layer.func == nn.InstanceNorm2d
        else:
            use_bias = norm_layer == nn.InstanceNorm2d
        if input_nc is None:
            input_nc = outer_nc
        downconv = nn.Conv2d(input_nc, inner_nc, kernel_size=4,
                             stride=2, padding=1, bias=use_bias)
        downrelu = nn.LeakyReLU(0.2, True)
        downnorm = norm_layer(inner_nc)
        uprelu = nn.ReLU(True)
        upnorm = norm_layer(outer_nc)

        if outermost:
            upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc,
                                        kernel_size=4, stride=2,
                                        padding=1)
            down = [downconv]
            up = [uprelu, upconv, nn.Tanh()]
            model = down + [submodule] + up
        elif innermost:
            upconv = nn.ConvTranspose2d(inner_nc, outer_nc,
                                        kernel_size=4, stride=2,
                                        padding=1, bias=use_bias)
            down = [downrelu, downconv]
            up = [uprelu, upconv, upnorm]
            model = down + up
        else:
            upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc,
                                        kernel_size=4, stride=2,
                                        padding=1, bias=use_bias)
            down = [downrelu, downconv, downnorm]
            up = [uprelu, upconv, upnorm]

            if use_dropout:
                model = down + [submodule] + up + [nn.Dropout(0.5)]
            else:
                model = down + [submodule] + up

        self.model = nn.Sequential(*model)

    def forward(self, x):
        if self.outermost:
            return self.model(x)
        else:   # add skip connections
            return torch.cat([x, self.model(x)], 1)

class SimpleGenerator(nn.Module):
    def __init__(self, input_nc, output_nc, n_residual_blocks=9, sigmoid=True):
        super(SimpleGenerator, self).__init__()

        # Initial convolution block
        model0 = [
            nn.ReflectionPad2d(3),
            nn.Conv2d(input_nc, 64, 7),
            norm_layer(64),
            nn.ReLU(inplace=True)
        ]
        self.model0 = nn.Sequential(*model0)

        # Downsampling
        model1 = []
        in_features = 64
        out_features = in_features*2
        for _ in range(2):
            model1 += [
                nn.Conv2d(in_features, out_features, 3, stride=2, padding=1),
                norm_layer(out_features),
                nn.ReLU(inplace=True)
            ]
            in_features = out_features
            out_features = in_features*2
        self.model1 = nn.Sequential(*model1)

        model2 = []
        # Residual blocks
        for _ in range(n_residual_blocks):
            model2 += [ResidualBlock(in_features)]
        self.model2 = nn.Sequential(*model2)

        # Upsampling
        model3 = []
        out_features = in_features//2
        for _ in range(2):
            model3 += [
                nn.ConvTranspose2d(in_features, out_features, 3, stride=2, padding=1, output_padding=1),
                norm_layer(out_features),
                nn.ReLU(inplace=True)
            ]
            in_features = out_features
            out_features = in_features//2
        self.model3 = nn.Sequential(*model3)

        # Output layer
        model4 = [
            nn.ReflectionPad2d(3),
            nn.Conv2d(64, output_nc, 7)
        ]
        if sigmoid:
            model4 += [nn.Sigmoid()]

        self.model4 = nn.Sequential(*model4)

    def forward(self, x, cond=None):
        out = self.model0(x)
        out = self.model1(out)
        out = self.model2(out)
        out = self.model3(out)
        out = self.model4(out)

        return out

class UnetGenerator(nn.Module):
    """Create a Unet-based generator"""

    def __init__(self, input_nc, output_nc, num_downs, ngf=64, norm_layer=nn.BatchNorm2d, use_dropout=False):
        """Construct a Unet generator
        Parameters:
            input_nc (int)  -- the number of channels in input images
            output_nc (int) -- the number of channels in output images
            num_downs (int) -- the number of downsamplings in UNet. For example, # if |num_downs| == 7,
                                image of size 128x128 will become of size 1x1 # at the bottleneck
            ngf (int)       -- the number of filters in the last conv layer
            norm_layer      -- normalization layer
        We construct the U-Net from the innermost layer to the outermost layer.
        It is a recursive process.
        """
        super(UnetGenerator, self).__init__()
        # construct unet structure
        unet_block = UnetSkipConnectionBlock(ngf * 8, ngf * 8, input_nc=None, submodule=None, norm_layer=norm_layer, innermost=True)  # add the innermost layer
        for _ in range(num_downs - 5):          # add intermediate layers with ngf * 8 filters
            unet_block = UnetSkipConnectionBlock(ngf * 8, ngf * 8, input_nc=None, submodule=unet_block, norm_layer=norm_layer, use_dropout=use_dropout)
        # gradually reduce the number of filters from ngf * 8 to ngf
        unet_block = UnetSkipConnectionBlock(ngf * 4, ngf * 8, input_nc=None, submodule=unet_block, norm_layer=norm_layer)
        unet_block = UnetSkipConnectionBlock(ngf * 2, ngf * 4, input_nc=None, submodule=unet_block, norm_layer=norm_layer)
        unet_block = UnetSkipConnectionBlock(ngf, ngf * 2, input_nc=None, submodule=unet_block, norm_layer=norm_layer)
        self.model = UnetSkipConnectionBlock(output_nc, ngf, input_nc=input_nc, submodule=unet_block, outermost=True, norm_layer=norm_layer)  # add the outermost layer

    def forward(self, input):
        """Standard forward"""
        return self.model(input)