npr_model.py

import torch
from torch import nn
from torch.nn import functional as F


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super().__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(
            planes, planes, kernel_size=3, stride=stride, padding=1, bias=False
        )
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * self.expansion, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample

    def forward(self, x):
        identity = x

        out = self.relu(self.bn1(self.conv1(x)))
        out = self.relu(self.bn2(self.conv2(out)))
        out = self.bn3(self.conv3(out))

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        return self.relu(out)


class NPRModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.unfold_size = 2
        self.unfold_index = 0
        self.inplanes = 64
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(64, 3)
        self.layer2 = self._make_layer(128, 4, stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc1 = nn.Linear(512, 1)

    def _make_layer(self, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * Bottleneck.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(
                    self.inplanes,
                    planes * Bottleneck.expansion,
                    kernel_size=1,
                    stride=stride,
                    bias=False,
                ),
                nn.BatchNorm2d(planes * Bottleneck.expansion),
            )

        layers = [Bottleneck(self.inplanes, planes, stride, downsample)]
        self.inplanes = planes * Bottleneck.expansion
        for _ in range(1, blocks):
            layers.append(Bottleneck(self.inplanes, planes))

        return nn.Sequential(*layers)

    @staticmethod
    def interpolate(image, factor):
        return F.interpolate(
            F.interpolate(image, scale_factor=factor, mode="nearest", recompute_scale_factor=True),
            scale_factor=1 / factor,
            mode="nearest",
            recompute_scale_factor=True,
        )

    def forward(self, x):
        _, _, height, width = x.shape
        if height % 2 == 1:
            x = x[:, :, :-1, :]
        if width % 2 == 1:
            x = x[:, :, :, :-1]

        x = (x - self.interpolate(x, 0.5)) * (2.0 / 3.0)
        x = self.relu(self.bn1(self.conv1(x)))
        x = self.maxpool(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = torch.flatten(self.avgpool(x), 1)
        return self.fc1(x)