Pytorch搭建SRGAN平台提升图片超分辨率

发布时间：2023-11-28 18:00

网络构建

一、什么是SRGAN

SRGAN出自论文Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network。

如果将SRGAN看作一个黑匣子，其主要的功能就是输入一张低分辨率图片，生成高分辨率图片。

$\"Pytorch搭建SRGAN平台提升图片超分辨率_第1张图片\"$

该文章提到，普通的超分辨率模型训练网络时只用到了均方差作为损失函数，虽然能够获得很高的峰值信噪比，但是恢复出来的图像通常会丢失高频细节。

SRGAN利用感知损失(perceptual loss)和对抗损失(adversarial loss)来提升恢复出的图片的真实感。

二、生成网络的构建

$\"Pytorch搭建SRGAN平台提升图片超分辨率_第2张图片\"$

生成网络的构成如上图所示，生成网络的作用是输入一张低分辨率图片，生成高分辨率图片。：

SRGAN的生成网络由三个部分组成。

1、低分辨率图像进入后会经过一个卷积+RELU函数。

2、然后经过B个残差网络结构，每个残差结构都包含两个卷积+标准化+RELU，还有一个残差边。

3、然后进入上采样部分，在经过两次上采样后，原图的高宽变为原来的4倍，实现分辨率的提升。

前两个部分用于特征提取，第三部分用于提高分辨率。

import math
import torch
from torch import nn
class ResidualBlock(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(channels)
        self.prelu = nn.PReLU(channels)
        self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(channels)
    def forward(self, x):
        short_cut = x
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.prelu(x)
        x = self.conv2(x)
        x = self.bn2(x)
        return x + short_cut
class UpsampleBLock(nn.Module):
    def __init__(self, in_channels, up_scale):
        super(UpsampleBLock, self).__init__()
        self.conv = nn.Conv2d(in_channels, in_channels * up_scale ** 2, kernel_size=3, padding=1)
        self.pixel_shuffle = nn.PixelShuffle(up_scale)
        self.prelu = nn.PReLU(in_channels)
    def forward(self, x):
        x = self.conv(x)
        x = self.pixel_shuffle(x)
        x = self.prelu(x)
        return x
class Generator(nn.Module):
    def __init__(self, scale_factor, num_residual=16):
        upsample_block_num = int(math.log(scale_factor, 2))
        super(Generator, self).__init__()
        self.block_in = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=9, padding=4),
            nn.PReLU(64)
        )
        self.blocks = []
        for _ in range(num_residual):
            self.blocks.append(ResidualBlock(64))
        self.blocks = nn.Sequential(*self.blocks)
        self.block_out = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, padding=1),
            nn.BatchNorm2d(64)
        )
        self.upsample = [UpsampleBLock(64, 2) for _ in range(upsample_block_num)]
        self.upsample.append(nn.Conv2d(64, 3, kernel_size=9, padding=4))
        self.upsample = nn.Sequential(*self.upsample)
    def forward(self, x):
        x = self.block_in(x)
        short_cut = x
        x = self.blocks(x)
        x = self.block_out(x)
        upsample = self.upsample(x + short_cut)
        return torch.tanh(upsample)

三、判别网络的构建

$\"Pytorch搭建SRGAN平台提升图片超分辨率_第3张图片\"$

判别网络的构成如上图所示：

SRGAN的判别网络由不断重复的卷积+LeakyRELU和标准化组成。
对于判断网络来讲，它的目的是判断输入图片的真假，它的输入是图片，输出是判断结果。

判断结果处于0-1之间，利用接近1代表判断为真图片，接近0代表判断为假图片。

判断网络的构建和普通卷积网络差距不大，都是不断的卷积对图片进行下采用，在多次卷积后，最终接一次全连接判断结果。

实现代码如下：

class Discriminator(nn.Module):
    def __init__(self):
        super(Discriminator, self).__init__()
        self.net = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=3, padding=1),
            nn.LeakyReLU(0.2),
            nn.Conv2d(64, 64, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(64),
            nn.LeakyReLU(0.2),
            nn.Conv2d(64, 128, kernel_size=3, padding=1),
            nn.BatchNorm2d(128),
            nn.LeakyReLU(0.2),
            nn.Conv2d(128, 128, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(128),
            nn.LeakyReLU(0.2),
            nn.Conv2d(128, 256, kernel_size=3, padding=1),
            nn.BatchNorm2d(256),
            nn.LeakyReLU(0.2),
            nn.Conv2d(256, 256, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(256),
            nn.LeakyReLU(0.2),
            nn.Conv2d(256, 512, kernel_size=3, padding=1),
            nn.BatchNorm2d(512),
            nn.LeakyReLU(0.2),
            nn.Conv2d(512, 512, kernel_size=3, stride=2, padding=1),
            nn.BatchNorm2d(512),
            nn.LeakyReLU(0.2),
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(512, 1024, kernel_size=1),
            nn.LeakyReLU(0.2),
            nn.Conv2d(1024, 1, kernel_size=1)
        )
    def forward(self, x):
        batch_size = x.size(0)
        return torch.sigmoid(self.net(x).view(batch_size))