main.py

import os
import math
import numpy as np

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


### common function in edsr github
def default_conv(in_channels, out_channels, kernel_size, bias=True):
    return nn.Conv2d(
        in_channels, out_channels, kernel_size,
        padding=(kernel_size//2), bias=bias)


class MeanShift(nn.Conv2d):
    def __init__(
        self, rgb_range,
        rgb_mean=(0.4488, 0.4371, 0.4040), rgb_std=(1.0, 1.0, 1.0), sign=-1):

        super(MeanShift, self).__init__(3, 3, kernel_size=1)
        std = torch.Tensor(rgb_std)
        self.weight.data = torch.eye(3).view(3, 3, 1, 1) / std.view(3, 1, 1, 1)
        self.bias.data = sign * rgb_range * torch.Tensor(rgb_mean) / std
        for p in self.parameters():
            p.requires_grad = False


class Upsampler(nn.Sequential):
    def __init__(self, conv, factor, n_feats, bn=False, act=False, bias=True):

        m = []
        if (factor & (factor - 1)) == 0:    # Is scale = 2^n?
            for _ in range(int(math.log(factor, 2))):
                m.append(conv(n_feats, 4 * n_feats, 3, bias))
                m.append(nn.PixelShuffle(2))
                if bn:
                    m.append(nn.BatchNorm2d(n_feats))
                if act == 'relu':
                    m.append(nn.ReLU(True))
                elif act == 'prelu':
                    m.append(nn.PReLU(n_feats))

        elif factor == 3:
            m.append(conv(n_feats, 9 * n_feats, 3, bias))
            m.append(nn.PixelShuffle(3))
            if bn:
                m.append(nn.BatchNorm2d(n_feats))
            if act == 'relu':
                m.append(nn.ReLU(True))
            elif act == 'prelu':
                m.append(nn.PReLU(n_feats))
        else:
            raise NotImplementedError

        super(Upsampler, self).__init__(*m)


## Channel Attention (CA) Layer
class CALayer(nn.Module):
    def __init__(self, channel, reduction=16):
        super(CALayer, self).__init__()
        # global average pooling: feature --> point
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        # feature channel downscale and upscale --> channel weight
        self.conv_du = nn.Sequential(
                nn.Conv2d(channel, channel // reduction, 1, padding=0, bias=True),
                nn.ReLU(inplace=True),
                nn.Conv2d(channel // reduction, channel, 1, padding=0, bias=True),
                nn.Sigmoid()
        )

    def forward(self, x):
        y = self.avg_pool(x)
        y = self.conv_du(y)
        return x * y


## Residual Channel Attention Block (RCAB)
class RCAB(nn.Module):
    def __init__(
        self, conv, n_feat, kernel_size, reduction,
        bias=True, bn=False, act=nn.ReLU(True), res_scale=1):

        super(RCAB, self).__init__()
        modules_body = []
        for i in range(2):
            modules_body.append(conv(n_feat, n_feat, kernel_size, bias=bias))
            if bn: modules_body.append(nn.BatchNorm2d(n_feat))
            if i == 0: modules_body.append(act)
        # modules_body.append(CALayer(n_feat, reduction))
        self.body = nn.Sequential(*modules_body)
        self.res_scale = res_scale

    def forward(self, x):
        res = self.body(x)
        #res = self.body(x).mul(self.res_scale)
        res += x
        return res


## Residual Group (RG)
class ResidualGroup(nn.Module):
    def __init__(self, conv, n_feat, kernel_size, reduction, act, res_scale, n_resblocks):
        super(ResidualGroup, self).__init__()
        modules_body = []
        modules_body = [
            RCAB(
                conv, n_feat, kernel_size, reduction, bias=True, bn=False, act=nn.ReLU(True), res_scale=1) \
            for _ in range(n_resblocks)]
        modules_body.append(conv(n_feat, n_feat, kernel_size))
        self.body = nn.Sequential(*modules_body)

    def forward(self, x):
        res = self.body(x)
        res += x
        return res


## Generator model
class Generator(nn.Module):
    def __init__(self, conv=default_conv):
        super(Generator, self).__init__()

        n_resgroups = 4
        n_resblocks = 4
        n_feats = 32
        reduction = 16
        scale = 4
        kernel_size = 3
        res_scale = 1
        n_colors = 3
        rgb_range = 1
        act = nn.ReLU(True)

        # RGB mean for DIV2K
        rgb_mean = (0.4488, 0.4371, 0.4040)
        rgb_std = (1.0, 1.0, 1.0)
        self.sub_mean = MeanShift(rgb_range, rgb_mean, rgb_std)

        # define head module
        modules_head = [conv(n_colors, n_feats, kernel_size)]

        # define body module
        modules_body = [
            ResidualGroup(
                conv, n_feats, kernel_size, reduction, act=act, res_scale=res_scale, n_resblocks=n_resblocks) \
            for _ in range(n_resgroups)]

        modules_body.append(conv(n_feats, n_feats, kernel_size))

        # define tail module
        modules_tail = [
            Upsampler(conv, scale, n_feats, act=False),
            conv(n_feats, n_colors, kernel_size)]

        self.add_mean = MeanShift(rgb_range, rgb_mean, rgb_std, 1)

        self.head = nn.Sequential(*modules_head)
        self.body = nn.Sequential(*modules_body)
        self.tail = nn.Sequential(*modules_tail)

    def forward(self, x):
        x = self.sub_mean(x)
        x = self.head(x)

        res = self.body(x)
        res += x

        x = self.tail(res)
        x = self.add_mean(x)

        return x