【无标题】Real_EDRGAN rrdbnet_arch.py

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

from basicsr.utils.registry import ARCH_REGISTRY
from .arch_util import default_init_weights, make_layer, pixel_unshuffle


class ResidualDenseBlock(nn.Module):
    """Residual Dense Block.

    Used in RRDB block in ESRGAN.

    Args:
        num_feat (int): Channel number of intermediate features.
        num_grow_ch (int): Channels for each growth.
    """

    def __init__(self, num_feat=64, num_grow_ch=32):
        super(ResidualDenseBlock, self).__init__()
        self.conv1 = nn.Conv2d(num_feat, num_grow_ch, 3, 1, 1)
        self.conv2 = nn.Conv2d(num_feat + num_grow_ch, num_grow_ch, 3, 1, 1)
        self.conv3 = nn.Conv2d(num_feat + 2 * num_grow_ch, num_grow_ch, 3, 1, 1)
        self.conv4 = nn.Conv2d(num_feat + 3 * num_grow_ch, num_grow_ch, 3, 1, 1)
        self.conv5 = nn.Conv2d(num_feat + 4 * num_grow_ch, num_feat, 3, 1, 1)

        self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)

        # initialization
        default_init_weights([self.conv1, self.conv2, self.conv3, self.conv4, self.conv5], 0.1)

    def forward(self, x):
        x1 = self.lrelu(self.conv1(x))
        x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1)))
        x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
        x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1)))
        x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1))
        # Empirically, we use 0.2 to scale the residual for better performance
        return x5 * 0.2 + x


class RRDB(nn.Module):
    """Residual in Residual Dense Block.

    Used in RRDB-Net in ESRGAN.

    Args:
        num_feat (int): Channel number of intermediate features.
        num_grow_ch (int): Channels for each growth.
    """

    def __init__(self, num_feat, num_grow_ch=32):
        super(RRDB, self).__init__()
        self.rdb1 = ResidualDenseBlock(num_feat, num_grow_ch)
        self.rdb2 = ResidualDenseBlock(num_feat, num_grow_ch)
        # self.rdb3 = ResidualDenseBlock(num_feat, num_grow_ch)

    def forward(self, x):
        out = self.rdb1(x)
        out = self.rdb2(out)
        # out = self.rdb3(out)
        # Empirically, we use 0.2 to scale the residual for better performance
        return out * 0.2 + x


# @ARCH_REGISTRY.register()
# class RRDBNet(nn.Module):
#     """Networks consisting of Residual in Residual Dense Block, which is used
#     in ESRGAN.

#     ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.

#     We extend ESRGAN for scale x2 and scale x1.
#     Note: This is one option for scale 1, scale 2 in RRDBNet.
#     We first employ the pixel-unshuffle (an inverse operation of pixelshuffle to reduce the spatial size
#     and enlarge the channel size before feeding inputs into the main ESRGAN architecture.

#     Args:
#         num_in_ch (int): Channel number of inputs.
#         num_out_ch (int): Channel number of outputs.
#         num_feat (int): Channel number of intermediate features.
#             Default: 64
#         num_block (int): Block number in the trunk network. Defaults: 23
#         num_grow_ch (int): Channels for each growth. Default: 32.
#     """

#     def __init__(self, num_in_ch, num_out_ch, scale=4, num_feat=64, num_block=23, num_grow_ch=32):
#         super(RRDBNet, self).__init__()
#         self.scale = scale
#         if scale == 2:
#             num_in_ch = num_in_ch * 4
#         elif scale == 1:
#             num_in_ch = num_in_ch * 16
#         self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
#         self.body = make_layer(RRDB, num_block, num_feat=num_feat, num_grow_ch=num_grow_ch)
#         self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
#         # upsample
#         self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
#         self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
#         self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
#         self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)

#         self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)

#     def forward(self, x):
#         if self.scale == 2:
#             feat = pixel_unshuffle(x, scale=2)
#         elif self.scale == 1:
#             feat = pixel_unshuffle(x, scale=4)
#         else:
#             feat = x
#         feat = self.conv_first(feat)
#         body_feat = self.conv_body(self.body(feat))
#         feat = feat + body_feat
#         # upsample
#         feat = self.lrelu(self.conv_up1(F.interpolate(feat, scale_factor=2, mode='nearest')))
#         feat = self.lrelu(self.conv_up2(F.interpolate(feat, scale_factor=2, mode='nearest')))
#         out = self.conv_last(self.lrelu(self.conv_hr(feat)))
#         return out



def pixel_shuffle_resume(x, scale):
    """ Pixel shuffle.

    Args:
        x (Tensor): Input feature with shape (b, c, h, w).
        scale (int): Upsample ratio.

    Returns:
        Tensor: the pixel shuffled feature.
    """
    scale = scale * 2
    b, c, h, w = x.size()
    out_channel = 1
    assert h % 2 == 0 and w % 2 == 0
    hh = h * scale
    ww = w  * scale
    # x_view = x.view(b, out_channel, 2, 4, h, w)
    # return x_view.permute(0, 1, 4, 2, 5, 3).reshape(b, out_channel, hh, ww)
    x_view = x.view(b, out_channel, scale, scale, h, w)
    return x_view.permute(0, 1, 4, 2, 5, 3).reshape(b, out_channel, hh, ww)

@ARCH_REGISTRY.register()
class RRDBNet(nn.Module):
    """Networks consisting of Residual in Residual Dense Block, which is used
    in ESRGAN.

    ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.

    We extend ESRGAN for scale x2 and scale x1.
    Note: This is one option for scale 1, scale 2 in RRDBNet.
    We first employ the pixel-unshuffle (an inverse operation of pixelshuffle to reduce the spatial size
    and enlarge the channel size before feeding inputs into the main ESRGAN architecture.

    Args:
        num_in_ch (int): Channel number of inputs.
        num_out_ch (int): Channel number of outputs.
        num_feat (int): Channel number of intermediate features.
            Default: 64
        num_block (int): Block number in the trunk network. Defaults: 23
        num_grow_ch (int): Channels for each growth. Default: 32.
    """

    def __init__(self, num_in_ch, num_out_ch, scale=4, num_feat=64, num_block=23, num_grow_ch=32):
        super(RRDBNet, self).__init__()
        self.scale = scale
        if scale == 2:
            num_in_ch = num_in_ch * 4 * 4
        elif scale == 1:
            num_in_ch = num_in_ch * 16
        self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
        self.body = make_layer(RRDB, num_block, num_feat=num_feat, num_grow_ch=num_grow_ch)
        self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
        # upsample
        self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
        # self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
        self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
        self.conv_last = nn.Conv2d(num_feat, num_out_ch * 4 * 4, 3, 1, 1)

        self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)

    def forward(self, x):
        if self.scale == 2:
            feat = pixel_unshuffle(x, scale=2)
        elif self.scale == 1:
            feat = pixel_unshuffle(x, scale=4)
        else:
            feat = x
        feat = self.conv_first(feat)
        body_feat = self.conv_body(self.body(feat))
        feat = feat + body_feat
        # upsample
        feat = self.lrelu(self.conv_up1(F.interpolate(feat, scale_factor=2, mode='nearest')))
        # feat = self.lrelu(self.conv_up2(F.interpolate(feat, scale_factor=2, mode='nearest')))
        out = self.conv_last(self.lrelu(self.conv_hr(feat)))
        # out = self.conv_last(feat)
        return pixel_shuffle_resume(out, self.scale)