File size: 4,594 Bytes
908a1ab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
import torch
from torch import nn as nn

from basicsr.utils.registry import ARCH_REGISTRY
from .arch_util import Upsample, make_layer


class ChannelAttention(nn.Module):
    """Channel attention used in RCAN.

    Args:
        num_feat (int): Channel number of intermediate features.
        squeeze_factor (int): Channel squeeze factor. Default: 16.
    """

    def __init__(self, num_feat, squeeze_factor=16):
        super(ChannelAttention, self).__init__()
        self.attention = nn.Sequential(
            nn.AdaptiveAvgPool2d(1), nn.Conv2d(num_feat, num_feat // squeeze_factor, 1, padding=0),
            nn.ReLU(inplace=True), nn.Conv2d(num_feat // squeeze_factor, num_feat, 1, padding=0), nn.Sigmoid())

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


class RCAB(nn.Module):
    """Residual Channel Attention Block (RCAB) used in RCAN.

    Args:
        num_feat (int): Channel number of intermediate features.
        squeeze_factor (int): Channel squeeze factor. Default: 16.
        res_scale (float): Scale the residual. Default: 1.
    """

    def __init__(self, num_feat, squeeze_factor=16, res_scale=1):
        super(RCAB, self).__init__()
        self.res_scale = res_scale

        self.rcab = nn.Sequential(
            nn.Conv2d(num_feat, num_feat, 3, 1, 1), nn.ReLU(True), nn.Conv2d(num_feat, num_feat, 3, 1, 1),
            ChannelAttention(num_feat, squeeze_factor))

    def forward(self, x):
        res = self.rcab(x) * self.res_scale
        return res + x


class ResidualGroup(nn.Module):
    """Residual Group of RCAB.

    Args:
        num_feat (int): Channel number of intermediate features.
        num_block (int): Block number in the body network.
        squeeze_factor (int): Channel squeeze factor. Default: 16.
        res_scale (float): Scale the residual. Default: 1.
    """

    def __init__(self, num_feat, num_block, squeeze_factor=16, res_scale=1):
        super(ResidualGroup, self).__init__()

        self.residual_group = make_layer(
            RCAB, num_block, num_feat=num_feat, squeeze_factor=squeeze_factor, res_scale=res_scale)
        self.conv = nn.Conv2d(num_feat, num_feat, 3, 1, 1)

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


@ARCH_REGISTRY.register()
class RCAN(nn.Module):
    """Residual Channel Attention Networks.

    Paper: Image Super-Resolution Using Very Deep Residual Channel Attention
        Networks
    Ref git repo: https://github.com/yulunzhang/RCAN.

    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_group (int): Number of ResidualGroup. Default: 10.
        num_block (int): Number of RCAB in ResidualGroup. Default: 16.
        squeeze_factor (int): Channel squeeze factor. Default: 16.
        upscale (int): Upsampling factor. Support 2^n and 3.
            Default: 4.
        res_scale (float): Used to scale the residual in residual block.
            Default: 1.
        img_range (float): Image range. Default: 255.
        rgb_mean (tuple[float]): Image mean in RGB orders.
            Default: (0.4488, 0.4371, 0.4040), calculated from DIV2K dataset.
    """

    def __init__(self,
                 num_in_ch,
                 num_out_ch,
                 num_feat=64,
                 num_group=10,
                 num_block=16,
                 squeeze_factor=16,
                 upscale=4,
                 res_scale=1,
                 img_range=255.,
                 rgb_mean=(0.4488, 0.4371, 0.4040)):
        super(RCAN, self).__init__()

        self.img_range = img_range
        self.mean = torch.Tensor(rgb_mean).view(1, 3, 1, 1)

        self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1)
        self.body = make_layer(
            ResidualGroup,
            num_group,
            num_feat=num_feat,
            num_block=num_block,
            squeeze_factor=squeeze_factor,
            res_scale=res_scale)
        self.conv_after_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1)
        self.upsample = Upsample(upscale, num_feat)
        self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)

    def forward(self, x):
        self.mean = self.mean.type_as(x)

        x = (x - self.mean) * self.img_range
        x = self.conv_first(x)
        res = self.conv_after_body(self.body(x))
        res += x

        x = self.conv_last(self.upsample(res))
        x = x / self.img_range + self.mean

        return x