File size: 5,813 Bytes
d6ec83b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
## ECCV-2018-Image Super-Resolution Using Very Deep Residual Channel Attention Networks
## https://arxiv.org/abs/1807.02758
from model import common
from model.attention import ContextualAttention
import torch.nn as nn
import torch
def make_model(args, parent=False):
return RCAN(args)
## 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.a = torch.nn.Parameter(torch.Tensor([0]))
#self.a.requires_grad=True
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
## Residual Channel Attention Network (RCAN)
class RCAN(nn.Module):
def __init__(self, args, conv=common.default_conv):
super(RCAN, self).__init__()
self.a = nn.Parameter(torch.Tensor([0]))
self.a.requires_grad=True
n_resgroups = args.n_resgroups
n_resblocks = args.n_resblocks
n_feats = args.n_feats
kernel_size = 3
reduction = args.reduction
scale = args.scale[0]
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 = common.MeanShift(args.rgb_range, rgb_mean, rgb_std)
# define head module
modules_head = [conv(args.n_colors, n_feats, kernel_size)]
self.msa = ContextualAttention()
# define body module
modules_body = [
ResidualGroup(
conv, n_feats, kernel_size, reduction, act=act, res_scale=args.res_scale, n_resblocks=n_resblocks) \
for _ in range(5)]
modules_body.append(self.msa)
for i in range(5):
modules_body.append(ResidualGroup(conv,n_feats,kernel_size,reduction,act=act,res_scale=args.res_scale,n_resblocks=n_resblocks))
modules_body.append(conv(n_feats, n_feats, kernel_size))
# define tail module
modules_tail = [
common.Upsampler(conv, scale, n_feats, act=False),
conv(n_feats, args.n_colors, kernel_size)]
self.add_mean = common.MeanShift(args.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
def load_state_dict(self, state_dict, strict=False):
own_state = self.state_dict()
for name, param in state_dict.items():
if name in own_state:
if isinstance(param, nn.Parameter):
param = param.data
try:
own_state[name].copy_(param)
except Exception:
if name.find('msa') or name.find('a') >= 0:
print('Replace pre-trained upsampler to new one...')
else:
raise RuntimeError('While copying the parameter named {}, '
'whose dimensions in the model are {} and '
'whose dimensions in the checkpoint are {}.'
.format(name, own_state[name].size(), param.size()))
elif strict:
if name.find('msa') == -1:
raise KeyError('unexpected key "{}" in state_dict'
.format(name))
if strict:
missing = set(own_state.keys()) - set(state_dict.keys())
if len(missing) > 0:
raise KeyError('missing keys in state_dict: "{}"'.format(missing))
|