Spaces:
Build error
Build error
File size: 9,236 Bytes
60e23e3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 |
import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange
from einops.layers.torch import Rearrange
import numbers
# LayerNorm
def to_3d(x):
return rearrange(x, 'b c h w -> b (h w) c')
def to_4d(x,h,w):
return rearrange(x, 'b (h w) c -> b c h w',h=h,w=w)
class BiasFree_LayerNorm(nn.Module):
def __init__(self, normalized_shape):
super(BiasFree_LayerNorm, self).__init__()
if isinstance(normalized_shape, numbers.Integral):
normalized_shape = (normalized_shape,)
normalized_shape = torch.Size(normalized_shape)
assert len(normalized_shape) == 1
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.normalized_shape = normalized_shape
def forward(self, x):
sigma = x.var(-1, keepdim=True, unbiased=False)
return x / torch.sqrt(sigma+1e-5) * self.weight
class WithBias_LayerNorm(nn.Module):
def __init__(self, normalized_shape):
super(WithBias_LayerNorm, self).__init__()
if isinstance(normalized_shape, numbers.Integral):
normalized_shape = (normalized_shape,)
normalized_shape = torch.Size(normalized_shape)
assert len(normalized_shape) == 1
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.bias = nn.Parameter(torch.zeros(normalized_shape))
self.normalized_shape = normalized_shape
def forward(self, x):
mu = x.mean(-1, keepdim=True)
sigma = x.var(-1, keepdim=True, unbiased=False)
return (x - mu) / torch.sqrt(sigma+1e-5) * self.weight + self.bias
class LayerNorm(nn.Module):
def __init__(self, dim, LayerNorm_type):
super(LayerNorm, self).__init__()
if LayerNorm_type =='BiasFree':
self.body = BiasFree_LayerNorm(dim)
else:
self.body = WithBias_LayerNorm(dim)
def forward(self, x):
h, w = x.shape[-2:]
return to_4d(self.body(to_3d(x)), h, w)
## Gated-Dconv Feed-Forward Network (GDFN)
class GFeedForward(nn.Module):
def __init__(self, dim, ffn_expansion_factor, bias):
super(GFeedForward, self).__init__()
hidden_features = int(dim * ffn_expansion_factor)
self.project_in = nn.Conv2d(dim, hidden_features * 2, kernel_size=1, bias=bias)
self.dwconv = nn.Conv2d(hidden_features * 2, hidden_features * 2, kernel_size=3, stride=1, padding=1,
groups=hidden_features * 2, bias=bias)
self.project_out = nn.Conv2d(hidden_features, dim, kernel_size=1, bias=bias)
def forward(self, x):
x = self.project_in(x)
x1, x2 = self.dwconv(x).chunk(2, dim=1)
x = F.gelu(x1) * x2
x = self.project_out(x)
return x
##########################################################################
## Multi-DConv Head Transposed Self-Attention (MDTA)
class Attention(nn.Module):
def __init__(self, dim, num_heads, bias):
super(Attention, self).__init__()
self.num_heads = num_heads
self.temperature = nn.Parameter(torch.ones(num_heads, 1, 1))
self.qkv = nn.Conv2d(dim, dim * 3, kernel_size=1, bias=bias)
self.qkv_dwconv = nn.Conv2d(dim * 3, dim * 3, kernel_size=3, stride=1, padding=1, groups=dim * 3, bias=bias)
self.project_out = nn.Conv2d(dim, dim, kernel_size=1, bias=bias)
def forward(self, x):
b, c, h, w = x.shape
qkv = self.qkv_dwconv(self.qkv(x))
q, k, v = qkv.chunk(3, dim=1)
q = rearrange(q, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
k = rearrange(k, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
v = rearrange(v, 'b (head c) h w -> b head c (h w)', head=self.num_heads)
q = torch.nn.functional.normalize(q, dim=-1)
k = torch.nn.functional.normalize(k, dim=-1)
attn = (q @ k.transpose(-2, -1)) * self.temperature
attn = attn.softmax(dim=-1)
out = (attn @ v)
out = rearrange(out, 'b head c (h w) -> b (head c) h w', head=self.num_heads, h=h, w=w)
out = self.project_out(out)
return out
class TransformerBlock(nn.Module):
def __init__(self, dim=48, num_heads=8, ffn_expansion_factor=2.66, bias=False, LayerNorm_type=WithBias_LayerNorm):
super(TransformerBlock, self).__init__()
self.norm1 = LayerNorm(dim, LayerNorm_type)
self.attn = Attention(dim, num_heads, bias)
self.norm2 = LayerNorm(dim, LayerNorm_type)
self.ffn = GFeedForward(dim, ffn_expansion_factor, bias)
def forward(self, x):
x = x + self.attn(self.norm1(x))
x = x + self.ffn(self.norm2(x))
return x
class BackBoneBlock(nn.Module):
def __init__(self, num, fm, **args):
super().__init__()
self.arr = nn.ModuleList([])
for _ in range(num):
self.arr.append(fm(**args))
def forward(self, x):
for block in self.arr:
x = block(x)
return x
class PAConv(nn.Module):
def __init__(self, nf, k_size=3):
super(PAConv, self).__init__()
self.k2 = nn.Conv2d(nf, nf, 1) # 1x1 convolution nf->nf
self.sigmoid = nn.Sigmoid()
self.k3 = nn.Conv2d(nf, nf, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False) # 3x3 convolution
self.k4 = nn.Conv2d(nf, nf, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False) # 3x3 convolution
def forward(self, x):
y = self.k2(x)
y = self.sigmoid(y)
out = torch.mul(self.k3(x), y)
out = self.k4(out)
return out
class SCPA(nn.Module):
"""SCPA is modified from SCNet (Jiang-Jiang Liu et al. Improving Convolutional Networks with Self-Calibrated Convolutions. In CVPR, 2020)
Github: https://github.com/MCG-NKU/SCNet
"""
def __init__(self, nf, reduction=2, stride=1, dilation=1):
super(SCPA, self).__init__()
group_width = nf // reduction
self.conv1_a = nn.Conv2d(nf, group_width, kernel_size=1, bias=False)
self.conv1_b = nn.Conv2d(nf, group_width, kernel_size=1, bias=False)
self.k1 = nn.Sequential(
nn.Conv2d(
group_width, group_width, kernel_size=3, stride=stride,
padding=dilation, dilation=dilation,
bias=False)
)
self.PAConv = PAConv(group_width)
self.conv3 = nn.Conv2d(
group_width * reduction, nf, kernel_size=1, bias=False)
self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
def forward(self, x):
residual = x
out_a = self.conv1_a(x)
out_b = self.conv1_b(x)
out_a = self.lrelu(out_a)
out_b = self.lrelu(out_b)
out_a = self.k1(out_a)
out_b = self.PAConv(out_b)
out_a = self.lrelu(out_a)
out_b = self.lrelu(out_b)
out = self.conv3(torch.cat([out_a, out_b], dim=1))
out += residual
return out
class SCET(nn.Module):
def __init__(self, hiddenDim=32, mlpDim=128, scaleFactor=2):
super().__init__()
self.conv3 = nn.Conv2d(3, hiddenDim,
kernel_size=3, padding=1)
lamRes = torch.nn.Parameter(torch.ones(1))
lamX = torch.nn.Parameter(torch.ones(1))
self.adaptiveWeight = (lamRes, lamX)
if scaleFactor == 3:
num_heads = 7
else:
num_heads = 8
self.path1 = nn.Sequential(
BackBoneBlock(16, SCPA, nf=hiddenDim, reduction=2, stride=1, dilation=1),
BackBoneBlock(1, TransformerBlock,
dim=hiddenDim, num_heads=num_heads, ffn_expansion_factor=2.66, bias=False, LayerNorm_type=WithBias_LayerNorm),
nn.Conv2d(hiddenDim, hiddenDim, kernel_size=3, padding=1),
nn.PixelShuffle(scaleFactor),
nn.Conv2d(hiddenDim // (scaleFactor ** 2),
3, kernel_size=3, padding=1),
)
self.path2 = nn.Sequential(
nn.PixelShuffle(scaleFactor),
nn.Conv2d(hiddenDim // (scaleFactor ** 2),
3, kernel_size=3, padding=1),
)
def forward(self, x):
x = self.conv3(x)
x1, x2 = self.path1(x), self.path2(x)
return x1 + x2
def init_weights(self, pretrained=None, strict=True):
"""Init weights for models.
Args:
pretrained (str, optional): Path for pretrained weights. If given
None, pretrained weights will not be loaded. Defaults to None.
strict (boo, optional): Whether strictly load the pretrained model.
Defaults to True.
"""
if isinstance(pretrained, str):
logger = get_root_logger()
load_checkpoint(self, pretrained, strict=strict, logger=logger)
elif pretrained is None:
pass # use default initialization
else:
raise TypeError('"pretrained" must be a str or None. '
f'But received {type(pretrained)}.')
if __name__ == '__main__':
from torchstat import stat
import time
import torchsummary
net = SCET(32, 128, 4).cuda()
torchsummary.summary(net, (3, 48, 48)) |