Spaces:
Running
on
Zero
Running
on
Zero
File size: 12,203 Bytes
c509e76 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 |
## Restormer: Efficient Transformer for High-Resolution Image Restoration
## Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang
## https://arxiv.org/abs/2111.09881
import torch
import torch.nn as nn
import torch.nn.functional as F
from pdb import set_trace as stx
import numbers
from einops import rearrange
##########################################################################
## Layer Norm
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 FeedForward(nn.Module):
def __init__(self, dim, ffn_expansion_factor, bias):
super(FeedForward, 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, num_heads, ffn_expansion_factor, bias, LayerNorm_type):
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 = FeedForward(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
##########################################################################
## Overlapped image patch embedding with 3x3 Conv
class OverlapPatchEmbed(nn.Module):
def __init__(self, in_c=3, embed_dim=48, bias=False):
super(OverlapPatchEmbed, self).__init__()
self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=3, stride=1, padding=1, bias=bias)
def forward(self, x):
x = self.proj(x)
return x
##########################################################################
## Resizing modules
class Downsample(nn.Module):
def __init__(self, n_feat):
super(Downsample, self).__init__()
self.body = nn.Sequential(nn.Conv2d(n_feat, n_feat//2, kernel_size=3, stride=1, padding=1, bias=False),
nn.PixelUnshuffle(2))
def forward(self, x):
return self.body(x)
class Upsample(nn.Module):
def __init__(self, n_feat):
super(Upsample, self).__init__()
self.body = nn.Sequential(nn.Conv2d(n_feat, n_feat*2, kernel_size=3, stride=1, padding=1, bias=False),
nn.PixelShuffle(2))
def forward(self, x):
return self.body(x)
##########################################################################
##---------- Restormer -----------------------
class Restormer(nn.Module):
def __init__(self,
inp_channels=3,
out_channels=3,
dim = 48,
num_blocks = [4,6,6,8],
num_refinement_blocks = 4,
heads = [1,2,4,8],
ffn_expansion_factor = 2.66,
bias = False,
LayerNorm_type = 'WithBias', ## Other option 'BiasFree'
dual_pixel_task = True ## True for dual-pixel defocus deblurring only. Also set inp_channels=6
):
super(Restormer, self).__init__()
self.patch_embed = OverlapPatchEmbed(inp_channels, dim)
self.encoder_level1 = nn.Sequential(*[TransformerBlock(dim=dim, num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[0])])
self.down1_2 = Downsample(dim) ## From Level 1 to Level 2
self.encoder_level2 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[1], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[1])])
self.down2_3 = Downsample(int(dim*2**1)) ## From Level 2 to Level 3
self.encoder_level3 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**2), num_heads=heads[2], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[2])])
self.down3_4 = Downsample(int(dim*2**2)) ## From Level 3 to Level 4
self.latent = nn.Sequential(*[TransformerBlock(dim=int(dim*2**3), num_heads=heads[3], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[3])])
self.up4_3 = Upsample(int(dim*2**3)) ## From Level 4 to Level 3
self.reduce_chan_level3 = nn.Conv2d(int(dim*2**3), int(dim*2**2), kernel_size=1, bias=bias)
self.decoder_level3 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**2), num_heads=heads[2], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[2])])
self.up3_2 = Upsample(int(dim*2**2)) ## From Level 3 to Level 2
self.reduce_chan_level2 = nn.Conv2d(int(dim*2**2), int(dim*2**1), kernel_size=1, bias=bias)
self.decoder_level2 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[1], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[1])])
self.up2_1 = Upsample(int(dim*2**1)) ## From Level 2 to Level 1 (NO 1x1 conv to reduce channels)
self.decoder_level1 = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_blocks[0])])
self.refinement = nn.Sequential(*[TransformerBlock(dim=int(dim*2**1), num_heads=heads[0], ffn_expansion_factor=ffn_expansion_factor, bias=bias, LayerNorm_type=LayerNorm_type) for i in range(num_refinement_blocks)])
#### For Dual-Pixel Defocus Deblurring Task ####
self.dual_pixel_task = dual_pixel_task
if self.dual_pixel_task:
self.skip_conv = nn.Conv2d(dim, int(dim*2**1), kernel_size=1, bias=bias)
###########################
self.output = nn.Conv2d(int(dim*2**1), out_channels, kernel_size=3, stride=1, padding=1, bias=bias)
def forward(self, inp_img,task=''):
inp_enc_level1 = self.patch_embed(inp_img)
out_enc_level1 = self.encoder_level1(inp_enc_level1)
inp_enc_level2 = self.down1_2(out_enc_level1)
out_enc_level2 = self.encoder_level2(inp_enc_level2)
inp_enc_level3 = self.down2_3(out_enc_level2)
out_enc_level3 = self.encoder_level3(inp_enc_level3)
inp_enc_level4 = self.down3_4(out_enc_level3)
latent = self.latent(inp_enc_level4)
inp_dec_level3 = self.up4_3(latent)
inp_dec_level3 = torch.cat([inp_dec_level3, out_enc_level3], 1)
inp_dec_level3 = self.reduce_chan_level3(inp_dec_level3)
out_dec_level3 = self.decoder_level3(inp_dec_level3)
inp_dec_level2 = self.up3_2(out_dec_level3)
inp_dec_level2 = torch.cat([inp_dec_level2, out_enc_level2], 1)
inp_dec_level2 = self.reduce_chan_level2(inp_dec_level2)
out_dec_level2 = self.decoder_level2(inp_dec_level2)
inp_dec_level1 = self.up2_1(out_dec_level2)
inp_dec_level1 = torch.cat([inp_dec_level1, out_enc_level1], 1)
out_dec_level1 = self.decoder_level1(inp_dec_level1)
out_dec_level1 = self.refinement(out_dec_level1)
out_dec_level1 = out_dec_level1 + self.skip_conv(inp_enc_level1)
out_dec_level1 = self.output(out_dec_level1)
return out_dec_level1
if __name__ == '__main__':
from torchtoolbox.tools import summary
model = Restormer(
inp_channels=6,
out_channels=3,
dim = 48,
# num_blocks = [4,6,6,8],
num_blocks = [2,3,3,4],
num_refinement_blocks = 4,
heads = [1,2,4,8],
ffn_expansion_factor = 2.66,
bias = False,
LayerNorm_type = 'WithBias', ## Other option 'BiasFree'
dual_pixel_task = True ## True for dual-pixel defocus deblurring only. Also set inp_channels=6
)
# model = Restormer(num_blocks=[4, 6, 6, 8], num_heads=[1, 2, 4, 8], channels=[48, 96, 192, 384], num_refinement=4, expansion_factor=2.66)
print(summary(model,torch.rand((1, 6, 256, 256))))
from thop import profile
input = torch.rand((1, 6, 256, 256))
gflops,params = profile(model,inputs=(input,))
gflops = gflops*2 / 10**9
params = params / 10**6
print(gflops,'==============')
print(params,'==============') |