| 227 | |
| 228 | |
| 229 | class AttnBlock(nn.Module): |
| 230 | def __init__(self, in_channels): |
| 231 | super().__init__() |
| 232 | self.in_channels = in_channels |
| 233 | |
| 234 | self.norm = Normalize(in_channels) |
| 235 | self.q = torch.nn.Conv2d(in_channels, |
| 236 | in_channels, |
| 237 | kernel_size=1, |
| 238 | stride=1, |
| 239 | padding=0) |
| 240 | self.k = torch.nn.Conv2d(in_channels, |
| 241 | in_channels, |
| 242 | kernel_size=1, |
| 243 | stride=1, |
| 244 | padding=0) |
| 245 | self.v = torch.nn.Conv2d(in_channels, |
| 246 | in_channels, |
| 247 | kernel_size=1, |
| 248 | stride=1, |
| 249 | padding=0) |
| 250 | self.proj_out = torch.nn.Conv2d(in_channels, |
| 251 | in_channels, |
| 252 | kernel_size=1, |
| 253 | stride=1, |
| 254 | padding=0) |
| 255 | |
| 256 | def forward(self, x): |
| 257 | h_ = x |
| 258 | h_ = self.norm(h_) |
| 259 | q = self.q(h_) |
| 260 | k = self.k(h_) |
| 261 | v = self.v(h_) |
| 262 | |
| 263 | # compute attention |
| 264 | b, c, h, w = q.shape |
| 265 | q = q.reshape(b, c, h*w) |
| 266 | q = q.permute(0, 2, 1) # b,hw,c |
| 267 | k = k.reshape(b, c, h*w) # b,c,hw |
| 268 | w_ = torch.bmm(q, k) # b,hw,hw w[b,i,j]=sum_c q[b,i,c]k[b,c,j] |
| 269 | w_ = w_ * (int(c)**(-0.5)) |
| 270 | w_ = torch.nn.functional.softmax(w_, dim=2) |
| 271 | |
| 272 | # attend to values |
| 273 | v = v.reshape(b, c, h*w) |
| 274 | w_ = w_.permute(0, 2, 1) # b,hw,hw (first hw of k, second of q) |
| 275 | h_ = torch.bmm(v, w_) # b, c,hw (hw of q) h_[b,c,j] = sum_i v[b,c,i] w_[b,i,j] |
| 276 | h_ = h_.reshape(b, c, h, w) |
| 277 | |
| 278 | h_ = self.proj_out(h_) |
| 279 | |
| 280 | return x+h_ |
| 281 | |
| 282 | |
| 283 | class Model(nn.Module): |