| 91 | |
| 92 | class SpatialSelfAttention(nn.Module): |
| 93 | def __init__(self, in_channels): |
| 94 | super().__init__() |
| 95 | self.in_channels = in_channels |
| 96 | |
| 97 | self.norm = Normalize(in_channels) |
| 98 | self.q = torch.nn.Conv2d(in_channels, |
| 99 | in_channels, |
| 100 | kernel_size=1, |
| 101 | stride=1, |
| 102 | padding=0) |
| 103 | self.k = torch.nn.Conv2d(in_channels, |
| 104 | in_channels, |
| 105 | kernel_size=1, |
| 106 | stride=1, |
| 107 | padding=0) |
| 108 | self.v = torch.nn.Conv2d(in_channels, |
| 109 | in_channels, |
| 110 | kernel_size=1, |
| 111 | stride=1, |
| 112 | padding=0) |
| 113 | self.proj_out = torch.nn.Conv2d(in_channels, |
| 114 | in_channels, |
| 115 | kernel_size=1, |
| 116 | stride=1, |
| 117 | padding=0) |
| 118 | |
| 119 | def forward(self, x): |
| 120 | h_ = x |