(self, x)
| 14 | self.BN = BN(half2) |
| 15 | |
| 16 | def forward(self, x): |
| 17 | split = torch.split(x, self.half, 1) |
| 18 | out1 = self.IN(split[0].contiguous()) |
| 19 | out2 = self.BN(split[1].contiguous()) |
| 20 | out = torch.cat((out1, out2), 1) |
| 21 | return out |
| 22 | |
| 23 | |
| 24 | def get_normalization(num_features, bn_type=None, **kwargs): |