(self, x: torch.Tensor)
| 38 | ])) |
| 39 | |
| 40 | def forward(self, x: torch.Tensor): |
| 41 | identity = x |
| 42 | |
| 43 | out = self.relu(self.bn1(self.conv1(x))) |
| 44 | out = self.relu(self.bn2(self.conv2(out))) |
| 45 | out = self.avgpool(out) |
| 46 | out = self.bn3(self.conv3(out)) |
| 47 | |
| 48 | if self.downsample is not None: |
| 49 | identity = self.downsample(x) |
| 50 | |
| 51 | out += identity |
| 52 | out = self.relu(out) |
| 53 | return out |
| 54 | |
| 55 | |
| 56 | class AttentionPool2d(nn.Module): |
nothing calls this directly
no outgoing calls
no test coverage detected