MCPcopy Create free account
hub / github.com/HobbitLong/PyContrast / forward

Method forward

pycontrast/networks/resnest.py:355–373  ·  view source on GitHub ↗
(self, x)

Source from the content-addressed store, hash-verified

353 return nn.Sequential(*layers)
354
355 def forward(self, x):
356 x = self.conv1(x)
357 x = self.bn1(x)
358 x = self.relu(x)
359 x = self.maxpool(x)
360
361 x = self.layer1(x)
362 x = self.layer2(x)
363 x = self.layer3(x)
364 x = self.layer4(x)
365
366 x = self.avgpool(x)
367 x = torch.flatten(x, 1)
368 # disable for contrastive learning
369 # if self.drop:
370 # x = self.drop(x)
371 # x = self.fc(x)
372
373 return x
374
375
376def resnest50(pretrained=False, **kwargs):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected