MCPcopy Create free account
hub / github.com/pytorch/tutorials / forward

Method forward

intermediate_source/mnist_train_nas.py:93–95  ·  view source on GitHub ↗
(self, x)

Source from the content-addressed store, hash-verified

91 self.model = nn.Sequential(*layers) # No need to use Relu for the last layer
92
93 def forward(self, x):
94 x = self.model(x)
95 return F.log_softmax(x, dim=1)
96
97 def training_step(self, batch, batch_idx):
98 x, y = batch

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected