MCPcopy Create free account
hub / github.com/Royalvice/DocDiff / forward

Method forward

model/DocDiff.py:202–206  ·  view source on GitHub ↗
(self, x: torch.Tensor, t: torch.Tensor)

Source from the content-addressed store, hash-verified

200 self.conv = nn.Conv2d(n_channels, n_channels, (3, 3), (2, 2), (1, 1))
201
202 def forward(self, x: torch.Tensor, t: torch.Tensor):
203 # `t` is not used, but it's kept in the arguments because for the attention layer function signature
204 # to match with `ResidualBlock`.
205 _ = t
206 return self.conv(x)
207
208
209class UNet(nn.Module):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected