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

Method forward

model/DocDiff.py:186–190  ·  view source on GitHub ↗
(self, x: torch.Tensor, t: torch.Tensor)

Source from the content-addressed store, hash-verified

184 self.conv = nn.ConvTranspose2d(n_channels, n_channels, (4, 4), (2, 2), (1, 1))
185
186 def forward(self, x: torch.Tensor, t: torch.Tensor):
187 # `t` is not used, but it's kept in the arguments because for the attention layer function signature
188 # to match with `ResidualBlock`.
189 _ = t
190 return self.conv(x)
191
192
193class Downsample(nn.Module):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected