MCPcopy Create free account
hub / github.com/VisionXLab/OF-Diff / forward

Method forward

ldm/modules/diffusionmodules/openaimodel.py:244–253  ·  view source on GitHub ↗

Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb: an [N x emb_channels] Tensor of timestep embeddings. :return: an [N x C x ...] Tensor of outputs.

(self, x, emb)

Source from the content-addressed store, hash-verified

242 self.skip_connection = conv_nd(dims, channels, self.out_channels, 1)
243
244 def forward(self, x, emb):
245 """
246 Apply the block to a Tensor, conditioned on a timestep embedding.
247 :param x: an [N x C x ...] Tensor of features.
248 :param emb: an [N x emb_channels] Tensor of timestep embeddings.
249 :return: an [N x C x ...] Tensor of outputs.
250 """
251 return checkpoint(
252 self._forward, (x, emb), self.parameters(), self.use_checkpoint
253 )
254
255
256 def _forward(self, x, emb):

Callers

nothing calls this directly

Calls 1

checkpointFunction · 0.90

Tested by

no test coverage detected