MCPcopy Create free account
hub / github.com/MotrixLab/MotionDiffuse / forward

Method forward

text2motion/models/transformer.py:167–170  ·  view source on GitHub ↗
(self, x, emb)

Source from the content-addressed store, hash-verified

165 self.proj_out = StylizationBlock(latent_dim, time_embed_dim, dropout)
166
167 def forward(self, x, emb):
168 y = self.linear2(self.dropout(self.activation(self.linear1(x))))
169 y = x + self.proj_out(y, emb)
170 return y
171
172
173class LinearTemporalDiffusionTransformerDecoderLayer(nn.Module):

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected