Closed charSLee013 closed 2 days ago
This PR addresses the issue of redundant transposition operations:
The original DVAE forward method included a transpose operation:
dec_out = self.out_conv( self.decoder( input=vq_feats.transpose_(1, 2), <- here ).transpose_(1, 2), <- and here )
This transpose was then repeated in the DVAEDecoder forward method:
def forward(self, input: torch.Tensor, conditioning=None) -> torch.Tensor: # B, T, C x = input.transpose_(1, 2) <- again ... return x.transpose_(1, 2) <- also extraneous transpose
Content:
This PR addresses the issue of redundant transposition operations:
The original DVAE forward method included a transpose operation:
This transpose was then repeated in the DVAEDecoder forward method: