MCPcopy Create free account
hub / github.com/OpenDriveLab/ReSim / forward

Method forward

sat/sgm/models/autoencoder.py:620–630  ·  view source on GitHub ↗
(
        self,
        x: torch.Tensor,
        input_cp: bool = False,
        latent_cp: bool = False,
        output_cp: bool = False,
        **additional_decode_kwargs,
    )

Source from the content-addressed store, hash-verified

618 return x
619
620 def forward(
621 self,
622 x: torch.Tensor,
623 input_cp: bool = False,
624 latent_cp: bool = False,
625 output_cp: bool = False,
626 **additional_decode_kwargs,
627 ) -> Tuple[torch.Tensor, torch.Tensor, dict]:
628 z, reg_log = self.encode(x, return_reg_log=True, input_cp=input_cp, output_cp=latent_cp)
629 dec = self.decode(z, input_cp=latent_cp, output_cp=output_cp, **additional_decode_kwargs)
630 return z, dec, reg_log

Callers

nothing calls this directly

Calls 2

encodeMethod · 0.95
decodeMethod · 0.95

Tested by

no test coverage detected