Method forward

src/sharp/models/monodepth.py:194–227

Process image and return disparity and feature maps.

(self, image: torch.Tensor)

        self.sorting_monodepth = sorting_monodepth

    def forward(self, image: torch.Tensor) -> MonodepthOutput:
        """Process image and return disparity and feature maps."""
        inputs = self.monodepth_predictor.normalizer(image)
        encoder_output = self.monodepth_predictor.encoder(inputs)

        num_encoder_features = len(self.monodepth_predictor.encoder.dims_encoder)

        # NOTE: whether intermediate features are empty have already been decided
        # in monodepth_predictor during create_monodepth_dpt.
        encoder_features = encoder_output[:num_encoder_features]
        intermediate_features = encoder_output[num_encoder_features:]
        decoder_features = self.monodepth_predictor.decoder(encoder_features)
        disparity = self.monodepth_predictor.head(decoder_features)

        # We cannot use disparity.shape[1], otherwise the tracer will fail.
        if self.num_monodepth_layers == 2 and self.sorting_monodepth:
            first_layer_disparity = disparity.max(dim=1, keepdims=True).values
            second_layer_disparity = disparity.min(dim=1, keepdims=True).values
            disparity = torch.cat([first_layer_disparity, second_layer_disparity], dim=1)

        output_features = []
        if self.return_encoder_features:
            output_features.extend(encoder_features)

        if self.return_decoder_features:
            output_features.append(decoder_features)

        return MonodepthOutput(
            disparity=disparity,
            encoder_features=encoder_features,
            decoder_features=decoder_features,
            output_features=output_features,
            intermediate_features=intermediate_features,
        )

    def get_feature_dims(self) -> list[int]:
        """Return dimensions of output feature maps."""