def forward()

in sam2/modeling/backbones/image_encoder.py [0:0]

• 28 lines of code
• 6 McCabe index (conditional complexity)

    def forward(self, xs: List[torch.Tensor]):
        out = [None] * len(self.convs)
        pos = [None] * len(self.convs)
        assert len(xs) == len(self.convs)
        # fpn forward pass
        # see https://github.com/facebookresearch/detectron2/blob/main/detectron2/modeling/backbone/fpn.py
        prev_features = None
        # forward in top-down order (from low to high resolution)
        n = len(self.convs) - 1
        for i in range(n, -1, -1):
            x = xs[i]
            lateral_features = self.convs[n - i](x)
            if i in self.fpn_top_down_levels and prev_features is not None:
                top_down_features = F.interpolate(
                    prev_features.to(dtype=torch.float32),
                    scale_factor=2.0,
                    mode=self.fpn_interp_model,
                    align_corners=(
                        None if self.fpn_interp_model == "nearest" else False
                    ),
                    antialias=False,
                )
                prev_features = lateral_features + top_down_features
                if self.fuse_type == "avg":
                    prev_features /= 2
            else:
                prev_features = lateral_features
            x_out = prev_features
            out[i] = x_out
            pos[i] = self.position_encoding(x_out).to(x_out.dtype)

        return out, pos