Reference for ultralytics/nn/backends/executorch.py#

class ExecuTorchBackend(BaseBackend):
    """Meta ExecuTorch inference backend for on-device deployment.

    Loads and runs inference with Meta ExecuTorch models (.pte files) using the ExecuTorch runtime. Supports both
    standalone .pte files and directory-based model packages with metadata.
    """

def forward(self, im: torch.Tensor) -> list:
    """Run inference using the ExecuTorch runtime.

    Args:
        im (torch.Tensor): Input image tensor in BCHW format, normalized to [0, 1].

    Returns:
        (list): Model predictions as a list of ExecuTorch output values.
    """
    return self.model.execute([im])

def load_model(self, weight: str | Path) -> None:
    """Load an ExecuTorch model from a .pte file or directory.

    Args:
        weight (str | Path): Path to the .pte model file or directory containing the model.
    """
    LOGGER.info(f"Loading {weight} for ExecuTorch inference...")
    check_executorch_requirements()

    from executorch.runtime import Runtime

    w = Path(weight)
    program = Runtime.get().load_program(str(next(w.rglob("*.pte")) if w.is_dir() else w))
    self.model = program.load_method("forward")
    self.apply_metadata(self.read_metadata(w))