Skip to content

Reference for ultralytics/nn/backends/axelera.py

Improvements

This page is sourced from https://github.com/ultralytics/ultralytics/blob/main/ultralytics/nn/backends/axelera.py. Have an improvement or example to add? Open a Pull Request — thank you! 🙏


Summary

class ultralytics.nn.backends.axelera.AxeleraBackend

AxeleraBackend()

Bases: BaseBackend

Axelera AI inference backend for Axelera Metis AI accelerators.

Loads compiled Axelera models (.axm files) and runs inference using the Axelera AI runtime SDK.

Methods

NameDescription
forwardRun inference on the Axelera hardware accelerator.
load_modelLoad an Axelera model from a directory containing a .axm file.
Source code in ultralytics/nn/backends/axelera.pyView on GitHub
class AxeleraBackend(BaseBackend):


method ultralytics.nn.backends.axelera.AxeleraBackend.forward

def forward(self, im: torch.Tensor) -> list

Run inference on the Axelera hardware accelerator.

Args

NameTypeDescriptionDefault
imtorch.TensorInput image tensor in BCHW format, normalized to [0, 1].required

Returns

TypeDescription
listModel predictions as a list of output arrays.
Source code in ultralytics/nn/backends/axelera.pyView on GitHub
def forward(self, im: torch.Tensor) -> list:
    """Run inference on the Axelera hardware accelerator.

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

    Returns:
        (list): Model predictions as a list of output arrays.
    """
    return self.model(im.cpu())


method ultralytics.nn.backends.axelera.AxeleraBackend.load_model

def load_model(self, weight: str | Path) -> None

Load an Axelera model from a directory containing a .axm file.

Args

NameTypeDescriptionDefault
weightstr | PathPath to the Axelera model directory containing the .axm binary.required
Source code in ultralytics/nn/backends/axelera.pyView on GitHub
def load_model(self, weight: str | Path) -> None:
    """Load an Axelera model from a directory containing a .axm file.

    Args:
        weight (str | Path): Path to the Axelera model directory containing the .axm binary.
    """
    try:
        from axelera.runtime import op
    except ImportError:
        check_requirements(
            "axelera-rt==1.6.0rc3",
            cmds="--extra-index-url https://software.axelera.ai/artifactory/api/pypi/axelera-pypi/simple",
        )

    from axelera.runtime import op

    w = Path(weight)
    found = next(w.rglob("*.axm"), None)
    if found is None:
        raise FileNotFoundError(f"No .axm file found in: {w}")

    self.model = op.load(str(found)).optimized()

    # Load metadata
    metadata_file = found.parent / "metadata.yaml"
    if metadata_file.exists():
        from ultralytics.utils import YAML

        self.apply_metadata(YAML.load(metadata_file))





📅 Created 15 days ago ✏️ Updated 15 days ago
Laughing-q