anomalib.deploy.optimize

Utilities for optimization and OpenVINO conversion.

Module Contents

Functions

get_model_metadata(→ Dict[str, torch.Tensor])

Get meta data related to normalization from model.

export_convert(model, input_size, onnx_path, export_path)

Export the model to onnx format and convert to OpenVINO IR.
anomalib.deploy.optimize.get_model_metadata(model: anomalib.models.components.AnomalyModule) → Dict[str, torch.Tensor][source]

Get meta data related to normalization from model.

Parameters

model (AnomalyModule) – Anomaly model which contains metadata related to normalization.

Returns

metadata

Return type

Dict[str, Tensor]

anomalib.deploy.optimize.export_convert(model: anomalib.models.components.AnomalyModule, input_size: Union[List[int], Tuple[int, int]], onnx_path: Union[str, pathlib.Path], export_path: Union[str, pathlib.Path])[source]

Export the model to onnx format and convert to OpenVINO IR.

Parameters

  • model (AnomalyModule) – Model to convert.

  • input_size (Union[List[int], Tuple[int, int]]) – Image size used as the input for onnx converter.

  • onnx_path (Union[str, Path]) – Path to output onnx model.

  • export_path (Union[str, Path]) – Path to exported OpenVINO IR.