otx.algorithms.segmentation.adapters.openvino#

OTX Adapters - openvino.

Classes

`OpenVINOSegmentationTask`(task_environment)	Task implementation for Segmentation using OpenVINO backend.
`OpenVINOSegmentationInferencer`(hparams, ...)	Inferencer implementation for Segmentation using OpenVINO backend.

class otx.algorithms.segmentation.adapters.openvino.OpenVINOSegmentationInferencer(hparams: SegmentationConfig, label_schema: LabelSchemaEntity, model_file: str | bytes, weight_file: str | bytes | None = None, device: str = 'CPU', num_requests: int = 1)[source]#

Inferencer implementation for Segmentation using OpenVINO backend.

Parameters:

hparams – Hyper parameters that the model should use.
label_schema – LabelSchemaEntity that was used during model training.
model_file – Path to model to load, .xml, .bin or .onnx file.
device – Device to run inference on, such as CPU, GPU or MYRIAD. Defaults to “CPU”.
num_requests – Maximum number of requests that the inferencer can make. Good value is the number of available cores. Defaults to 1.

enqueue_prediction(image: ndarray, id: int, result_handler: Any) → None[source]#: Runs async inference.

predict(image: ndarray) → Tuple[ImageResultWithSoftPrediction, AnnotationSceneEntity][source]#: Perform a prediction for a given input image.

class otx.algorithms.segmentation.adapters.openvino.OpenVINOSegmentationTask(task_environment: TaskEnvironment)[source]#

Task implementation for Segmentation using OpenVINO backend.

deploy(output_model: ModelEntity) → None[source]#: Deploy function of OpenVINOSegmentationTask.

evaluate(output_resultset: ResultSetEntity, evaluation_metric: str | None = None)[source]#: Evaluate function of OpenVINOSegmentationTask.

infer(dataset: DatasetEntity, inference_parameters: InferenceParameters | None = None) → DatasetEntity[source]#: Infer function of OpenVINOSegmentationTask.

load_inferencer() → OpenVINOSegmentationInferencer[source]#: load_inferencer function of OpenVINO Segmentation Task.

optimize(optimization_type: OptimizationType, dataset: DatasetEntity, output_model: ModelEntity, optimization_parameters: OptimizationParameters | None = None)[source]#: Optimize function of OpenVINOSegmentationTask.

property avg_time_per_image: float | None#: Average inference time per image.