otx.algorithms.anomaly.tasks#

Initialization of OTX Anomalib.

Classes

`InferenceTask`(task_environment[, output_path])	Base Anomaly Task.
`TrainingTask`(task_environment[, output_path])	Base Anomaly Task.
`NNCFTask`(task_environment, **kwargs)	Base Anomaly Task.
`OpenVINOTask`(task_environment)	OpenVINO inference task.

class otx.algorithms.anomaly.tasks.InferenceTask(task_environment: TaskEnvironment, output_path: str | None = None)[source]#

Bases: IInferenceTask, IEvaluationTask, IExportTask, IUnload

Base Anomaly Task.

Train, Infer, Export, Optimize and Deploy an Anomaly Classification Task.

Parameters:

task_environment (TaskEnvironment) – OTX Task environment.
output_path (Optional[str]) – output path where task output are saved.

cancel_training() → None[source]#

Cancel the training after_batch_end.

This terminates the training; however validation is still performed.

cleanup() → None[source]#: Clean up work directory.

evaluate(output_resultset: ResultSetEntity, evaluation_metric: str | None = None) → None[source]#

Evaluate the performance on a result set.

Parameters:

output_resultset (ResultSetEntity) – Result Set from which the performance is evaluated.
evaluation_metric (Optional[str], optional) – Evaluation metric. Defaults to None. Instead, metric is chosen depending on the task type.

export(export_type: ExportType, output_model: ModelEntity, precision: ModelPrecision = ModelPrecision.FP32, dump_features: bool = False) → None[source]#

Export model to OpenVINO IR.

Parameters:

export_type (ExportType) – Export type should be ExportType.OPENVINO
output_model (ModelEntity) – The model entity in which to write the OpenVINO IR data
precision (bool) – Output model weights and inference precision
dump_features (bool) – Flag to return “feature_vector” and “saliency_map”.

Raises:

Exception – If export_type is not ExportType.OPENVINO

get_config() → DictConfig | ListConfig[source]#

Get Anomalib Config from task environment.

Returns:: Anomalib config.
Return type:: Union[DictConfig, ListConfig]

infer(dataset: DatasetEntity, inference_parameters: InferenceParameters) → DatasetEntity[source]#

Perform inference on a dataset.

Parameters:

dataset (DatasetEntity) – Dataset to infer.
inference_parameters (InferenceParameters) – Inference parameters.

Returns:

Output dataset with predictions.

Return type:

DatasetEntity

load_model(otx_model: ModelEntity | None) → AnomalyModule[source]#

Create and Load Anomalib Module from OTX Model.

This method checks if the task environment has a saved OTX Model, and creates one. If the OTX model already exists, it returns the the model with the saved weights.

Parameters:

otx_model (Optional[ModelEntity]) – OTX Model from the task environment.

Returns:

Anomalib: classification or segmentation model with/without weights.

Return type:

AnomalyModule

model_info() → Dict[source]#

Return model info to save the model weights.

Returns:: Model info.
Return type:: Dict

save_model(output_model: ModelEntity) → None[source]#

Save the model after training is completed.

Parameters:: output_model (ModelEntity) – Output model onto which the weights are saved.

unload() → None[source]#: Unload the task.

class otx.algorithms.anomaly.tasks.NNCFTask(task_environment: TaskEnvironment, **kwargs)[source]#

Bases: InferenceTask, IOptimizationTask

Base Anomaly Task.

Task for compressing models using NNCF.

Parameters:

task_environment (TaskEnvironment) – OTX Task environment.
**kwargs – Addition keyword arguments.

load_model(otx_model: ModelEntity | None) → AnomalyModule[source]#

Create and Load Anomalib Module from OTX Model.

This method checks if the task environment has a saved OTX Model, and creates one. If the OTX model already exists, it returns the the model with the saved weights.

Parameters:

otx_model (Optional[ModelEntity]) – OTX Model from the task environment.

Returns:

Anomalib: classification or segmentation model with/without weights.

Return type:

AnomalyModule

model_info() → Dict[source]#

Return model info to save the model weights.

Returns:: Model info.
Return type:: Dict

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

Train the anomaly classification model.

Parameters:

optimization_type (OptimizationType) – Type of optimization.
dataset (DatasetEntity) – Input dataset.
output_model (ModelEntity) – Output model to save the model weights.
optimization_parameters (OptimizationParameters) – Training parameters

class otx.algorithms.anomaly.tasks.OpenVINOTask(task_environment: TaskEnvironment)[source]#

Bases: IInferenceTask, IEvaluationTask, IOptimizationTask, IDeploymentTask

OpenVINO inference task.

Parameters:: task_environment (TaskEnvironment) – task environment of the trained anomaly model

deploy(output_model: ModelEntity) → None[source]#

Exports the weights from output_model along with exportable code.

Parameters:: output_model (ModelEntity) – Model with openvino.xml and .bin keys
Raises:: Exception – If task_environment.model is None

evaluate(output_resultset: ResultSetEntity, evaluation_metric: str | None = None)[source]#

Evaluate the performance of the model.

Parameters:

output_resultset (ResultSetEntity) – Result set storing ground truth and predicted dataset.
evaluation_metric (Optional[str], optional) – Evaluation metric. Defaults to None.

get_config() → Dict[source]#

Get Anomalib Config from task environment.

Returns:: Anomalib config
Return type:: ADDict

get_metadata() → Dict[source]#: Get Meta Data.

get_openvino_model() → AnomalyDetection[source]#

Create the OpenVINO inferencer object.

Returns:: AnomalyDetection model

infer(dataset: DatasetEntity, inference_parameters: InferenceParameters) → DatasetEntity[source]#

Perform Inference.

Parameters:

dataset (DatasetEntity) – Inference dataset
inference_parameters (InferenceParameters) – Inference parameters.

Returns:

Output dataset storing inference predictions.

Return type:

DatasetEntity

optimize(optimization_type: OptimizationType, dataset: DatasetEntity, output_model: ModelEntity, optimization_parameters: OptimizationParameters | None)[source]#

Optimize the model.

Parameters:

optimization_type (OptimizationType) – Type of optimization [POT or NNCF]
dataset (DatasetEntity) – Input Dataset.
output_model (ModelEntity) – Output model.
optimization_parameters (Optional[OptimizationParameters]) – Optimization parameters.

Raises:

ValueError – When the optimization type is not POT, which is the only support type at the moment.

class otx.algorithms.anomaly.tasks.TrainingTask(task_environment: TaskEnvironment, output_path: str | None = None)[source]#

Bases: InferenceTask, ITrainingTask

Base Anomaly Task.

Train, Infer, Export, Optimize and Deploy an Anomaly Classification Task.

Parameters:

task_environment (TaskEnvironment) – OTX Task environment.
output_path (Optional[str]) – output path where task output are saved.

load_model(otx_model: ModelEntity | None) → AnomalyModule[source]#

Create and Load Anomalib Module from OTX Model.

This method checks if the task environment has a saved OTX Model, and creates one. If the OTX model already exists, it returns the the model with the saved weights.

Parameters:

otx_model (Optional[ModelEntity]) – OTX Model from the task environment.

Returns:

Anomalib: classification or segmentation model with/without weights.

Return type:

AnomalyModule

train(dataset: DatasetEntity, output_model: ModelEntity, train_parameters: TrainParameters, seed: int | None = None, deterministic: bool = False) → None[source]#

Train the anomaly classification model.

Parameters:

dataset (DatasetEntity) – Input dataset.
output_model (ModelEntity) – Output model to save the model weights.
train_parameters (TrainParameters) – Training parameters
seed (Optional[int]) – Setting seed to a value other than 0
deterministic (bool) – Setting PytorchLightning trainer’s deterministic flag.