nicetoolbox.configs.video_runtime_config

Runtime configuration for processing a single video. Created by Configuration factory, discarded after video processing.

Classes

SequenceRuntimeConfig

Immutable configuration context for processing a single video.
class nicetoolbox.configs.video_runtime_config.SequenceRuntimeConfig(*, log_level: LoggingLevelEnum, log_file: Path, dataset_name: str, video_config: RunConfigVideo, dataset_properties: DatasetConfig, io: DetectorsRunIO, machine: MachineSpecificConfig, detectors_config: DetectorsConfig, predictions_mapping: PredictionsMappingConfig, algorithms: List[str], all_camera_names: List[str])[source]

Immutable configuration context for processing a single video.

Created by Configuration.iter_sequence_contexts(), holds all resolved configuration needed for one video. Discarded after processing.

All placeholders (except <cur_component_name> and <cur_algorithm_name> in IO paths) are fully resolved at construction time.

Note: frozen=True only prevents reassignment of top-level attributes. Nested models are mutable but should be treated as immutable by convention.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

get_detector_config(algorithm_name: str) → BaseModel[source]

Get the pre-resolved configuration for a detector.

Parameters:

algorithm_name – Name of the algorithm (e.g., ‘hrnetw48’, ‘velocity_body’)

Returns:

Resolved configuration dict ready for detector initialization. Includes the injected ‘visualize’ flag.

Raises:

KeyError – If algorithm was not in the selected algorithms for this video

get_detector_folder(component: str, algorithm: str, folder_type: str) → Path[source]

Get resolved detector-specific folder path.

The IO paths contain <cur_component_name> and <cur_algorithm_name> placeholders that are resolved here based on the specific detector.

Parameters:

  • component – Component name (e.g., ‘body_joints’)

  • algorithm – Algorithm name (e.g., ‘hrnetw48’)

  • folder_type – One of ‘output’, ‘visualization’, ‘additional’, ‘run_config’, ‘result’

Returns:

Resolved Path to the requested folder

model_config: ClassVar[ConfigDict] = {'extra': 'forbid', 'frozen': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].