l5kit.environment.gym_metric_set module¶

class l5kit.environment.gym_metric_set.CLEMetricSet(metric_prefix: str = 'CLE')¶

Bases: l5kit.cle.metric_set.L5MetricSet

This class is responsible for computing a set of metric parametrization for the L5Kit Gym-compatible environment. The metrics in this class comprise the closed loop evaluation metrics of L5Kit.

Parameters: metric_prefix – this is a prefix that will identify the metric set being used.

build_composite_metrics() → List[l5kit.cle.composite_metrics.SupportsCompositeMetricCompute]¶: Return a list of composite metrics that should be computed. Composite metrics are metrics that depend upon metrics and validator results.

build_metrics() → List[l5kit.cle.metrics.SupportsMetricCompute]¶: Returns a list of metrics that will be computed.

build_validators() → List[l5kit.cle.validators.SupportsMetricValidate]¶: Returns a list of validators that will operate on the computed metrics.

evaluator: l5kit.cle.closed_loop_evaluator.ClosedLoopEvaluator¶

get_validator_interventions() → List[str]¶: Returns a list of validators that are considered an intervention.

metric_prefix: str¶: The prefix that will identify this metric

class l5kit.environment.gym_metric_set.L2DisplacementYawMetricSet(metric_prefix: str = 'L2DisplacementYaw')¶

Bases: l5kit.cle.metric_set.L5MetricSet

This class is responsible for computing a set of metric parametrization for the L5Kit Gym-compatible environment. The metrics in this class comprise L2 displacement error for the (x, y) coordinates and closest-angle error for the yaw.

Parameters: metric_prefix – this is a prefix that will identify the metric set being used.

build_metrics() → List[l5kit.cle.metrics.SupportsMetricCompute]¶: Returns a list of metrics that will be computed.

evaluator: l5kit.cle.closed_loop_evaluator.ClosedLoopEvaluator¶

metric_prefix: str¶: The prefix that will identify this metric