metrics.metric.Metric Class Reference

Public Member Functions
	reset_state (self)
	update_state (self, outputs, expecteds)
	result (self)

Detailed Description

Abstract base class for all metrics.

Definition at line 1 of file metric.py.

Member Function Documentation

reset_state()

metrics.metric.Metric.reset_state

(

self

)

Reset the metric's state.

Reimplemented in metrics.categorical_accuracy.CategoricalAccuracy.

Definition at line 5 of file metric.py.

    def reset_state(self):
        """
        Reset the metric's state.
        """
        raise NotImplementedError
 

result()

metrics.metric.Metric.result

(

self

)

Compute and return the final metric value.
Returns:
    float: Metric value.

Reimplemented in metrics.categorical_accuracy.CategoricalAccuracy.

Definition at line 20 of file metric.py.

    def result(self):
        """
        Compute and return the final metric value.
        Returns:
            float: Metric value.
        """
        raise NotImplementedError

update_state()

metrics.metric.Metric.update_state	(		self,
			outputs,
			expecteds
	)

Update the metric's state based on the outputs and expecteds.
Args:
    outputs (np.ndarray): Model outputs.
    expecteds (np.ndarray): Expected ground truth values.

Reimplemented in metrics.categorical_accuracy.CategoricalAccuracy.

Definition at line 11 of file metric.py.

    def update_state(self, outputs, expecteds):
        """
        Update the metric's state based on the outputs and expecteds.
        Args:
            outputs (np.ndarray): Model outputs.
            expecteds (np.ndarray): Expected ground truth values.
        """
        raise NotImplementedError
 

---

The documentation for this class was generated from the following file:

• runtime/onert/api/python/package/experimental/train/metrics/metric.py