keras-team/keras · error · ValueError

Argument `specificity` must be in the range [0, 1]. Received

Error message

Argument `specificity` must be in the range [0, 1]. Received: specificity={specificity}

What it means

Raised in the constructor of keras.metrics.SpecificityAtSpecificity when the specificity argument falls outside [0, 1]. Specificity is a probability-like quantity (true negative rate), so Keros rejects out-of-range values immediately at construction time.

Source

Thrown at keras/src/metrics/confusion_metrics.py:743

    ```python
    model.compile(
        optimizer='sgd',
        loss='binary_crossentropy',
        metrics=[keras.metrics.SensitivityAtSpecificity(specificity=0.5)])
    ```
    """

    def __init__(
        self,
        specificity,
        num_thresholds=200,
        class_id=None,
        name=None,
        dtype=None,
    ):
        if specificity < 0 or specificity > 1:
            raise ValueError(
                "Argument `specificity` must be in the range [0, 1]. "
                f"Received: specificity={specificity}"
            )
        self.specificity = specificity
        self.num_thresholds = num_thresholds
        super().__init__(
            specificity,
            num_thresholds=num_thresholds,
            class_id=class_id,
            name=name,
            dtype=dtype,
        )

    def result(self):
        sensitivities = ops.divide_no_nan(
            self.true_positives,
            ops.add(self.true_positives, self.false_negatives),
        )

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Pass a fraction in [0, 1], e.g. 0.9 instead of 90.
2. Validate computed values: assert 0 <= v <= 1.
3. Clamp drifting floats with min(max(v, 0.0), 1.0).

Example fix

# before
m = keras.metrics.SpecificityAtSpecificity(specificity=90)

# after
m = keras.metrics.SpecificityAtSpecificity(specificity=0.9)

if not (0.0 <= specificity <= 1.0):
    raise ValueError(f'specificity must be in [0,1], got {specificity}')

def is_probability(v) -> bool:
    return isinstance(v, (int, float)) and 0.0 <= v <= 1.0

When it happens

Trigger: keras.metrics.SpecificityAtSpecificity(specificity=1.2) or (-0.1); passing a percentage like 90 instead of 0.9; unclamped computed values.

Common situations: Percent-vs-fraction confusion; values from unnormalized expressions; floating-point drift slightly above 1.0.

Related errors

• Argument `sensitivity` must be in the range [0, 1]. Received
• Argument `recall` must be in the range [0, 1]. Received: rec
• Argument `precision` must be in the range [0, 1]. Received:
• Invalid `beta` argument value. It should be > 0. Received: b
• Invalid `threshold` argument value. It should verify 0 < thr

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/a22b04b56403b78f. Report an issue: GitHub.