open-mmlab/mmdetection · error · KeyError

metric item "{metric_item}" is not supported

Error message

metric item "{metric_item}" is not supported

What it means

OV-COCOMetric validates self.metric_items against the fixed set of coco_metric_names keys (mAP, mAP_50, ..., AR_l@1000). Any item not in that table raises this KeyError, because the metric cannot compute an unknown statistic.

Source

Thrown at mmdet/evaluation/metrics/ov_coco_metric.py:138

            coco_metric_names = {
                'mAP': 0,
                'mAP_50': 1,
                'mAP_75': 2,
                'mAP_s': 3,
                'mAP_m': 4,
                'mAP_l': 5,
                'AR@100': 6,
                'AR@300': 7,
                'AR@1000': 8,
                'AR_s@1000': 9,
                'AR_m@1000': 10,
                'AR_l@1000': 11
            }
            metric_items = self.metric_items
            if metric_items is not None:
                for metric_item in metric_items:
                    if metric_item not in coco_metric_names:
                        raise KeyError(
                            f'metric item "{metric_item}" is not supported')

            if metric == 'proposal':
                coco_eval.params.useCats = 0
                coco_eval.evaluate()
                coco_eval.accumulate()
                coco_eval.summarize()
                if metric_items is None:
                    metric_items = [
                        'AR@100', 'AR@300', 'AR@1000', 'AR_s@1000',
                        'AR_m@1000', 'AR_l@1000'
                    ]

                for item in metric_items:
                    val = float(
                        f'{coco_eval.stats[coco_metric_names[item]]:.3f}')
                    eval_results[item] = val
            else:

View on GitHub (pinned to cfd5d3a985)

Solutions

1. Use only supported items: mAP, mAP_50, mAP_75, mAP_s, mAP_m, mAP_l, AR@100, AR@300, AR@1000, AR_s@1000, AR_m@1000, AR_l@1000
2. Leave metric_items=None to get the default set (mAP, mAP_50, mAP_75, mAP_s, mAP_m, mAP_l)
3. Check the coco_metric_names dict in the source for the exact accepted keys of your mmdet version

Example fix

# before
val_evaluator = dict(type='OVCocoMetric', metric='bbox', metric_items=['AP50', 'AP75'])
# after
val_evaluator = dict(type='OVCocoMetric', metric='bbox', metric_items=['mAP_50', 'mAP_75'])

SUPPORTED = {'mAP','mAP_50','mAP_75','mAP_s','mAP_m','mAP_l','AR@100','AR@300','AR@1000','AR_s@1000','AR_m@1000','AR_l@1000'}
bad = set(metric_items or []) - SUPPORTED
assert not bad, f'unsupported metric_items: {bad}'

def is_valid_metric_items(items) -> bool:
    SUPPORTED = {'mAP','mAP_50','mAP_75','mAP_s','mAP_m','mAP_l','AR@100','AR@300','AR@1000','AR_s@1000','AR_m@1000','AR_l@1000'}
    return items is None or all(i in SUPPORTED for i in items)

try:
    evaluator.evaluate(results)
except KeyError as e:
    raise ValueError(f'fix metric_items in config: {e}') from e

When it happens

Trigger: Passing metric_items=['mAP@0.5:0.95', 'AP50', 'AR@100'] or other non-standard names to OVCocoMetric; misspelling a supported item like 'mAP_50'.

Common situations: Copy-pasting metric_items strings from pycocotools logs or papers instead of the supported keys; version changes renaming items; mixing Pascal VOC item names into a COCO evaluator.

Related errors

• {metric} is not in results
• metric item "{metric_item}" is not supported
• batch_size should be a positive integer value, but got batch
• img_border_value must be float or tuple with 3 elements.
• metric must be a list or a str.

AI-assisted analysis of open-mmlab/mmdetection@cfd5d3a985 (2026-08-27). Data as JSON: /api/errors/c153a5d9d1ebf84f. Report an issue: GitHub.