abidlabs-mean-iou

name	abidlabs-mean-iou
description	Compute abidlabs/mean_iou via the HuggingFace `evaluate` library. Use when the user has predictions + references and wants the canonical implementation of abidlabs/mean_iou.
metadata	{"skill_kind":"metric","source_lib":"huggingface-evaluate","hf_module":"abidlabs/mean_iou","source":"library_introspection"}

abidlabs-mean-iou

Metric abidlabs/mean_iou from the HuggingFace evaluate library.

When to invoke

User asks to compute abidlabs/mean_iou or wants HF evaluate's canonical version.

Recipe

import evaluate
metric = evaluate.load("abidlabs/mean_iou")
result = metric.compute(predictions=preds, references=refs)
print(result)

Don'ts

• Don't assume your in-house abidlabs/mean_iou matches HF — version conventions vary.
• Many evaluate metrics have task-specific arguments (average=, lang=, model_type=); read the metric card before reporting numbers.