Instructions
- •Read config.json for output_dir, target_accuracy
- •Run: uv run .agents/skills/eval/scripts/run.py
- •Outputs: output/eval_results.json with mAP, precision, recall, per-class breakdown
使用 mAP 指标及逐类别误差分析评估已训练 YOLO 模型的准确率,精准识别模型的失效案例,从而有针对性地优化模型性能。建议在模型训练完成后使用。
--- frontmattername: eval description: Evaluate trained YOLO model accuracy with mAP metrics and per-class error analysis. Identifies failure cases for targeted improvement. Use after training.