[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-03-06。"],[[["This document guides you through understanding and viewing evaluation metrics produced by Data Labeling Service's evaluation jobs, which vary based on your machine learning model."],["Before viewing metrics, you must create and run an evaluation job, which includes human review and metric calculation, potentially taking more than a day for the first results."],["AI Platform Prediction allows comparison of mean average precision across different model versions over time, helping assess performance differences."],["You can also examine detailed metrics for a specific model version, including mean average precision, precision-recall curves, and confusion matrices, and filter these metrics by date or label."],["Depending on the classification type, you can view a side-by-side comparison of the model's predicted labels or bounding boxes against the ground truth labels, aiding in detailed analysis of performance."]]],[]]