public sealed class ImageObjectDetectionEvaluationMetrics : IMessage<ImageObjectDetectionEvaluationMetrics>, IEquatable<ImageObjectDetectionEvaluationMetrics>, IDeepCloneable<ImageObjectDetectionEvaluationMetrics>, IBufferMessage, IMessage
Model evaluation metrics for image object detection problems.
Evaluates prediction quality of labeled bounding boxes.
public RepeatedField<BoundingBoxMetricsEntry> BoundingBoxMetricsEntries { get; }
Output only. The bounding boxes match metrics for each
Intersection-over-union threshold 0.05,0.10,...,0.95,0.96,0.97,0.98,0.99
and each label confidence threshold 0.05,0.10,...,0.95,0.96,0.97,0.98,0.99
pair.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eThis webpage details the \u003ccode\u003eImageObjectDetectionEvaluationMetrics\u003c/code\u003e class, which is used for evaluating the quality of labeled bounding boxes in image object detection problems.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eImageObjectDetectionEvaluationMetrics\u003c/code\u003e class is implemented as part of the \u003ccode\u003eGoogle.Cloud.AutoML.V1\u003c/code\u003e namespace, within the \u003ccode\u003eGoogle.Cloud.AutoML.V1.dll\u003c/code\u003e assembly, and has several inherited members from the base \u003ccode\u003eObject\u003c/code\u003e class.\u003c/p\u003e\n"],["\u003cp\u003eIt includes two constructors: a default constructor and one that takes another \u003ccode\u003eImageObjectDetectionEvaluationMetrics\u003c/code\u003e object as a parameter.\u003c/p\u003e\n"],["\u003cp\u003eKey properties include \u003ccode\u003eBoundingBoxMeanAveragePrecision\u003c/code\u003e, which calculates the mean average precision across all bounding box metric entries, \u003ccode\u003eBoundingBoxMetricsEntries\u003c/code\u003e to get the bounding box match metrics for various thresholds, and \u003ccode\u003eEvaluatedBoundingBoxCount\u003c/code\u003e to get the total number of ground truth bounding boxes.\u003c/p\u003e\n"],["\u003cp\u003eThe page also lists previous versions of this \u003ccode\u003eImageObjectDetectionEvaluationMetrics\u003c/code\u003e class, ranging from the latest \u003ccode\u003e3.4.0\u003c/code\u003e down to \u003ccode\u003e2.2.0\u003c/code\u003e.\u003c/p\u003e\n"]]],[],null,[]]
