Hi there! Are you looking for the official Deno documentation? Try docs.deno.com for all your Deno learning needs.

XPSEvaluationMetrics

import type { XPSEvaluationMetrics } from "https://googleapis.deno.dev/v1/language:v2.ts";

Contains xPS-specific model evaluation metrics either for a single annotation spec (label), or for the model overall. Next tag: 18.

interface XPSEvaluationMetrics {
annotationSpecIdToken?: string;
category?: number;
evaluatedExampleCount?: number;
imageClassificationEvalMetrics?: XPSClassificationEvaluationMetrics;
imageObjectDetectionEvalMetrics?: XPSImageObjectDetectionEvaluationMetrics;
imageSegmentationEvalMetrics?: XPSImageSegmentationEvaluationMetrics;
label?: string;
regressionEvalMetrics?: XPSRegressionEvaluationMetrics;
tablesClassificationEvalMetrics?: XPSClassificationEvaluationMetrics;
tablesEvalMetrics?: XPSTablesEvaluationMetrics;
textClassificationEvalMetrics?: XPSClassificationEvaluationMetrics;
textExtractionEvalMetrics?: XPSTextExtractionEvaluationMetrics;
textSentimentEvalMetrics?: XPSTextSentimentEvaluationMetrics;
translationEvalMetrics?: XPSTranslationEvaluationMetrics;
videoActionRecognitionEvalMetrics?: XPSVideoActionRecognitionEvaluationMetrics;
videoClassificationEvalMetrics?: XPSClassificationEvaluationMetrics;
videoObjectTrackingEvalMetrics?: XPSVideoObjectTrackingEvaluationMetrics;
}

§Properties

§
annotationSpecIdToken?: string
[src]

The annotation_spec for which this evaluation metrics instance had been created. Empty iff this is an overall model evaluation (like Tables evaluation metrics), i.e. aggregated across all labels. The value comes from the input annotations in AnnotatedExample. For MVP product or for text sentiment models where annotation_spec_id_token is not available, set label instead.

§
category?: number
[src]

The integer category label for which this evaluation metric instance had been created. Valid categories are 0 or higher. Overall model evaluation should set this to negative values (rather than implicit zero). Only used for Image Segmentation (prefer to set annotation_spec_id_token instead). Note: uCAIP Image Segmentation should use annotation_spec_id_token.

§
evaluatedExampleCount?: number
[src]

The number of examples used to create this evaluation metrics instance.

§
imageClassificationEvalMetrics?: XPSClassificationEvaluationMetrics
[src]
§
imageObjectDetectionEvalMetrics?: XPSImageObjectDetectionEvaluationMetrics
[src]
§
imageSegmentationEvalMetrics?: XPSImageSegmentationEvaluationMetrics
[src]
§
label?: string
[src]

The label for which this evaluation metrics instance had been created. Empty iff this is an overall model evaluation (like Tables evaluation metrics), i.e. aggregated across all labels. The label maps to AnnotationSpec.display_name in Public API protos. Only used by MVP implementation and text sentiment FULL implementation.

§
tablesClassificationEvalMetrics?: XPSClassificationEvaluationMetrics
[src]
§
textClassificationEvalMetrics?: XPSClassificationEvaluationMetrics
[src]
§
textExtractionEvalMetrics?: XPSTextExtractionEvaluationMetrics
[src]
§
textSentimentEvalMetrics?: XPSTextSentimentEvaluationMetrics
[src]
§
videoActionRecognitionEvalMetrics?: XPSVideoActionRecognitionEvaluationMetrics
[src]
§
videoClassificationEvalMetrics?: XPSClassificationEvaluationMetrics
[src]
§
videoObjectTrackingEvalMetrics?: XPSVideoObjectTrackingEvaluationMetrics
[src]