Add ObjectDetector.getLabels() on the Web Tasks API - #6339
Open
a2105z wants to merge 1 commit into
Open
Conversation
Apps that swap custom detector models cannot list class names without hardcoding them, because detect() only returns labels for objects that fire. Read the labelmap already written onto DetectionLabelIdToTextCalculator from TFLite Model Metadata, matching ImageSegmenter.getLabels(). Fixes google-ai-edge#6294
This was referenced Aug 20, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
.tflitecannot show that model's class list without hardcoding it.detect()only returns categories for objects that actually fire.ObjectDetector.getLabels(): string[]on the Web Tasks API, matchingImageSegmenter.getLabels().DetectionLabelIdToTextCalculatorfrom TFLite Model Metadata. Returns[]when the model has no label file. Reloads whensetOptions()loads a new model.Fixes #6294
Test plan
object_detector_test.ts: empty labelmap, EfficientDet-style labels, labels refresh after model swapbazel test //mediapipe/tasks/web/vision/object_detector:object_detector_testObjectDetector.createFromOptionswith efficientdet_lite0, thendetector.getLabels()lists COCO classes (person, bicycle, car, …) without runningdetect().tflitethat has metadata labels, then swap models viasetOptions({ baseOptions: { modelAssetPath } })and confirmgetLabels()updates