Module: tflite_support.task.processor

TensorFlow Lite Task Library's processor module.

This module contains classes related to the pre-processing and post-processing steps of the Task Library.


class BertCluAnnotationOptions: Options for Bert CLU Annotator processor.

class BoundingBox: An integer bounding box, axis aligned.

class CategoricalSlot: Represents a categorical slot whose values are within a finite set.

class Category: A classification category.

class ClassificationOptions: Options for classification processor.

class ClassificationResult: Contains one set of results per classifier head.

class Classifications: List of predicted classes (aka labels) for a given classifier head.

class CluRequest: The input to CLU (Conversational Language Understanding).

class CluResponse: The output of CLU.

class ColoredLabel: Defines a label associated with an RGB color, for display purposes.

class ConfidenceMask: 2D-array representing the confidence mask in row major order.

class Detection: Represents one detected object in the object detector's results.

class DetectionOptions: Options for object detection processor.

class DetectionResult: Represents the list of detected objects.

class Embedding: Result produced by one of the embedder model output layers.

class EmbeddingOptions: Options for embedding processor.

class EmbeddingResult: Embeddings produced by the Embedder.

class FeatureVector: A dense feature vector.

class Mention: A single mention result.

class MentionedSlot: Non-categorical slot whose values are open text extracted from the input text.

class NearestNeighbor: A single nearest neighbor.

class OutputType: An enumeration.

class Pos: Position information of the answer relative to context.

class QaAnswer: Represents the Answer to BertQuestionAnswerer.

class QuestionAnswererResult: The list of probable answers generated by BertQuestionAnswerer.

class SearchOptions: Options for search processor.

class SearchResult: Results from a search as a list of nearest neigbors.

class Segmentation: Represents one Segmentation object in the image segmenter's results.

class SegmentationOptions: Options for segmentation processor.

class SegmentationResult: Results of performing image segmentation.