tflite_support.metadata_writers.metadata_info.ClassificationTensorMd

A container for the classification tensor metadata information.

Inherits From: TensorMd

View aliases

Main aliases

tflite_support.metadata_writers.audio_classifier.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.audio_classifier.metadata_writer.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.bert_nl_classifier.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.bert_nl_classifier.metadata_writer.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.image_classifier.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.image_classifier.metadata_writer.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.image_segmenter.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.image_segmenter.metadata_writer.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.nl_classifier.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.nl_classifier.metadata_writer.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.object_detector.metadata_info.ClassificationTensorMd, tflite_support.metadata_writers.object_detector.metadata_writer.metadata_info.ClassificationTensorMd

tflite_support.metadata_writers.metadata_info.ClassificationTensorMd(
    name: Optional[str] = None,
    description: Optional[str] = None,
    label_files: Optional[List[LabelFileMd]] = None,
    tensor_type: Optional[_schema_fb.TensorType] = None,
    score_calibration_md: Optional[tflite_support.metadata_writers.metadata_info.ScoreCalibrationMd] = None,
    tensor_name: Optional[str] = None
)

Args
name	name of the tensor.
description	description of what the tensor is.
label_files	information of the label files 1 in the classification tensor.
tensor_type	data type of the tensor.
score_calibration_md	information of the score calibration files operation 2 in the classification tensor.
tensor_name	name of the corresponding tensor 3 in the TFLite model. It is used to locate the corresponding classification tensor and decide the order of the tensor metadata 4 when populating model metadata.

Attributes
label_files	information of the label files 1 in the classification tensor.
score_calibration_md	information of the score calibration operation 2 in the classification tensor.

Methods

create_metadata

View source

create_metadata() -> tflite_support.metadata_schema_py_generated.TensorMetadataT

Creates the classification tensor metadata based on the information.