tflite_support.metadata_writers.metadata_info.InputImageTensorMd

A container for input image tensor metadata information.

Inherits From: TensorMd

tflite_support.metadata_writers.metadata_info.InputImageTensorMd(
    name: Optional[str] = None,
    description: Optional[str] = None,
    norm_mean: Optional[List[float]] = None,
    norm_std: Optional[List[float]] = None,
    color_space_type: Optional[tflite_support.metadata_schema_py_generated.ColorSpaceType] = _metadata_fb.ColorSpaceType.UNKNOWN,
    tensor_type: Optional[_schema_fb.TensorType] = None
)

name name of the tensor.
description description of what the tensor is.
norm_mean the mean value used in tensor normalization 1.
norm_std the std value used in the tensor normalization 1. norm_mean and norm_std must have the same dimension.
color_space_type the color space type of the input image 2.
tensor_type data type of the tensor.

ValueError if norm_mean and norm_std have different dimensions.

norm_mean the mean value used in tensor normalization 1.
norm_std the std value used in the tensor normalization 1. norm_mean and norm_std must have the same dimension.
color_space_type the color space type of the input image 2.

Methods

create_metadata

View source

create_metadata() -> tflite_support.metadata_schema_py_generated.TensorMetadataT

Creates the input image metadata based on the information.

Returns
A Flatbuffers Python object of the input image metadata.