Introducing LiteRT: Google's high-performance runtime for on-device AI, formerly known as TensorFlow Lite. Learn more

tflite_support.metadata.MetadataDisplayer

Displays metadata and associated file info in human-readable format.

tflite_support.metadata.MetadataDisplayer(
    model_buffer, metadata_buffer, associated_file_list
)

Args
`model_buffer`	valid buffer of the model file.
`metadata_buffer`	valid buffer of the metadata file.
`associated_file_list`	list of associate files in the model file.

Methods

get_associated_file_buffer(
    filename
)

Get the specified associated file content in bytearray.

Args
`filename`	name of the file to be extracted.

Returns
The file content in bytearray.

Raises
`ValueError`	if the file does not exist in the model.

get_metadata_buffer()

Get the metadata buffer in bytearray out from the model.

get_metadata_json()

Converts the metadata into a json string.

get_packed_associated_file_list()

Returns a list of associated files that are packed in the model.

Returns
A name list of associated files.

@classmethod
with_model_buffer(
    model_buffer
)

Creates a MetadataDisplayer object for a file buffer.

Args
`model_buffer`	TensorFlow Lite model buffer in bytearray.

Returns
MetadataDisplayer object.

@classmethod
with_model_file(
    model_file
)

Creates a MetadataDisplayer object for the model file.

Args
`model_file`	valid path to a TensorFlow Lite model file.

Returns
MetadataDisplayer object.

Raises
`IOError`	File not found.
`ValueError`	The model does not have metadata.