@spec build_from_buffer(binary(), Keyword.t()) ::
  %TFLiteElixir.FlatBufferModel{
    initialized: term(),
    minimum_runtime: term(),
    model: term()
  }
  | nif_error()

Build model from caller owned memory buffer

Note that buffer will be copied.

Build model from a given .tflite file

Note that if the tensorflow-lite library was compiled with TFLITE_MCU, then this function will always have return type nif_error().

Keyword parameters

• error_reporter: TFLiteElixir.ErrorReporter.

  Caller retains ownership of error_reporter and must ensure its lifetime is longer than the FlatBufferModel instance.

Raising version of build_from_file/2.

@spec error_reporter(%TFLiteElixir.FlatBufferModel{
  initialized: term(),
  minimum_runtime: term(),
  model: reference()
}) :: %TFLiteElixir.ErrorReporter{ref: term()} | {:error, String.t()}

Get the error report of the current FlatBuffer model.

@spec get_associated_file(binary(), [String.t()] | String.t()) ::
  %{required(String.t()) => String.t()} | String.t() | nif_error()

Get associated file(s) from a FlatBuffer model

@spec get_minimum_runtime(%TFLiteElixir.FlatBufferModel{
  initialized: term(),
  minimum_runtime: term(),
  model: term()
}) :: String.t() | nif_error()

Returns the minimum runtime version from the flatbuffer. This runtime version encodes the minimum required interpreter version to run the flatbuffer model. If the minimum version can't be determined, an empty string will be returned.

Note that the returned minimum version is a lower-bound but not a strict lower-bound; ops in the graph may not have an associated runtime version, in which case the actual required runtime might be greater than the reported minimum.

@spec initialized(%TFLiteElixir.FlatBufferModel{
  initialized: term(),
  minimum_runtime: term(),
  model: term()
}) :: bool() | nif_error()

Check whether current model has been initialized

@spec list_associated_files(binary()) :: [String.t()] | nif_error()

Get a list of all associated file(s) in a TFLite model file

@spec read_all_metadata(%TFLiteElixir.FlatBufferModel{
  initialized: term(),
  minimum_runtime: term(),
  model: term()
}) :: %{required(String.t()) => String.t()} | nif_error()

Return model metadata as a mapping of name & buffer strings.

See Metadata table in TFLite schema.

@spec verify_and_build_from_file(String.t(), Keyword.t()) ::
  %TFLiteElixir.FlatBufferModel{
    initialized: term(),
    minimum_runtime: term(),
    model: term()
  }
  | :invalid
  | {:error, String.t()}

Verifies whether the content of the file is legit, then builds a model based on the file.

Keyword parameters

• error_reporter: TFLiteElixir.ErrorReporter.

  Caller retains ownership of error_reporter and must ensure its lifetime is longer than the FlatBufferModel instance.

Returns :invalid in case of failure.