Optimum documentation
Configuration classes for TFLite export
Configuration classes for TFLite export
Base classes
class optimum.exporters.tflite.TFLiteConfig
< source >( config: PretrainedConfig task: str batch_size: int = 1 sequence_length: typing.Optional[int] = None num_choices: typing.Optional[int] = None width: typing.Optional[int] = None height: typing.Optional[int] = None num_channels: typing.Optional[int] = None feature_size: typing.Optional[int] = None nb_max_frames: typing.Optional[int] = None audio_sequence_length: typing.Optional[int] = None point_batch_size: typing.Optional[int] = None nb_points_per_image: typing.Optional[int] = None visual_seq_length: typing.Optional[int] = None )
Parameters
- config (
transformers.PretrainedConfig) — The model configuration. - task (
str, defaults to"feature-extraction") — The task the model should be exported for. - The rest of the arguments are used to specify the shape of the inputs the model can take. —
- They are required or not depending on the model the
TFLiteConfigis designed for. —
Base class for TFLite exportable model describing metadata on how to export the model through the TFLite format.
Class attributes:
NORMALIZED_CONFIG_CLASS (
Type) — A class derived from NormalizedConfig specifying how to normalize the model config.DUMMY_INPUT_GENERATOR_CLASSES (
Tuple[Type]) — A tuple of classes derived from DummyInputGenerator specifying how to create dummy inputs.ATOL_FOR_VALIDATION (
Union[float, Dict[str, float]]) — A float or a dictionary mapping task names to float, where the float values represent the absolute tolerance value to use during model conversion validation.MANDATORY_AXES (
Tuple[Union[str, Tuple[Union[str, Tuple[str]]]]]) — A tuple where each element is either:- An axis name, for instance “batch_size” or “sequence_length”, that indicates that the axis dimension is needed to export the model,
- Or a tuple containing two elements:
- The first one is either a string or a tuple of strings and specifies for which task(s) the axis is needed
- The second one is the axis name.
For example:
MANDATORY_AXES = ("batch_size", "sequence_length", ("multiple-choice", "num_choices"))means that to export the model, the batch size and sequence length values always need to be specified, and that a value for the number of possible choices is needed when the task is multiple-choice.
inputs
< source >( ) → Dict[str, Dict[int, str]]
Returns
Dict[str, Dict[int, str]]
A mapping of each input name to a mapping of axis position to the axes symbolic name.
Dict containing the axis definition of the input tensors to provide to the model.
outputs
< source >( ) → Dict[str, Dict[int, str]]
Returns
Dict[str, Dict[int, str]]
A mapping of each output name to a mapping of axis position to the axes symbolic name.
Dict containing the axis definition of the output tensors to provide to the model.
Middle-end classes
class optimum.exporters.tflite.config.TextEncoderTFliteConfig
< source >( config: PretrainedConfig task: str batch_size: int = 1 sequence_length: typing.Optional[int] = None num_choices: typing.Optional[int] = None width: typing.Optional[int] = None height: typing.Optional[int] = None num_channels: typing.Optional[int] = None feature_size: typing.Optional[int] = None nb_max_frames: typing.Optional[int] = None audio_sequence_length: typing.Optional[int] = None point_batch_size: typing.Optional[int] = None nb_points_per_image: typing.Optional[int] = None visual_seq_length: typing.Optional[int] = None )
Handles encoder-based text architectures.
class optimum.exporters.tflite.config.VisionTFLiteConfig
< source >( config: PretrainedConfig task: str batch_size: int = 1 sequence_length: typing.Optional[int] = None num_choices: typing.Optional[int] = None width: typing.Optional[int] = None height: typing.Optional[int] = None num_channels: typing.Optional[int] = None feature_size: typing.Optional[int] = None nb_max_frames: typing.Optional[int] = None audio_sequence_length: typing.Optional[int] = None point_batch_size: typing.Optional[int] = None nb_points_per_image: typing.Optional[int] = None visual_seq_length: typing.Optional[int] = None )
Handles vision architectures.