View source on GitHub
|
The hyperparameters for a Bert Classifier.
Inherits From: BaseHParams
mediapipe_model_maker.text_classifier.BertHParams(
learning_rate: float = 3e-05,
batch_size: int = 48,
epochs: int = 2,
steps_per_epoch: Optional[int] = None,
class_weights: Optional[Mapping[int, float]] = None,
shuffle: bool = False,
repeat: bool = False,
export_dir: str = tempfile.mkdtemp(),
distribution_strategy: