tff.learning.models.save

Serializes model as a TensorFlow SavedModel to path.

tff.learning.models.save(
    model: tff.learning.models.VariableModel,
    path: str,
    input_type=None
) -> None

The resulting SavedModel will contain the default serving signature, which can be used with the TFLite converter to create a TFLite flatbuffer for inference.

model The tff.learning.models.VariableModel to save.
path The str directory path to serialize the model to.
input_type An optional structure of tf.TensorSpecs representing the expected input of model.predict_on_batch, to override reading from model.input_spec. Typically this will be similar to model.input_spec, with any example labels removed. If None, default to model.input_spec['x'] if the input_spec is a mapping, otherwise default to model.input_spec[0].