R/model-persistence.R

model_to_saved_model

(Deprecated) Export to Saved Model format

Description

(Deprecated) Export to Saved Model format

Usage

 
model_to_saved_model( 
  model, 
  saved_model_path, 
  custom_objects = NULL, 
  as_text = FALSE, 
  input_signature = NULL, 
  serving_only = FALSE 
) 

Arguments

Arguments Description
model A Keras model to be saved. If the model is subclassed, the flag serving_only must be set to TRUE.
saved_model_path a string specifying the path to the SavedModel directory.
custom_objects Optional dictionary mapping string names to custom classes or functions (e.g. custom loss functions).
as_text bool, FALSE by default. Whether to write the SavedModel proto in text format. Currently unavailable in serving-only mode.
input_signature A possibly nested sequence of tf.TensorSpec objects, used to specify the expected model inputs. See tf.function for more details.
serving_only bool, FALSE by default. When this is true, only the prediction graph is saved.

Value

Invisibly returns the saved_model_path.

Note

This functionality is experimental and only works with TensorFlow version >= “2.0”.

See Also

Other saved_model: model_from_saved_model()