TensorFlow 2.0 Beta is available Learn more

tf.keras.models.model_from_config

Instantiates a Keras model from its config.

Aliases:

  • tf.compat.v1.keras.models.model_from_config
  • tf.compat.v2.keras.models.model_from_config
  • tf.keras.models.model_from_config
tf.keras.models.model_from_config(
    config,
    custom_objects=None
)

Defined in python/keras/saving/model_config.py.

Arguments:

  • config: Configuration dictionary.
  • custom_objects: Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization.

Returns:

A Keras model instance (uncompiled).

Raises:

  • TypeError: if config is not a dictionary.