tf.keras.models.model_from_yaml

TensorFlow 1 version View source on GitHub

Parses a yaml model configuration file and returns a model instance.

Used in the notebooks

Used in the guide

Usage:

model = tf.keras.Sequential([
    tf.keras.layers.Dense(5, input_shape=(3,)),
    tf.keras.layers.Softmax()])
try:
  import yaml
  config = model.to_yaml()
  loaded_model = tf.keras.models.model_from_yaml(config)
except ImportError:
  pass

yaml_string YAML string or open file encoding a model configuration.
custom_objects Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization.

A Keras model instance (uncompiled).

ImportError if yaml module is not found.