View source on GitHub |
Instantiates a layer from a config dictionary.
tf.keras.layers.deserialize(
config, custom_objects=None
)
config
: dict of the form {'class_name': str, 'config': dict}custom_objects
: dict mapping class names (or function names)
of custom (non-Keras) objects to class/functionsLayer instance (may be Model, Sequential, Network, Layer...)