tf.keras.layers.deserialize

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/functions

Layer instance (may be Model, Sequential, Network, Layer...)

Example:

# Configuration of Dense(32, activation='relu')
config = {
  'class_name': 'Dense',
  'config': {
    'activation': 'relu',
    'activity_regularizer': None,
    'bias_constraint': None,
    'bias_initializer': {'class_name': 'Zeros', 'config': {} },
    'bias_regularizer': None,
    'dtype': 'float32',
    'kernel_constraint': None,
    'kernel_initializer': {'class_name': 'GlorotUniform',
                           'config': {'seed': None} },
    'kernel_regularizer': None,
    'name': 'dense',
    'trainable': True,
    'units': 32,
    'use_bias': True
  }
}
dense_layer = tf.keras.layers.deserialize(config)