tf.keras.mixed_precision.experimental.global_policy

Stay organized with collections Save and categorize content based on your preferences.

TensorFlow 1 version View source on GitHub

Returns the global Policy.

The global policy is the default policy used for layers, if no policy is passed to the layer constructor. If no policy has been set with keras.mixed_precision.experimental.set_policy, this will return a policy constructed from tf.keras.backend.floatx() in TensorFlow 2 (floatx defaults to float32), or an "infer" policy in TensorFlow 1.

See keras.mixed_precision.experimental.Policy for more information.

The global Policy.