TensorFlow 2.0 Beta is available Learn more

tf.keras.mixed_precision.experimental.global_policy

Returns the global Policy.

Aliases:

  • tf.compat.v1.keras.mixed_precision.experimental.global_policy
  • tf.compat.v2.keras.mixed_precision.experimental.global_policy
  • tf.keras.mixed_precision.experimental.global_policy
tf.keras.mixed_precision.experimental.global_policy()
View source on GitHub

The global policy is the default policy used for layers, if no policy is passed to the layer constructor. When TensorFlow starts, the global policy is set to an "infer" policy, and can be changed with set_policy.

Returns:

The global Policy.