TensorFlow 1 version
|
View source on GitHub
|
Provides a scope within which the learning phase is equal to value.
@tf_contextlib.contextmanagertf.keras.backend.learning_phase_scope( value )
The learning phase gets restored to its original value upon exiting the scope.
Arguments | |
|---|---|
value
|
Learning phase value, either 0 or 1 (integers). 0 = test, 1 = train |
Yields:
None.
Raises | |
|---|---|
ValueError
|
if value is neither 0 nor 1.
|
TensorFlow 1 version
View source on GitHub