Keras learning_phase()和learning_phase_scope()

tf.keras.backend.learning_phase()

The learning phase flag is a bool tensor (0 = test, 1 = train) to be passed as input to any Keras function that uses a different behavior at train time and test time.

tf.keras.backend.learning_phase_scope(value)

The learning phase gets restored to its original value upon exiting the scope.
value: Learning phase value, either 0 or 1 (integers). 0 = test, 1 = train

tf.keras.backend.learning_phase()返回當前狀態flag，是train還是test階段
tf.keras.backend.learning_phase_scope(value)將當前scope下的代碼運行於train(value=1)或test(value=0)狀態下

with keras.backend.learning_phase_scope(1): 
    y_probas = np.stack([model.predict(X_test_scaled) for sample in range(100)])