Dragon API Dragon v0.3.0 Python L1L2¶ class dragon.vm.tensorflow.keras.regularizers.L1L2( l1=0.01, l2=0.01)[source]¶ The L1L2 regularizer. The L1L2 regularizer is defined as: \[loss_{reg} = loss + \alpha|w| + \frac{\beta}{2}|w|_{2} \] __init__¶ L1L2.__init__( l1=0.01, l2=0.01)[source]¶ Create a L1L2 regularizer. Parameters: l1 (float, optional, default=0.01) – The value to \(\alpha\). l2 (float, optional, default=0.01) – The value to \(\beta\).