Dragon API Dragon v0.3.0 Python L2¶ class dragon.vm.tensorflow.keras.regularizers.L2(l2=0.01)[source]¶ The L2 regularizer. The L2 regularizer is defined as: \[loss_{reg} = loss + \frac{\beta}{2}|w|_{2} \] __init__¶ L2.__init__(l2=0.01)[source]¶ Create a L2 regularizer. Parameters: l1 (float, optional, default=0.01) – The value to \(\alpha\).