tf.contrib.layers.l2_regularizer(scale, scope=None)

tf.contrib.layers.l2_regularizer(scale, scope=None)

See the guide: Layers (contrib) > Regularizers

Returns a function that can be used to apply L2 regularization to weights.

Small values of L2 can help prevent overfitting the training data.


  • scale: A scalar multiplier Tensor. 0.0 disables the regularizer.
  • scope: An optional scope name.


A function with signature l2(weights) that applies L2 regularization.


  • ValueError: If scale is negative or if scale is not a float.

Defined in tensorflow/contrib/layers/python/layers/