tf.contrib.layers.apply_regularization( regularizer, weights_list=None )
See the guide: Layers (contrib) > Regularizers
Returns the summed penalty by applying
regularizer to the
Adding a regularization penalty over the layer weights and embedding weights can help prevent overfitting the training data. Regularization over layer biases is less common/useful, but assuming proper data preprocessing/mean subtraction, it usually shouldn't hurt much either.
regularizer: A function that takes a single
Tensorargument and returns a scalar
weights_list: List of weights
regularizerover. Defaults to the
A scalar representing the overall regularization penalty.
regularizerdoes not return a scalar output, or if we find no weights.