Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf.keras.regularizers.l1

TensorFlow 1 version View source on GitHub

Create a regularizer that applies an L1 regularization penalty.

tf.keras.regularizers.l1(
    l=0.01
)

Used in the notebooks

Used in the guide

The L1 regularization penalty is computed as:

\(\ell_1\,\,penalty =\ell_1\sum_{i=0}^n|x_i|\)

Arguments:

  • l: Float; L1 regularization factor.

Returns:

An L1 Regularizer with the given regularization factor.