tf.nn.l2_loss(t, name=None)

tf.nn.l2_loss(t, name=None)

See the guide: Neural Network > Losses

L2 Loss.

Computes half the L2 norm of a tensor without the sqrt:

output = sum(t ** 2) / 2


  • t: A Tensor. Must be one of the following types: float32, float64, int64, int32, uint8, uint16, int16, int8, complex64, complex128, qint8, quint8, qint32, half. Typically 2-D, but may have any dimensions.
  • name: A name for the operation (optional).


A Tensor. Has the same type as t. 0-D.

Defined in tensorflow/python/ops/