l2_loss¶

dragon.vm.tensorflow.nn.l2_loss(
  t,
  name=None
)[source]¶

Compute the loss of element-wise squared error.

The L2Loss function is defined as:

\[\text{L2Loss}(t) = sum(0.5 * t^{2}) \]

Examples:

t = tf.constant([-1., 2., -3.])
print(tf.nn.l2_loss(t))  # 7.0

Parameters:

• t (dragon.Tensor) – The input tensor.
• name (str, optional) – The operation name.

Returns:

dragon.Tensor – The output tensor.