LostTech.TensorFlow : API Documentation

Type Huber

Namespace tensorflow.keras.losses

Parent LossFunctionWrapper

Interfaces IHuber

Computes the Huber loss between `y_true` and `y_pred`.

For each value x in `error = y_true - y_pred`:

``` loss = 0.5 * x^2 if |x| <= d loss = 0.5 * d^2 + d * (|x| - d) if |x| > d ``` where d is `delta`. See: https://en.wikipedia.org/wiki/Huber_loss

Usage: Usage with the `compile` API:
Show Example
l = tf.keras.losses.Huber()
            loss = l([0., 1., 1.], [1., 0., 1.])
            print('Loss: ', loss.numpy())  # Loss: 0.333 

Properties

Public properties

object fn get; set;

string name get; set;

object PythonObject get;

string reduction get; set;