tf.keras自定义损失函数

In statistics, the Huber loss is a loss function used in robust regression, that is less sensitive to outliers in data than the squared error loss. A variant for classification is also sometimes used.

def huber_fn(y_true, y_pred):
    error = y_true - y_pred
    is_small_error = tf.abs(error) < 1
    squared_loss = tf.square(error) / 2
    linear_loss  = tf.abs(error) - 0.5
    return tf.where(is_small_error, squared_loss, linear_loss)

注意，自定义损失函数的返回值是一个向量而不是损失平均值，每个元素对应一个实例。这样的好处是Keras可以通过class_weight或sample_weight调整权重。

huber_fn(y_valid, y_pred)
<tf.Tensor: id=4894, shape=(3870, 1), dtype=float64, numpy=
array([[0.10571115],
       [0.03953311],
       [0.02417886],
       ...,
       [0.00039475],
       [0.00245003],
       [0.12238744]])>