l1_loss¶
dragon.losses.
l1_loss
(
inputs,
reduction='mean',
**kwargs
)[source]¶Compute the loss of element-wise absolute value difference.
The L1Loss function is defined as:
\[\text{L1Loss}(x, y) = |x - y| \]Examples:
x = dragon.constant([1., 2., 3.]) y = dragon.constant([0., 0., 0.]) print(dragon.losses.l1_loss([x, y])) # 2.0
- Parameters:
- inputs (Sequence[dragon.Tensor]) – The tensor
input
andtarget
. - reduction ({'none', 'sum', 'mean'}, optional) – The reduction method.
- inputs (Sequence[dragon.Tensor]) – The tensor
- Returns:
dragon.Tensor – The output tensor.