L1Loss

class paddle.nn. L1Loss ( reduction='mean', name=None ) [source]

Construct a callable object of the L1Loss class. The L1Loss layer calculates the L1 Loss of input and label as follows.

If reduction set to 'none', the loss is:

\[Out = \lvert input - label\rvert\]

If reduction set to 'mean', the loss is:

\[Out = MEAN(\lvert input - label\rvert)\]

If reduction set to 'sum', the loss is:

\[Out = SUM(\lvert input - label\rvert)\]
Parameters

  • reduction (str, optional) – Indicate the reduction to apply to the loss, the candidates are 'none' | 'mean' | 'sum'. If reduction is 'none', the unreduced loss is returned; If reduction is 'mean', the reduced mean loss is returned. If reduction is 'sum', the reduced sum loss is returned. Default is 'mean'.

  • name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Shape:

  • input (Tensor): The input tensor. The shapes is [N, *], where N is batch size and * means any number of additional dimensions. It’s data type should be float32, float64, int32, int64.

  • label (Tensor): label. The shapes is [N, *], same shape as input . It’s data type should be float32, float64, int32, int64.

  • output (Tensor): The L1 Loss of input and label. If reduction is 'none', the shape of output loss is [N, *], the same as input . If reduction is 'mean' or 'sum', the shape of output loss is [].

Examples

>>> import paddle

>>> input = paddle.to_tensor([[1.5, 0.8], [0.2, 1.3]])
>>> label = paddle.to_tensor([[1.7, 1], [0.4, 0.5]])

>>> l1_loss = paddle.nn.L1Loss()
>>> output = l1_loss(input, label)
>>> print(output)
Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
0.34999999)

>>> l1_loss = paddle.nn.L1Loss(reduction='sum')
>>> output = l1_loss(input, label)
>>> print(output)
Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
1.39999998)

>>> l1_loss = paddle.nn.L1Loss(reduction='none')
>>> output = l1_loss(input, label)
>>> print(output)
Tensor(shape=[2, 2], dtype=float32, place=Place(cpu), stop_gradient=True,
[[0.20000005, 0.19999999],
 [0.20000000, 0.79999995]])
forward ( input, label )

forward

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

  • *inputs (tuple) – unpacked tuple arguments

  • **kwargs (dict) – unpacked dict arguments