margin_ranking_loss

paddle.nn.functional. margin_ranking_loss ( input, other, label, margin=0.0, reduction='mean', name=None ) [source]

Calcluate the margin rank loss between the input, other and label, use the math function as follows.

\[margin\_rank\_loss = max(0, -label * (input - other) + margin)\]

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

\[Out = MEAN(margin\_rank\_loss)\]

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

\[Out = SUM(margin\_rank\_loss)\]

If reduction set to 'none', just return the origin margin_rank_loss.

Parameters

  • input (Tensor) – the first input tensor, it’s data type should be float32, float64.

  • other (Tensor) – the second input tensor, it’s data type should be float32, float64.

  • label (Tensor) – the label value corresponding to input, it’s data type should be float32, float64.

  • margin (float, optional) – The margin value to add, default value is 0;

  • reduction (str, optional) – Indicate the reduction to apply to the loss, the candicates 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.

Returns

Tensor, if reduction is 'mean' or 'sum', the out shape is \([1]\), otherwise the shape is the same as input .The same dtype as input tensor.

Examples

import paddle

input = paddle.to_tensor([[1, 2], [3, 4]], dtype='float32')
other = paddle.to_tensor([[2, 1], [2, 4]], dtype='float32')
label = paddle.to_tensor([[1, -1], [-1, -1]], dtype='float32')
loss = paddle.nn.functional.margin_ranking_loss(input, other, label)
print(loss) # [0.75]