MarginRankingLoss(margin: float = 0.0, size_average=None, reduce=None, reduction: str = 'mean')¶
Creates a criterion that measures the loss given inputs , , two 1D mini-batch Tensors, and a label 1D mini-batch tensor (containing 1 or -1).
If then it assumed the first input should be ranked higher (have a larger value) than the second input, and vice-versa for .
The loss function for each pair of samples in the mini-batch is:
margin (float, optional) – Has a default value of .
size_average (bool, optional) – Deprecated (see
reduction). By default, the losses are averaged over each loss element in the batch. Note that for some losses, there are multiple elements per sample. If the field
size_averageis set to
False, the losses are instead summed for each minibatch. Ignored when reduce is
reduce (bool, optional) – Deprecated (see
reduction). By default, the losses are averaged or summed over observations for each minibatch depending on
False, returns a loss per batch element instead and ignores
reduction (string, optional) – Specifies the reduction to apply to the output:
'none': no reduction will be applied,
'mean': the sum of the output will be divided by the number of elements in the output,
'sum': the output will be summed. Note:
reduceare in the process of being deprecated, and in the meantime, specifying either of those two args will override
Input1: where N is the batch size.
Input2: , same shape as the Input1.
Target: , same shape as the inputs.
Output: scalar. If
'none', then .
>>> loss = nn.MarginRankingLoss() >>> input1 = torch.randn(3, requires_grad=True) >>> input2 = torch.randn(3, requires_grad=True) >>> target = torch.randn(3).sign() >>> output = loss(input1, input2, target) >>> output.backward()