MultiLabelMarginLoss(size_average=None, reduce=None, reduction='mean')[source]¶
Creates a criterion that optimizes a multi-class multi-classification hinge loss (margin-based loss) between input (a 2D mini-batch Tensor) and output (which is a 2D Tensor of target class indices). For each sample in the mini-batch:
where , , , and for all and .
and must have the same size.
The criterion only considers a contiguous block of non-negative targets that starts at the front.
This allows for different samples to have variable amounts of target classes.
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 (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
Input: or where N is the batch size and C is the number of classes.
Target: or , label targets padded by -1 ensuring same shape as the input.
Output: scalar. If
'none', then .
>>> loss = nn.MultiLabelMarginLoss() >>> x = torch.FloatTensor([[0.1, 0.2, 0.4, 0.8]]) >>> # for target y, only consider labels 3 and 0, not after label -1 >>> y = torch.LongTensor([[3, 0, -1, 1]]) >>> loss(x, y) >>> # 0.25 * ((1-(0.1-0.2)) + (1-(0.1-0.4)) + (1-(0.8-0.2)) + (1-(0.8-0.4))) tensor(0.8500)