TripletMarginLoss(margin: float = 1.0, p: float = 2.0, eps: float = 1e-06, swap: bool = False, size_average=None, reduce=None, reduction: str = 'mean')¶
Creates a criterion that measures the triplet loss given an input tensors , , and a margin with a value greater than . This is used for measuring a relative similarity between samples. A triplet is composed by a, p and n (i.e., anchor, positive examples and negative examples respectively). The shapes of all input tensors should be .
The distance swap is described in detail in the paper Learning shallow convolutional feature descriptors with triplet losses by V. Balntas, E. Riba et al.
The loss function for each sample in the mini-batch is:
margin (float, optional) – Default: .
p (int, optional) – The norm degree for pairwise distance. Default: .
swap (bool, optional) – The distance swap is described in detail in the paper Learning shallow convolutional feature descriptors with triplet losses by V. Balntas, E. Riba et al. Default:
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
Input: where is the vector dimension.
Output: scalar. If
'none', then .
>>> triplet_loss = nn.TripletMarginLoss(margin=1.0, p=2) >>> anchor = torch.randn(100, 128, requires_grad=True) >>> positive = torch.randn(100, 128, requires_grad=True) >>> negative = torch.randn(100, 128, requires_grad=True) >>> output = triplet_loss(anchor, positive, negative) >>> output.backward()