oneflow.nn.functional.triplet_margin_loss

oneflow.nn.functional.triplet_margin_loss()

Creates a criterion that measures the triplet loss given an input tensors \(x1\), \(x2\), \(x3\) and a margin with a value greater than \(0\). 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 \((N, D)\).

The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.functional.triplet_margin_loss.html.

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:

\[L(a, p, n) = \max \{d(a_i, p_i) - d(a_i, n_i) + {\rm margin}, 0\}\]

where

\[d(x_i, y_i) = \left\lVert {\bf x}_i - {\bf y}_i \right\rVert_p\]
Parameters
  • margin (float, optional) – Default: \(1\).

  • p (float, optional) – The norm degree for pairwise distance. Default: \(2.0\).

  • 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: False.

  • reduction (string, optional) – Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. '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: size_average and reduce are in the process of being deprecated, and in the meantime, specifying either of those two args will override reduction. Default: 'mean'

Shape:
  • Input: \((N, D)\) where \(D\) is the vector dimension.

  • Output: A Tensor of shape \((N)\) if reduction is 'none', or a scalar otherwise.

For example:

>>> import oneflow as flow
>>> import numpy as np
>>> triplet_loss = flow.nn.TripletMarginLoss(margin=1.0, p=2)
>>> anchor = np.array([[1, -1, 1],[-1, 1, -1], [1, 1, 1]])
>>> positive = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
>>> negative = np.array([[2, 2, 2], [2, 2, 2], [2, 2, 2]])
>>> output = triplet_loss(flow.Tensor(anchor), flow.Tensor(positive), flow.Tensor(negative))
>>> output
tensor(6.2971, dtype=oneflow.float32)