hinge_embedding_loss

paddle.nn.functional. hinge_embedding_loss ( input, label, margin=1.0, reduction='mean', name=None ) [source]

Calculates hinge_embedding_loss. Measures the loss given an input tensor \(x\) and a labels tensor \(y\), and is typically used for learning nonlinear embeddings or semi-supervised learning.

The loss function for \(n\)-th sample in the mini-batch is

\[\begin{split}l_n = \begin{cases} x_n, & \text{if}\; y_n = 1,\\ \max \{0, \Delta - x_n\}, & \text{if}\; y_n = -1, \end{cases}\end{split}\]

and the total loss functions is

\[\begin{split}\ell(x, y) = \begin{cases} \operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\ \operatorname{sum}(L), & \text{if reduction} = \text{'sum'.} \end{cases}\end{split}\]

where \(L = \{l_1,\dots,l_N\}^\top\).

Parameters
  • input (Tensor) – Input tensor, the data type is float32 or float64. the shape is [N, *], N is batch size and * means any number of additional dimensions, available dtype is float32, float64.

  • label (Tensor) – Label tensor containing 1 or -1, the data type is float32 or float64. The shape of label is the same as the shape of input.

  • margin (float, optional) – Specifies the hyperparameter margin to be used. The value determines how large the input need to be to calculate in hinge_embedding_loss. When label is -1, Input smaller than margin are minimized with hinge_embedding_loss. Default = 1.0

  • reduction (str, optional) – Indicate how to average the loss by batch_size. the candidates 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 summed loss is returned. Default: 'mean'

  • name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Shape:

input: N-D Tensor, the shape is [N, *], N is batch size and * means any number of additional dimensions, available dtype is float32, float64. The sum operation operates over all the elements.

label: N-D Tensor, same shape as the input. tensor elements should containing 1 or -1, the data type is float32 or float64.

output: scalar. If reduction is 'none', then same shape as the input.

Returns

Tensor. The tensor variable storing the hinge_embedding_loss of input and label.

Examples

>>> import paddle
>>> import paddle.nn.functional as F

>>> input = paddle.to_tensor([[1, -2, 3], [0, -1, 2], [1, 0, 1]], dtype=paddle.float32)
>>> # label elements in {1., -1.}
>>> label = paddle.to_tensor([[-1, 1, -1], [1, 1, 1], [1, -1, 1]], dtype=paddle.float32)

>>> loss = F.hinge_embedding_loss(input, label, margin=1.0, reduction='none')
>>> print(loss)
Tensor(shape=[3, 3], dtype=float32, place=Place(cpu), stop_gradient=True,
       [[ 0., -2.,  0.],
        [ 0., -1.,  2.],
        [ 1.,  1.,  1.]])
>>> loss = F.hinge_embedding_loss(input, label, margin=1.0, reduction='mean')
>>> print(loss)
Tensor(shape=[], dtype=float32, place=Place(cpu), stop_gradient=True,
       0.22222222)