mindspore.ops.multilabel_soft_margin_loss

mindspore.ops.multilabel_soft_margin_loss(input, target, weight=None, reduction='mean')[source]

Calculates the MultiLabelSoftMarginLoss. The multi-label soft margin loss is a commonly used loss function in multi-label classification tasks where an input sample can belong to multiple classes. Given an input $i n p u t$ and binary labels $o u t p u t$ of size $(N, C)$ , where $N$ denotes the number of samples and $C$ denotes the number of classes.

loss (input, output) = - \frac{1}{N} \frac{1}{C} \sum_{i = 1}^{N} \sum_{j = 1}^{C} (o u t p u t_{i j} \log \frac{1}{1 + e^{- i n p u t_{i j}}} + (1 - o u t p u t_{i j}) \log \frac{e^{- i n p u t_{i j}}}{1 + e^{- i n p u t_{i j}}})

where $i n p u t_{i j}$ represents the predicted score of sample $i$ for class $j$ . $o u t p u t_{i j}$ represents the binary label of sample $i$ for class $j$ , where sample $i$ belongs to class $j$ if $o u t p u t_{i j} = 1$ , and sample $i$ does not belong to class $j$ if $o u t p u t_{i j} = 0$ . For a multi-label classification task, each sample may have multiple labels with a value of 1 in the binary label $o u t p u t$ . weight will multiply to the loss of each class if given.

Parameters

input (Tensor) – A tensor of shape $(N, C)$ , where N is batch size and C is number of classes.
target (Tensor) – The label target Tensor which has the same shape as input.
weight (Union[Tensor, int, float]) – The manual rescaling weight given to each class. Default: None.
reduction (str, optional) –
Apply specific reduction method to the output: 'none' , 'mean' , 'sum' . Default: 'mean' .
- 'none': no reduction will be applied.
- 'mean': compute and return the weighted mean of elements in the output.
- 'sum': the output elements will be summed.

Returns

Tensor, the data type is the same as input, if the reduction is 'none', its shape is $(N)$ , otherwise it is zero.

Supported Platforms:: Ascend GPU CPU

Examples

>>> from mindspore import Tensor, ops
>>> input = Tensor([[0.3, 0.6, 0.6], [0.9, 0.4, 0.2]])
>>> target = Tensor([[0.0, 0.0, 1.0], [0.0, 0.0, 1.0]])
>>> loss = ops.multilabel_soft_margin_loss(input, target, reduction='mean')
>>> print(loss.asnumpy())
0.84693956