oneflow.nn.BCEWithLogitsLoss

class oneflow.nn.BCEWithLogitsLoss(weight: Optional[oneflow.Tensor] = None, reduction: str = 'mean', pos_weight: Optional[oneflow.Tensor] = None)

This operator combines the Sigmoid and BCELoss together. For numerical stability, we apply some math tricks instead of using Sigmoid layer with BCELoss.

The equation is:

if reduction = "none":

\[out = -weight*[Pos\_weight*y*log\sigma({x}) + (1-y)*log(1-\sigma(x))]\]

if reduction = "mean":

\[out = -\frac{weight}{n}\sum_{i=1}^n[Pos\_weight*y*log\sigma({x}) + (1-y)*log(1-\sigma(x))]\]

if reduction = "sum":

\[out = -weight*\sum_{i=1}^n[Pos\_weight*y*log\sigma({x}) + (1-y)*log(1-\sigma(x))]\]
Parameters

  • weight (Tensor, optional) – The manual rescaling weight to the loss. Default: None

  • size_average (bool, optional) – Deprecated (see reduction). Default: True

  • reduce (bool, optional) – Deprecated (see reduction). Default: True

  • reduction (str, optional) – The reduce type, it can be one of "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. Default: "mean"

  • pos_weight (Tensor, optional) – The manual rescaling weight to the positive examples. Default: None

Shape:

  • Input: \((N,*)\) where * means, any number of additional dimensions

  • Target: \((N,*)\), same shape as the input

  • Output: scalar. If reduction is "none", then \((N,*)\), same shape as input.

For example:

>>> import oneflow as flow
>>> input = flow.tensor([[1.2, 0.2, -0.3], [0.7, 0.6, -2], [0.7, 0.6, -2]], dtype=flow.float32)
>>> target = flow.tensor([[0, 1, 0], [1, 0, 1], [1, 0, 1]], dtype=flow.float32)
>>> weight = flow.tensor([[2, 2, 2], [2, 2, 2], [2, 2, 2]], dtype=flow.float32)
>>> pos_weight = flow.tensor([1.2, 1.3, 1.4], dtype=flow.float32)

>>> m = flow.nn.BCEWithLogitsLoss(weight=weight, pos_weight=pos_weight, reduction="none")
>>> out = m(input, target)
>>> out
tensor([[2.9266, 1.5552, 1.1087],
        [0.9676, 2.0750, 5.9554],
        [0.9676, 2.0750, 5.9554]], dtype=oneflow.float32)

>>> m = flow.nn.BCEWithLogitsLoss(weight=weight, pos_weight=pos_weight, reduction="mean")
>>> out = m(input, target)
>>> out
tensor(2.6207, dtype=oneflow.float32)

>>> m = flow.nn.BCEWithLogitsLoss(weight=weight, pos_weight=pos_weight, reduction="sum")
>>> out = m(input, target)
>>> out
tensor(23.5865, dtype=oneflow.float32)