binary_cross_entropy(input, target, weight=None, reduction='mean')¶
The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.functional.binary_cross_entropy.html.
Function that measures the Binary Cross Entropy between the target and input probabilities.
input – Tensor of arbitrary shape as probabilities.
target – Tensor of the same shape as input with values between 0 and 1.
weight (Tensor, optional) – a manual rescaling weight if provided it’s repeated to match input tensor shape
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
>>> import oneflow as flow >>> import oneflow.nn.functional as F >>> input = flow.randn(3, 2, requires_grad=True) >>> target = flow.rand(3, 2, requires_grad=False) >>> loss = F.binary_cross_entropy(flow.sigmoid(input), target) >>> loss.backward()