Examples::
 
    >>> target = torch.ones([10, 64], dtype=torch.float32)  # 64 classes, batch size = 10
    >>> output = torch.full([10, 64], 0.999)  # A prediction (logit)
    >>> pos_weight = torch.ones([64])  # All weights are equal to 1
    >>> criterion = torch.nn.BCEWithLogitsLoss(pos_weight=pos_weight)
    >>> criterion(output, target)  # -log(sigmoid(0.999))
    tensor(0.3135)
 
Args:
    weight (Tensor, optional): a manual rescaling weight given to the loss
        of each batch element. If given, has to be a Tensor of size `nbatch`.
    size_average (bool, optional): Deprecated (see :attr:`reduction`). By default,
        the losses are averaged over each loss element in the batch. Note that for
        some losses, there are multiple elements per sample. If the field :attr:`size_average`
        is set to ``False``, the losses are instead summed for each minibatch. Ignored
        when reduce is ``False``. Default: ``True``
    reduce (bool, optional): Deprecated (see :attr:`reduction`). By default, the
        losses are averaged or summed over observations for each minibatch depending
        on :attr:`size_average`. When :attr:`reduce` is ``False``, returns a loss per
        batch element instead and ignores :attr:`size_average`. Default: ``True``
    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: :attr:`size_average`
        and :attr:`reduce` are in the process of being deprecated, and in the meantime,
        specifying either of those two args will override :attr:`reduction`. Default: ``'mean'``
    pos_weight (Tensor, optional): a weight of positive examples.
            Must be a vector with length equal to the number of classes.

criterion = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([4]))
 
# pos_weight (Tensor, optional): a weight of positive examples.
#            Must be a vector with length equal to the number of classes.

Examples::
 
    >>> target = torch.ones([10, 64], dtype=torch.float32)  # 64 classes, batch size = 10
    >>> output = torch.full([10, 64], 0.999)  # A prediction (logit)
    >>> pos_weight = torch.ones([64])  # All weights are equal to 1
    >>> criterion = torch.nn.BCEWithLogitsLoss(pos_weight=pos_weight)
    >>> criterion(output, target)  # -log(sigmoid(0.999))
    tensor(0.3135)

torch.sigmoid() + torch.nn.BCELoss()

def ce_loss(y_pred, y_train, alpha=1):
    
    p = torch.sigmoid(y_pred)
    # p = torch.clamp(p, min=1e-9, max=0.99)  
    loss = torch.sum(- alpha * torch.log(p) * y_train \
           - torch.log(1 - p) * (1 - y_train))/len(y_train)
    return loss~

import torch
import torch.nn as nn
torch.cuda.manual_seed(300)       # 為當(dāng)前GPU設(shè)置隨機(jī)種子
torch.manual_seed(300)            # 為CPU設(shè)置隨機(jī)種子
def ce_loss(y_pred, y_train, alpha=1):
   # 計算loss
   p = torch.sigmoid(y_pred)
   # p = torch.clamp(p, min=1e-9, max=0.99)
   loss = torch.sum(- alpha * torch.log(p) * y_train \
          - torch.log(1 - p) * (1 - y_train))/len(y_train)
   return loss
py_lossFun = nn.BCEWithLogitsLoss()
input = torch.randn((10000,1), requires_grad=True)
target = torch.ones((10000,1))
target.requires_grad_(True)
py_loss = py_lossFun(input, target)
py_loss.backward()
print("*********BCEWithLogitsLoss***********")
print("loss: ")
print(py_loss.item())
print("梯度: ")
print(input.grad)
input = input.detach()
input.requires_grad_(True)
self_loss = ce_loss(input, target)
self_loss.backward()
print("*********SelfCELoss***********")
print("loss: ")
print(self_loss.item())
print("梯度: ")
print(input.grad)