BCE Loss (PyTorch)

admin

June 10, 2019, 9:10 p.m.

read: 1641

适合最后一层（输出层）为二分类,
label==>1 为一个类别，label==> 0 为另一个类别
两个样例：

>>> 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)

>>> m = nn.Sigmoid()
>>> loss = nn.BCELoss()
>>> input = torch.randn(3, requires_grad=True)
>>> target = torch.empty(3).random_(2)
>>> output = loss(m(input), target)
>>> output.backward()