Change input value in examples of `BCEWithLogitsLoss` (#34053)
Summary:
In the examples of `BCEWithLogitsLoss`, `0.999` is passed as the prediction value. The value `0.999` seems to be a probability, but actually it's not. I think it's better to pass a value that is greater than 1, not to confuse readers.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/34053
Differential Revision: D20195456
Pulled By: ezyang
fbshipit-source-id: 3abbda6232ee1ab141d202d0ce1177526ad59c53
diff --git a/torch/nn/modules/loss.py b/torch/nn/modules/loss.py
index c13b9da..bc51005 100644
--- a/torch/nn/modules/loss.py
+++ b/torch/nn/modules/loss.py
@@ -564,11 +564,11 @@
Examples::
>>> target = torch.ones([10, 64], dtype=torch.float32) # 64 classes, batch size = 10
- >>> output = torch.full([10, 64], 0.999) # A prediction (logit)
+ >>> output = torch.full([10, 64], 1.5) # 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)
+ >>> criterion(output, target) # -log(sigmoid(1.5))
+ tensor(0.2014)
Args:
weight (Tensor, optional): a manual rescaling weight given to the loss
