docs:
torch.nn.KLDivLoss
which I think should be:
Hi Kabu!
No, the documentation for KLDivLoss
is correct.
The equation you posted an image of contains the term:
y_n (log y_n - x_n)
You are expecting log x_n
rather than just x_n
. But KLDivLoss
expects x_n
to be already a log-probability. Quoting from the
documentation you linked to:
As with
NLLLoss
, the input given is expected to contain log-probabilities and is not restricted to a 2D Tensor. The targets are interpreted as probabilities by default, but could be considered as log-probabilities withlog_target
set toTrue
.
Best.
K. Frank
2 Likes