You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
So, the loss is calculated on log_softmax which is not recommended by pytorch as nn.CrossEntropy Loss function already does that in its subroutine. (https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html).
I found that it has been done in other models too.
I am not sure whether it was done intentionally or an implementation bug or a mistake in my understanding. Can you explain me before I run my computation.
The text was updated successfully, but these errors were encountered:
BreizhCrops/breizhcrops/models/PETransformerModel.py
Lines 40 to 52 in 6de796e
I wanted to implement your models on my data and I found at line 50 of script ```PETransformerModel.py" log_softmax function has been implemented.
Secondly, when I saw your
examples/train.py
, I found criterion used is CrossEntropyLossBreizhCrops/examples/train.py
Lines 36 to 40 in 6de796e
BreizhCrops/examples/train.py
Lines 170 to 182 in 6de796e
So, the loss is calculated on log_softmax which is not recommended by pytorch as nn.CrossEntropy Loss function already does that in its subroutine. (https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html).
I found that it has been done in other models too.
I am not sure whether it was done intentionally or an implementation bug or a mistake in my understanding. Can you explain me before I run my computation.
The text was updated successfully, but these errors were encountered: