Closed EmbraceLife closed 7 years ago
PyTorch only natively supports a border: valid
mode. We can emulate the same
mode in Kur, of course. It turns out it is trivial to emulate same
mode when size
has odd sizes (because of the way that PyTorch does its padding), but I haven't given the even sizes too much thought. Until I, or some other contributor, get around to it, PyTorch users should either use valid
(with any receptive field) or same
with an odd receptive field.
You say you did this, but got an error. The traceback indicates that the problem was encountered in File "/Users/Natsume/Downloads/kur/kur/backend/pytorch_backend.py", line 176, in restore
, which almost certainly means you accidentally had old weights sitting on disk which were the wrong size (inconsistent tensor size
). Try clearing out (deleting) the old weights and try again.
Thanks! I shall always remember to clear out the previous folders for weights every time I change the model even a little bit.
with
cifar.yml
demo insidekur/
, after change the backend topytorch
as belowI got the following error message:
After set
border
from default tovalid
, it works fine.My question If user intends to use
border = "same"
, then what shall be done to make pytorch work?Maybe, we shall change receptive field should not be even, so I tried to set it odd:
But I got a new error this time: