Hello,
in order to use less memory I wanted to change my uses of FloatTensor to HalfTensor since I don’t need the precision, but when I did so, running my full connected network ended up in an error
_cat is not implemented for type torch.HalfTensor
I would like to know if there is a way to go around this, as I use a cat in my model and don’t really know how else to do it.
Thank you in advance for your help 