Hey Fred,
good catch. Yeah T.fmatrix() is already float32 by default so changing it
with .astype() wouldn't do anything good. But the fact that T.mean() casts
an input of float32 to float64, apply the mean operator and then recast the
output to float32 is that efficient either. It's a waste of c
Le 20 sept. 2016 10:20, a écrit :
>
> I'll answer my own question. I've figured out where the error was.
>
> 1. I had to explicitly define the symbolic variables as type float32
> e..g X = T.fmatrix('X').astype(dtype=float32)
This is not useful. The astype should not change anything here. Did you
I'll answer my own question. I've figured out where the error was.
1. I had to explicitly define the symbolic variables as type float32
e..g X = T.fmatrix('X').astype(dtype=float32)
Which is really a bummer if you ask me, I thought the whole point of having
a .theanorc file and defining your typ