Hi, this is not specific to Theano/Keras, but is general computation. I'm not sure what you want to do. I'm not an expert in fixed point computation, but from what I remember reading, it use int computation, not float computation.
Frédéric On Mon, Feb 6, 2017 at 4:10 AM Kartikeya Karnatak <k.o.karna...@gmail.com> wrote: > Hi, > > I want to know if, it's theoretically possible to approximate two > fixed-point 8bit operations (or 16bit operations) with float 32? OR do you > need float 64? > > Thanks > > -- > > --- > You received this message because you are subscribed to the Google Groups > "theano-users" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to theano-users+unsubscr...@googlegroups.com. > For more options, visit https://groups.google.com/d/optout. > -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to theano-users+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
