Hello, does anyone know what is the easiest way to pinpoint float64 tensors in our code, because when I usually run code not generated by me it often happens that they use float64 for the creation of tensors. For instance I'm trying to run the example of rnn_rbm from the theano examples and I usually get the exception warning me about the use of float64 in the code but I can't easily pinpoint where that piece of code might be.
Is there any way to let's say print all al the float64 variables in the code or some other alternative that would easily allow to pinpoint where in the code those float64 variables are being initialized? 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 [email protected]. For more options, visit https://groups.google.com/d/optout.
