I'm trying to implement a simple Boltzmann Machine using Theano. So far
everything is working but I'm having the problem that I calculate some
things more than once which is causing a quite noticeable but unnecessary
slowdown.
You can check out my SO question [1] but it boils down to this
h1_activ = sigmoid(self.bias_visiblie + T.dot(D, self.W))
h1_sample = h1_activ > rnds.uniform((n_samples, self.n_hidden ))
f_h1_sample = theano.function(
inputs=[D],
outputs=h1_sample,
# I'd like to take the result from 'h1_sample' and store it into
'H1_sample'
updates=[(self.H1_sample, ? h1_sample ? )]
)
I'd like to know how I could store this intermediate result of h1_sample into
the member variable.
Is that possible and if so how?
BR; Stefan
[1] http://stackoverflow.com/questions/40070098/can-i-store-intermediate-results
--
---
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.
