Assume that i have two vectors a and b, and i would like to add these two to
get a matrix. In numpy i can do it in this way.
import numpy as np
a = np.array([0,1,2])
b = a.reshape(3,1)
a+b
In theano i can do it like
a = numpy.array([[0,1,2]])
b = numpy.array([[0],[1],[2]])##b = a.reshape(a.shape[1],a.shape[0])
a1=theano.shared(numpy.asarray(a), broadcastable =(True,False), borrow =True)
b1 = theano.shared(numpy.asarray(b),broadcastable=(False, True),borrow = True)
alpha_matrix = T.add(a1, b1)
alpha_matrix_compute = theano.function([], alpha_matrix)for i in range(10000):
c = alpha_matrix_compute()
But the problem is that, a and b are not given and they are calculated during
the program running. So they cannot be defined as shared values.
So, symbolic value must be used. How to calculate it with symbolic value?
--
---
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.
