Element wise matrix multiplication in Theano

Question

I could see element wise matrix multiplication using numpy can be done with * operator.

print np.mat(np.ones((10,10)))*np.mat(np.ones((10,10)))

But couldnt get it working under theano. The code I tried is

x = T.dmatrix('x')
y = T.dmatrix('y')
z = x * y
f1 = theano.function([x, y], z)

print f1(np.mat(np.ones((10,10))),np.mat(np.ones((10,10))))

If you just want elementwise multiplication, change `z = x + y` to `z = x * y`. — Alex Riley, Apr 23 '16 at 17:59
That code works for me (produces a 10 by 10 array of 1s), what result are you seeing? — Chris K, Apr 27 '16 at 21:57

score 4 · Accepted Answer · answered Feb 08 '17 at 15:50

If I try the following (which is basically your code):

import theano
import theano.tensor as T

import numpy as np

x = T.dmatrix('x')
y = T.dmatrix('y')
z = x * y
f1 = theano.function([x, y], z)

print f1(np.mat(np.ones((10,10))),np.mat(np.ones((10,10))))

I get the following:

[[ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]
 [ 1.  1.  1.  1.  1.  1.  1.  1.  1.  1.]]

So, it works for me.

Element wise matrix multiplication in Theano

1 Answers1