fix GpuElemwise version for ndim==0

theano/sandbox/cuda/elemwise.py

@@ -599,7 +599,7 @@ class NaiveAlgo(object):
             for d in xrange(nd):
                 print >> sio, 'std::cerr << " " << local_dims[%(d)s]; ' % locals()
             print >> sio, 'std::cerr << "\\n";'
-
+            if nd > 0:
                 for ipos in xrange(len(node.inputs)):
                     print >> sio, 'std::cerr << " local_str inputs %(ipos)s: " <<'%locals() + \
                         ' << " " << '.join(["local_str[%s][%s]" % (ipos, x) for x in xrange(nd)])+'<<"\\n";'
@@ -642,7 +642,7 @@ class NaiveAlgo(object):
             for d in xrange(nd):
                 print >> sio, 'std::cerr << " " << local_dims[%(d)s]; '%locals()
             print >> sio, 'std::cerr << "\\n";'
-
+            if nd > 0:
                 for ipos in xrange(len(node.inputs)):
                     print >> sio, 'std::cerr << " local_str %(ipos)s: " <<'%locals()+' << " " << '.join(["local_str[%s][%s]" % (ipos, x) for x in xrange(nd)])+'<<"\\n";'
                     for ipos in xrange(len(node.outputs)):
@@ -729,7 +729,7 @@ nd_collapse_[i]=0;
             for d in xrange(nd):
                 print >> sio, 'std::cerr << " " << local_dims[%(d)s]; '%locals()
             print >> sio, 'std::cerr << "\\n";'
-
+            if nd > 0:
                 for ipos in xrange(len(node.inputs)):
                     print >> sio, 'std::cerr << " local_str %(ipos)s: " <<'%locals()+' << " " << '.join(["local_str[%s][%s]"%(ipos, x) for x in xrange(nd)])+'<<"\\n";'
                     for ipos in xrange(len(node.outputs)):