Merge pull request #4611 from Sentient07/CrashFix#1

theano/gpuarray/elemwise.py

@@ -75,10 +75,11 @@ class GpuElemwise(HideC, Elemwise):
             pass
         try:
             support_code = self.scalar_op.c_support_code()
-            if (support_code.strip() != "#define THEANO_MACRO_MOD(x,y) (x % y)" and
-                    support_code.strip() != ""):
+            if "struct" in support_code:
                 # The macro is fine, the C++ struct is not.
-                raise SupportCodeError(support_code)
+                raise SupportCodeError(
+                    "struct aren't supported in GpuElemwise support_code" +
+                    support_code)
         except MethodNotDefined:
             pass
 

theano/gpuarray/opt.py

@@ -881,6 +881,10 @@ def local_gpua_softmaxwithbias(node, context_name):
 @register_opt('fast_compile')
 @op_lifter([theano.tensor.opt.Assert])
 def local_assert(node, context_name):
+
+    # Check if input nodes are already on the GPU
+    if isinstance(node.inputs[0].type, GpuArrayType):
+        return
     return [host_from_gpu(node.op(as_gpuarray_variable(node.inputs[0],
                                                        context_name),
                                   *node.inputs[1:]))]
@@ -946,7 +950,7 @@ def local_lift_abstractconv2d(node, context_name):
     return [node.op(*inps)]
 
 # Register this here so that it goes after the abstract lifting
-register_opt()(conv_groupopt)
+register_opt('fast_compile')(conv_groupopt)
 
 
 @register_opt("low_memory")

theano/tensor/opt.py

@@ -1031,6 +1031,8 @@ class ShapeFeature(object):
             # don't make the optimizer merge a zillion ones together
             # by always returning the same object to represent 1
             return self.lscalar_one
+        if type(s_i) is float and int(s_i) == s_i:
+            s_i = int(s_i)
         if (type(s_i) in integer_types or
                 isinstance(s_i, numpy.integer) or
                 (isinstance(s_i, numpy.ndarray) and s_i.ndim == 0)):