Merge pull request #908 from lamblin/fix_test_neib

theano/sandbox/cuda/neighbours.py

@@ -404,6 +404,7 @@ def gpu_images2neibs(ten4, neib_shape, neib_step=None, mode='valid'):
 @local_optimizer()
 def use_gpu_images2neibs(node):
     if (type(node.op) is Images2Neibs and
+        node.inputs[0].dtype == 'float32' and
         node.op.mode in ['valid', 'wrap_centered']):
         return [host_from_gpu(gpu_images2neibs(gpu_from_host(node.inputs[0]),
                                                node.inputs[1], node.inputs[2],

theano/sandbox/cuda/nvcc_compiler.py

@@ -139,6 +139,7 @@ class NVCC_compiler(object):
                                         default_to_move_computation_to_gpu=False,
                                         move_shared_float32_to_gpu=False,
                                         enable_cuda=False)
+                n = theano.sandbox.cuda.use.device_number
 
             p = theano.sandbox.cuda.device_properties(n)
             flags.append('-arch=sm_' + str(p['major']) + str(p['minor']))

theano/sandbox/cuda/tests/test_neighbours.py

@@ -20,6 +20,7 @@ else:
 class T_GpuImages2Neibs(theano.sandbox.test_neighbours.T_Images2Neibs):
     mode = mode_with_gpu
     op = GpuImages2Neibs
+    dtypes = ['float32']
 
 if __name__ == '__main__':
     unittest.main()

theano/tests/unittest_tools.py

@@ -166,9 +166,11 @@ class T_OpContractMixin(object):
 class InferShapeTester(unittest.TestCase):
     def setUp(self):
         seed_rng()
+        # Take into account any mode that may be defined in a child class
+        mode = getattr(self, 'mode', theano.compile.get_default_mode())
         # This mode seems to be the minimal one including the shape_i
         # optimizations, if we don't want to enumerate them explicitly.
-        self.mode = theano.compile.get_default_mode().including("canonicalize")
+        self.mode = mode.including("canonicalize")
 
     def _compile_and_check(self, inputs, outputs, numeric_inputs, cls,
                            excluding=None):