Merge pull request #1919 from nouiz/crash_fix_broadcast

theano/sandbox/gpuarray/subtensor.py

@@ -20,7 +20,6 @@ from theano.sandbox.gpuarray.elemwise import GpuElemwise
 from theano.sandbox.gpuarray.comp import NVCC_compiler
 
 
-
 class GpuSubtensor(HideC, Subtensor):
     def make_node(self, x, *inputs):
         rval = tensor.Subtensor.make_node(self, x, *inputs)
@@ -32,15 +31,10 @@ class GpuSubtensor(HideC, Subtensor):
     def perform(self, node, inputs, out_):
         out, = out_
         x = inputs[0]
-        if self.perform_cache_cdata is not None:
-            out[0] = x.__getitem__(self.perform_cache_cdata)
-            return
 
         cdata = get_idx_list(inputs, self.idx_list)
         if len(cdata) == 1:
             cdata = cdata[0]
-        if len(inputs) == 1:
-            self.perform_cache_cdata = cdata
 
         out[0] = x.__getitem__(cdata)
 
@@ -232,7 +226,8 @@ class GpuIncSubtensor(IncSubtensor):
             # scalar case
             if not self.set_instead_of_inc:
                 #x.__setitem__(cdata, sub_x + y)
-                tmp = pygpu.elemwise.elemwise2(sub_x, '+', y,  sub_x, broadcast=False)
+                tmp = pygpu.elemwise.elemwise2(sub_x, '+', y,  sub_x,
+                                               broadcast=False)
                 x.__setitem__(cdata, tmp)
             else:
                 x.__setitem__(cdata, y)
@@ -592,4 +587,4 @@ class GpuAdvancedIncSubtensor1_dev20(GpuAdvancedIncSubtensor1):
                 return;
         }
 
-        """ %locals()
+        """ % locals()

theano/tensor/tests/test_subtensor.py

@@ -88,7 +88,7 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
         f = inplace_func([], t, mode=self.mode)
         topo = f.maker.fgraph.toposort()
         topo_ = [node for node in topo if not isinstance(node.op,
-             self.ignore_topo)]
+                                                         self.ignore_topo)]
         assert len(topo_) == 1
         if not list:
             assert isinstance(topo_[0].op, self.sub)
@@ -365,19 +365,39 @@ class T_subtensor(unittest.TestCase, utt.TestOptimizationMixin):
         f = inplace_func([], gn, mode=self.mode)
         topo = f.maker.fgraph.toposort()
         topo_ = [node for node in topo if not isinstance(node.op,
-             self.ignore_topo)]
+                                                         self.ignore_topo)]
         if not self.fast_compile:
             assert len(topo_) == 6
         assert numpy.sum([isinstance(node.op, self.inc_sub)
-             for node in topo_]) == 1
+                          for node in topo_]) == 1
         assert numpy.sum([isinstance(node.op, self.sub)
-             for node in topo_]) == 1
+                          for node in topo_]) == 1
         gval = f()
 
         good = numpy.zeros_like(data)
         good[subi:, subi] = numpy.exp(data[subi:, subi])
         self.assertTrue(numpy.allclose(gval, good), (gval, good))
 
+    def test_grad_2d_inc_set_subtensor(self):
+        for n_shape, m_shape in [
+            [(2, 3), (2, 2)],
+            [(3, 2), (2, 2)],
+            [(3, 2), (1, 2)],
+            [(3, 2), (2,)],
+        ]:
+            for op in [inc_subtensor, set_subtensor]:
+                subi = 2
+                data = numpy.asarray(rand(*n_shape), dtype=self.dtype)
+                n = self.shared(data)
+                z = scal.constant(subi)
+                m = matrix('m', dtype=self.dtype)
+                mv = numpy.asarray(rand(*m_shape), dtype=self.dtype)
+
+                t = op(n[:z, :z], m)
+                gn, gm = theano.tensor.grad(theano.tensor.sum(t), [n, m])
+                utt.verify_grad(lambda m: op(n[:z, :z], m), [mv])
+                utt.verify_grad(lambda nn: op(nn[:z, :z], mv), [data])
+
     def test_grad_0d(self):
         data = numpy.asarray(rand(2, 3), dtype=self.dtype)
         n = self.shared(data)

theano/tensor/type.py

@@ -643,10 +643,10 @@ theano.compile.register_shape_i_c_code(
         TensorType,
         """
         if(!%(oname)s)
-            %(oname)s=(PyArrayObject*)PyArray_ZEROS(0, NULL, NPY_INT64, 0);
+            %(oname)s=(PyArrayObject*)PyArray_EMPTY(0, NULL, NPY_INT64, 0);
         ((npy_int64*)PyArray_DATA(%(oname)s))[0]=PyArray_DIMS(%(iname)s)[%(i)s];
         """,
-        version=1)
+        version=2)
 
 # Register TensorType C code for DeepCopyOp
 theano.compile.register_deep_copy_op_c_code(