Made the suggested changes

theano/sandbox/cuda/basic_ops.py

@@ -121,7 +121,6 @@ class GpuFromHost(GpuOp):
 
     check_input = False
 
-    __props__ = ()
 
     def make_node(self, x):
         if not isinstance(x.type, tensor.TensorType):
@@ -178,8 +177,6 @@ class GpuElemwise(GpuOp):
 
     """
 
-    __props__ = ("scalar_op", "inplace_pattern", "sync", )
-
     nin = property(lambda self: self.scalar_op.nin)
     nout = property(lambda self: self.scalar_op.nout)
 
@@ -231,6 +228,12 @@ class GpuElemwise(GpuOp):
         assert h == getattr(self, '_hashval', h)
         self._hashval = h
 
+    def __eq__(self, other):
+        return (type(self) == type(other) and
+                self.scalar_op == other.scalar_op and
+                self.inplace_pattern == other.inplace_pattern and
+                self.sync == other.sync)
+
     def __hash__(self):
         return self._hashval
 
@@ -309,9 +312,9 @@ class GpuDimShuffle(GpuOp):
 
     check_broadcast = False
 
-    __props__ = ("input_broadcastable", "inplace", "new_order")
+    __props__ = ("input_broadcastable", "new_order")
 
-    def __init__(self, input_broadcastable, inplace, new_order):
+    def __init__(self, input_broadcastable, new_order):
         input_broadcastable = tuple(input_broadcastable)
         self.input_broadcastable = input_broadcastable
         self.new_order = tuple(new_order)

theano/sandbox/cuda/blas.py

@@ -2207,6 +2207,9 @@ class GpuDownsampleFactorMax(GpuOp):
     Implement downsample with max on the gpu.
 
     """
+
+    __props__ = ('ds', 'ignore_border')
+
     def __init__(self, ds, ignore_border=False):
         self.ds = tuple(ds)
         self.ignore_border = ignore_border

theano/sandbox/cuda/opt.py

@@ -288,7 +288,7 @@ def local_gpu_elemwise_0(node):
                     new_op = GpuElemwise(erfcx_gpu)
                 else:
                     try:
-                        new_op = GpuElemwise(**node.op._props_dict())
+                        new_op = GpuElemwise(node.op.scalar_op)
                     except SupportCodeError:
                         # This happens when scalar_op requires support code
                         return False
@@ -398,9 +398,6 @@ def local_gpu_dimshuffle_0(node):
         input, = node.inputs
         if input.owner and isinstance(input.owner.op, HostFromGpu):
             # move the add to a GpuAdd
-            if 'inplace' in node.op._props_dict():
-                import pdb
-                pdb.set_trace()
             new_op = GpuDimShuffle(**node.op._props_dict())
             return [host_from_gpu(new_op(as_cuda_ndarray_variable(input)))]
     if isinstance(node.op, GpuFromHost):
@@ -1130,7 +1127,7 @@ def local_gpu_advanced_incsubtensor1(node):
             compute_capability = device_properties(active_device_no)['major']
             if (compute_capability < 2 or y.ndim != 2 or x.ndim != 2):
 
-                gpu_op = tensor.AdvancedIncSubtensor1(**node.op._props_dict())
+                gpu_op = GpuAdvancedIncSubtensor1(set_instead_of_inc=set_instead_of_inc)
             else:
                 gpu_op = theano.sandbox.cuda.basic_ops.GPUAdvancedIncSubtensor1_dev20(**node.op._props_dict())
             return [gpu_op(as_cuda_ndarray_variable(x),
@@ -1915,7 +1912,7 @@ def local_gpu_downsample_factor_max(node):
         if (pad) != (0, 0) or node.op.mode != 'max' or stride != ws:
             return
         if (x.owner and isinstance(x.owner.op, HostFromGpu)):
-            gpu_ds = GpuDownsampleFactorMax(node.op.ds, node.op.ignore_border)
+            gpu_ds = GpuDownsampleFactorMax(**node.op._props_dict())
             return [host_from_gpu(gpu_ds(x.owner.inputs[0]))]
 
 

theano/tensor/elemwise.py

@@ -140,7 +140,11 @@ class DimShuffle(Op):
         self.input_broadcastable = input_broadcastable
         new_order = tuple(new_order)
         self.new_order = new_order
-        self.inplace = inplace
+        if inplace is True:
+            self.inplace = inplace
+            self._props_dict().pop('inplace')
+        else:
+            raise ValueError("DimShuffle is inplace by default and hence the inplace for DimShuffle must be true")
 
         for i, j in enumerate(new_order):
             if j != 'x':
@@ -503,8 +507,6 @@ second dimension
 
     """
 
-    __props__ = ("scalar_op", "inplace_pattern")
-
     def __init__(self, scalar_op, inplace_pattern=None, name=None,
                  nfunc_spec=None, openmp=None):
         if inplace_pattern is None:
@@ -800,7 +802,7 @@ second dimension
                 # dimensions
                 res = theano.tensor.constant(numpy.asarray(r.data),
                                              dtype=r.type.dtype)
-                return DimShuffle((), ['x'] * nd, inplace=False)(res)
+                return DimShuffle((), ['x'] * nd)(res)
 
             new_r = Elemwise(node.op, {})(
                 *[transform(ipt) for ipt in node.inputs])

theano/tensor/opt.py

@@ -561,8 +561,7 @@ def local_dimshuffle_lift(node):
         new_inputs = []
         for inp in inode.inputs:
             new_inp = op.__class__(inp.type.broadcastable,
-                                   op.new_order,
-                                   op.inplace)(inp)
+                                   op.new_order)(inp)
             new_inputs.append(apply_local_dimshuffle_lift(new_inp))
         copy_stack_trace(node.outputs[0], new_inputs)
         ret = inode.op(*new_inputs, **dict(return_list=True))
@@ -570,14 +569,12 @@ def local_dimshuffle_lift(node):
     if inode and isinstance(inode.op, DimShuffle):
         new_order = [x == 'x' and 'x' or inode.op.new_order[x] for x in
                      new_order]
-        inplace = op.inplace and inode.op.inplace
         input = inode.inputs[0]
 
     if is_dimshuffle_useless(new_order, input):
         return [input]
     elif inode and isinstance(inode.op, DimShuffle):
-        ret = op.__class__(input.type.broadcastable, new_order,
-                           inplace)(input)
+        ret = op.__class__(input.type.broadcastable, new_order)(input)
         ret = apply_local_dimshuffle_lift(ret)
         copy_stack_trace(node.outputs[0], ret)
         return [ret]