Add and fix docstring.

theano/sandbox/cuda/basic_ops.py

@@ -34,6 +34,9 @@ def as_cuda_array(obj):
         raise TypeError("Don't know how to cast to a CudaNdarray object")
 
 class HostFromGpu(Op):
+    """
+    Implement the transfer from gpu to the cpu.
+    """
     def __eq__(self, other):
         return type(self) == type(other)
     def __hash__(self):
@@ -63,6 +66,9 @@ class HostFromGpu(Op):
 host_from_gpu = HostFromGpu()
 
 class GpuFromHost(Op):
+    """
+    Implement the transfer from cpu to the gpu.
+    """
     def __eq__(self, other):
         return type(self) == type(other)
     def __hash__(self):
@@ -93,6 +99,9 @@ class GpuFromHost(Op):
 gpu_from_host = GpuFromHost()
 
 class GpuElemwise(Op):
+    """
+    Implement a generic elemwise on the gpu.
+    """
     nin = property(lambda self: self.scalar_op.nin)
     nout = property(lambda self: self.scalar_op.nout)
 
@@ -200,6 +209,9 @@ class GpuElemwise(Op):
         return self.src_generator.cache_version
 
 class GpuDimShuffle(Op):
+    """
+    Implement DimShuffle on the gpu.
+    """
     def __init__(self, input_broadcastable, new_order):
         input_broadcastable = tuple(input_broadcastable)
         self.input_broadcastable = input_broadcastable
@@ -1706,6 +1718,9 @@ class GpuSum(Op):
         return sio.getvalue()
 
 class GpuReshape(tensor.Reshape):
+    """
+    Implement Reshape on the gpu.
+    """
     # __hash__, __eq__, __str__ come from tensor.Subtensor
     def make_node(self, x, shp):
         host_reshaped = host_from_gpu(x).reshape(shp,ndim=self.ndim)
@@ -1719,6 +1734,9 @@ class GpuReshape(tensor.Reshape):
         out[0] = x.reshape(tuple(shp))
 
 class GpuSubtensor(tensor.Subtensor):
+    """
+    Implement subtensor on the gpu.
+    """
     # __hash__, __eq__, __str__ come from tensor.Subtensor
     def make_node(self, x, *inputs):
         assert isinstance(x.type, CudaNdarrayType)
@@ -1747,6 +1765,9 @@ class GpuSubtensor(tensor.Subtensor):
         out[0] = x.__getitem__(cdata)
 
 class GpuAdvancedSubtensor1(tensor.AdvancedSubtensor1):
+    """
+    Implement AdvancedSubtensor1 on the gpu.
+    """
     def make_node(self, x, ilist):
         x_ = as_cuda_ndarray_variable(x)
         ilist_ = tensor.as_tensor_variable(ilist)
@@ -1770,6 +1791,9 @@ class GpuAdvancedSubtensor1(tensor.AdvancedSubtensor1):
         out[0] = o
 
 class GpuAdvancedIncSubtensor1(tensor.AdvancedIncSubtensor1):
+    """
+    Implement AdvancedIncSubtensor1 on the gpu.
+    """
     def make_node(self, x, y, ilist):
         x_ = as_cuda_ndarray_variable(x)
         y_ = as_cuda_ndarray_variable(y)
@@ -1795,6 +1819,9 @@ class GpuAdvancedIncSubtensor1(tensor.AdvancedIncSubtensor1):
         # so we use the parent version that loop on each indices.
 
 class GpuIncSubtensor(tensor.IncSubtensor):
+    """
+    Implement IncSubtensor on the gpu.
+    """
     def make_node(self, x, y, *inputs):
         assert isinstance(x.type, CudaNdarrayType)
         assert isinstance(y.type, CudaNdarrayType)
@@ -1802,6 +1829,9 @@ class GpuIncSubtensor(tensor.IncSubtensor):
         return Apply(self, [x,y]+rval.inputs[2:], [x.type()])
 
 class GpuFlatten(tensor.Flatten):
+    """
+    Implement Flatten on the gpu.
+    """
     def make_node(self, x ):
         assert isinstance(x.type, CudaNdarrayType)
         rval = tensor.Flatten.make_node(self, x)
@@ -1810,11 +1840,17 @@ class GpuFlatten(tensor.Flatten):
         return Apply(self, [x], [out_type()])
 
 class GpuShape(tensor.Shape):
+    """
+    Implement Shape on the gpu.
+    """
     def make_node(self, x):
         return Apply(self, [x], [tensor.lvector()])
 gpu_shape = GpuShape()
 
 class GpuJoin(tensor.Join):
+    """
+    Implement Join on the gpu.
+    """
     def make_node(self, *axis_and_tensors):
         axis, tensors = axis_and_tensors[0], axis_and_tensors[1:]
         if not tensors:
@@ -1889,6 +1925,9 @@ class GpuJoin(tensor.Join):
 gpu_join = GpuJoin()
 
 class GpuAlloc(Op):
+    """
+    Implement Alloc on the gpu.
+    """
     def __init__(self):
         pass
 
@@ -1967,7 +2006,12 @@ class GpuAlloc(Op):
 
 gpu_alloc = GpuAlloc()
 
+
 class GpuContiguous(Op):
+    """
+    Always return a c contiguous output. Copy the input only if it is
+    not already c contiguous.
+    """
     view_map = {0: [0]}
 
     def __eq__(self, other):

theano/sandbox/cuda/blas.py

@@ -6,6 +6,9 @@ import cuda_ndarray.cuda_ndarray as cuda
 from theano.sandbox.cuda.type import CudaNdarrayType
 
 class GpuDot22(Op):
+    """
+    Implement dot(2d, 2d) on the gpu.
+    """
     def __str__(self):
         return 'GpuDot22'
     def __eq__(self, other):
@@ -74,6 +77,9 @@ class GpuDot22(Op):
 gpu_dot22 = GpuDot22()
 
 class GpuDot22Scalar(Op):
+    """
+    Implement dot(2d, 2d) * scalar on the gpu.
+    """
     def __str__(self):
         return 'GpuDot22Scalar'
     def __eq__(self, other):
@@ -434,6 +440,7 @@ gpu_ger_no_inplace = GpuGer(inplace=False)
 gpu_ger_inplace = GpuGer(inplace=True)
 
 class GpuOuter(Op):
+    """ Implement outer on the gpu."""
     def make_node(self, x, y):
         # we suppose type checking has been done, but make sure.
         assert (x.type.ndim == 1 and y.type.ndim == 1 and
@@ -526,6 +533,9 @@ gpu_outer = GpuOuter()
 # Not really a BLAS operation, but whatever.
 #
 class GpuConv(Op):
+    """
+    Implement the batched and stacked 2d convolution on the gpu.
+    """
     @staticmethod
     def logical_output_shape_2d(imshp, kshp, mode):
         if mode == 'valid':
@@ -689,6 +699,9 @@ class GpuConv(Op):
 
 
 class GpuDownsampleFactorMax(Op):
+    """
+    Implement downsample with max on the gpu.
+    """
     def __init__(self, ds, ignore_border=False):
         self.ds = tuple(ds)
         self.ignore_border = ignore_border
@@ -846,6 +859,9 @@ class GpuDownsampleFactorMax(Op):
         """ % locals()
 
 class GpuDownsampleFactorMaxGrad(Op):
+    """
+    Implement the grad of downsample with max on the gpu.
+    """
     def __init__(self, ds, ignore_border):
         self.ds = tuple(ds)
         self.ignore_border = ignore_border

theano/sandbox/cuda/nnet.py

@@ -6,7 +6,11 @@ from theano.sandbox.cuda.type import CudaNdarrayType
 
 from theano.sandbox.cuda.kernel_codegen import nvcc_kernel, inline_reduce_max, inline_reduce_sum, inline_softmax
 
+
 class GpuCrossentropySoftmaxArgmax1HotWithBias (Op):
+    """
+    Implement CrossentropySoftmaxArgmax1HotWithBias on the gpu.
+    """
     nin=3
     nout=3
     def __eq__(self, other):
@@ -177,6 +181,9 @@ class GpuCrossentropySoftmaxArgmax1HotWithBias (Op):
 gpu_crossentropy_softmax_argmax_1hot_with_bias = GpuCrossentropySoftmaxArgmax1HotWithBias()
 
 class GpuCrossentropySoftmax1HotWithBiasDx (Op):
+    """
+    Implement CrossentropySoftmax1HotWithBiasDx on the gpu.
+    """
     nin=3
     nout=1
     """Gradient wrt x of the CrossentropySoftmax1Hot Op"""
@@ -296,7 +303,9 @@ class GpuCrossentropySoftmax1HotWithBiasDx (Op):
 gpu_crossentropy_softmax_1hot_with_bias_dx = GpuCrossentropySoftmax1HotWithBiasDx()
 
 class GpuSoftmax (Op):
-    """Writeme"""
+    """
+    Implement Softmax on the gpu.
+    """
     def __eq__(self, other):
         return type(self) == type(other)
     def __hash__(self):
@@ -392,7 +401,9 @@ class GpuSoftmax (Op):
 gpu_softmax = GpuSoftmax()
 
 class GpuSoftmaxWithBias (Op):
-    """Writeme"""
+    """
+    Implement SoftmaxWithBias on the gpu.
+    """
     nin = 2
     nout = 1
     def __eq__(self, other):

theano/sandbox/cuda/rng_curand.py

@@ -247,7 +247,8 @@ class CURAND_Uniform(CURAND_Base):
 
 
 class CURAND_RandomStreams(object):
-    """RandomStreams instance that creates CURAND-based random variables.
+    """
+    RandomStreams instance that creates CURAND-based random variables.
 
     One caveat is that generators are not serializable.
     """