better doc

doc/library/sandbox/cuda/dnn.txt

@@ -6,31 +6,33 @@
 
 .. moduleauthor:: LISA
 
-Normally you should not call directly GPU Ops, but the CPU interface
-currently do not allow all options supported by cuDNN ops. So it is
-possible that you need to call them manually.
-
-`cuDNN <https://developer.nvidia.com/cuDNN>`_ is NVIDIA library with
-functionality used by deep neural network. It provide faster
-implementation of some operation like the convolution. cuDNN currently
-is not installed with CUDA 6.5. You must download it and install it
+`cuDNN <https://developer.nvidia.com/cuDNN>`_ is an NVIDIA library with
+functionality used by deep neural network. It provides optimized versions
+of some operations like the convolution. cuDNN is not currently
+installed with CUDA 6.5. You must download and install it
 yourself.
 
 To install it, decompress the downloaded file and make the ``*.h`` and
 ``*.so*`` files available to the compilation environment. On Linux,
-this can be done by setting the environment variable
+this can be done by setting the environment variables
 ``LD_LIBRARY_PATH``, ``LIBRARY_PATH`` and ``CPATH`` to the
-uncompressed directory path. They work the same way as ``PATH``. Or
-you can copy the ``*.h`` files to ``/usr/include`` and the files
-``*.so*`` to ``/lib64``.
+uncompressed directory path. Separate multiple directory with ``:`` as
+the ``PATH`` environment variable. Or you can copy the ``*.h`` files
+to ``/usr/include`` and the ``*.so*`` files to ``/lib64``.
 
 By default, Theano will detect if it can use cuDNN. If so, it will use
-it.  If not, Theano optimization will not introduce cuDNN op. So
+it.  If not, Theano optimizations will not introduce cuDNN ops. So
 Theano will still work if the user did not introduce them manually.
 
-To get an error if Theano can not use cuDNN, use this Theano flags:
+To get an error if Theano can not use cuDNN, use this Theano flag:
 ``optimizer_including=cudnn``.
 
+.. note::
+
+    Normally you should not call GPU Ops directly, but the CPU interface
+    currently does not allow all options supported by cuDNN ops. So it is
+    possible that you will need to call them manually.
+
 
 Functions
 =========

theano/sandbox/cuda/dnn.py

@@ -90,12 +90,13 @@ if ((err = cudnnCreate(&_handle)) != CUDNN_STATUS_SUCCESS) {
 
 
 class GpuDnnConvDesc(GpuOp):
-    """
-    The convolution description.
+    """This Op builds a convolution descriptor for use in the other
+    convolution operations.
 
     :param border_mode: 'valid' or 'full'
     :param subsample: The subsample, tuple like (dx, dy)
     :param conv_mode: 'conv' or 'cross'
+
     """
     __props__ = ('border_mode', 'subsample', 'conv_mode')
 
@@ -446,7 +447,8 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
 
 class GpuDnnPoolDesc(GpuOp):
     """
-    The pooling descriptor.
+    This Op builds a pooling descriptor for use in the other
+    pooling operations.
 
     :param ws: windows size
     :param stride: (dx, dy)