Small fix according to the pull request comments

doc/library/tensor/nnet/conv.txt

@@ -36,6 +36,11 @@ TODO: Give examples for how to use these things! They are pretty complicated.
       that it requires CUDA >= 5.0, scikits.cuda >= 0.5.0 and PyCUDA to run.
     - :func:`conv3d_fft <theano.sandbox.cuda.fftconv.conv3d_fft>`
       This is the same as conv2d_fft but with 3d data instead.
+       You can enable it by setting THEANO_FLAGS to
+      'optimizer_including=conv3d_fft:convgrad3d_fft:convtransp3d_fft'
+      in your environement.  This is not enabled by default because it
+      has some restrictions on input and uses more memory.  Also note
+      that it requires CUDA >= 5.0, scikits.cuda >= 0.5.0 and PyCUDA to run.
     - :func:`conv3D <theano.tensor.nnet.Conv3D.conv3D>`. Doesn't work on the GPU.
     - :func:`conv3d2d <theano.tensor.nnet.conv3d2d.conv3d>`
       Another conv3d implementation that uses the conv2d with data reshaping.

theano/sandbox/cuda/opt.py

@@ -80,9 +80,6 @@ def register_opt(*tags, **kwargs):
         return local_opt
     return f
 
-
-
-
 #register local_track_shape_i at this level too
 #to make multi-level lift of shape work.
 register_opt()(theano.tensor.opt.local_track_shape_i)
@@ -1121,6 +1118,7 @@ def local_gpu_softmax_with_bias(node):
 #### Convolution, maxpooling
 from theano.tensor.nnet import conv
 
+
 @register_opt()
 @local_optimizer([gpu_from_host, conv.ConvOp])
 def local_gpu_conv(node):