More fixes to doc syntax.

doc/library/tensor/basic.txt

@@ -750,8 +750,10 @@ Creating Tensor
 
 .. function:: stack(*tensors)
 
-    .. warning:: The interface stack(*tensors) is deprecated! 
-             Use stack(tensors, axis=0) instead.
+    .. warning::
+
+        The interface `stack(*tensors)` is deprecated!  Use
+        `stack(tensors, axis=0)` instead.
 
     Stack tensors in sequence vertically (row wise).
 
@@ -1773,6 +1775,7 @@ Gradient / Differentiation
 
 .. automodule:: theano.gradient
     :members: grad
+    :noindex:
 
 See the :ref:`gradient <libdoc_gradient>` page for complete documentation
 of the gradient module.

doc/tutorial/debug_faq.txt

@@ -181,7 +181,7 @@ of error can thus be identified with much more precision and much earlier in
 the compilation pipeline. For example, running the above code yields the
 following error message, which properly identifies *line 24* as the culprit.
 
-.. code-block:: node
+.. code-block:: none
 
     Traceback (most recent call last):
       File "test2.py", line 24, in <module>

doc/tutorial/extending_theano_c.txt

@@ -878,7 +878,7 @@ pre-defined macros.  These section tags have no macros: ``init_code``,
 discussed below.
 
 *      ``APPLY_SPECIFIC(str)`` which will automatically append a name
-       unique to the :ref:`Apply node that applies the Op at the end
+       unique to the :ref:`Apply` node that applies the Op at the end
        of the provided ``str``. The use of this macro is discussed
        futher below.
 

theano/gradient.py

@@ -371,58 +371,51 @@ def grad(cost, wrt, consider_constant=None,
     see :mod:`gradient`. For information on how to implement the gradient of
     a certain Op, see :func:`grad`.
 
-    :type cost: Scalar (0-dimensional) tensor variable.
-        May optionally be None if known_grads is provided.
-    :param cost: a scalar with respect to which we are differentiating
+    Parameters
+    ----------
+    cost : scalar (0-dimensional) tensor variable or None
+        Value with respect to which we are differentiating.  May be
+        `None` if known_grads is provided.
+    wrt : variable or list of variables
+        term[s] for which we want gradients
+    consider_constant : list of variables
+        expressions not to backpropagate through
+    disconnected_inputs : {'ignore', 'warn', 'raise'}
+        Defines the behaviour if some of the variables in `wrt` are
+        not part of the computational graph computing `cost` (or if
+        all links are non-differentiable). The possible values are:
 
-    :type wrt: Tensor variable or list of variables.
-    :param wrt: term[s] for which we want gradients
-
-    :type consider_constant: list of variables
-    :param consider_constant: a list of expressions not to backpropagate
-        through
-
-    :type disconnected_inputs: string
-    :param disconnected_inputs: Defines the behaviour if some of the variables
-        in ``wrt`` are not part of the computational graph computing ``cost``
-        (or if all links are non-differentiable). The possible values are:
         - 'ignore': considers that the gradient on these parameters is zero.
         - 'warn': consider the gradient zero, and print a warning.
         - 'raise': raise DisconnectedInputError.
-
-    :type add_names: bool
-    :param add_names: If True, variables generated by grad will be named
-        (d<cost.name>/d<wrt.name>) provided that both cost and wrt have
-        names
-
-    :type known_grads: dict
-    :param known_grads: If not None, a dictionary mapping variables to their
-            gradients. This is useful in the case where you know the
-            gradient on some variables but do not know the original
-            cost.
-
-    :type return_disconnected: string
-    :param return_disconnected:
+    add_names : bool
+        If True, variables generated by grad will be named
+        (d<cost.name>/d<wrt.name>) provided that both cost and wrt
+        have names
+    known_grads : dict, optional
+        A dictionary mapping variables to their gradients. This is
+        useful in the case where you know the gradient on some
+        variables but do not know the original cost.
+    return_disconnected : {'zero', 'None', 'Disconnected'}
         - 'zero' : If wrt[i] is disconnected, return value i will be
                    wrt[i].zeros_like()
         - 'None' : If wrt[i] is disconnected, return value i will be
                    None
         - 'Disconnected' : returns variables of type DisconnectedType
+    null_gradients : {'raise', 'return'}
+        Defines the behaviour if some of the variables in `wrt` have a
+        null gradient. The possibles values are:
 
-    :type null_gradients: string
-    :param null_gradients: Defines the behaviour if some of the variables in
-            ``wrt`` have a null gradient. The possibles values are :
         - 'raise' : raise a NullTypeGradError exception
         - 'return' : return the null gradients
 
-    :rtype: variable or list/tuple of Variables (matching `wrt`)
-
-    :return: symbolic expression of gradient of `cost` with respect to each
-             of the `wrt` terms.
-             If an element of `wrt` is not differentiable with respect
-             to the output, then a zero variable is returned.
-             It returns an object of same type as `wrt`: a list/tuple
-             or Variable in all cases.
+    Returns
+    -------
+    variable or list/tuple of variables (matches `wrt`)
+        symbolic expression of gradient of `cost` with respect to each
+        of the `wrt` terms.  If an element of `wrt` is not
+        differentiable with respect to the output, then a zero
+        variable is returned.
 
     """
     t0 = time.time()

theano/sandbox/cuda/var.py

@@ -126,14 +126,17 @@ class CudaNdarraySharedVariable(_operators, SharedVariable):
 
             * The destination on the GPU must be c_contiguous.
             * The source is on the CPU.
-            * The old value must have the same dtype as the new value (which is
-            a given for now, since only float32 is supported).
+            * The old value must have the same dtype as the new value
+              (which is a given for now, since only float32 is
+              supported).
             * The old and new value must have the same shape.
-            * The old value is being completely replaced by the new value (not
-            partially modified, e.g. by replacing some subtensor of it).
-            * You change the value of the shared variable via set_value, not via
-            the .value accessors. You should not use the .value accessors
-            anyway, since they will soon be deprecated and removed.
+            * The old value is being completely replaced by the new
+              value (not partially modified, e.g. by replacing some
+              subtensor of it).
+            * You change the value of the shared variable via
+              set_value, not via the .value accessors. You should not
+              use the .value accessors anyway, since they will soon be
+              deprecated and removed.
 
         It is also worth mentioning that, for efficient transfer to the GPU,
         Theano will make the new data ``c_contiguous``. This can require an

theano/tensor/nnet/neighbours.py

@@ -14,22 +14,20 @@ from theano.gradient import grad_undefined
 
 class Images2Neibs(Op):
     """
+    Reshapes the input as a 2D tensor where each row is an pooling
+    example.
 
     Parameters
     ----------
     mode : {'valid', 'ignore_borders', 'wrap_centered'}
-        'valid': Requires an input that is a multiple of the
-            pooling factor (in each direction).
-        'ignore_borders': Same as valid, but will ignore the borders
-            if the shape(s) of the input is not a multiple of the pooling
-            factor(s).
-        'wrap_centered' : ?? TODO comment
-
-    Returns
-    -------
-    object
-        Reshapes the input as a 2D tensor where each row is an
-        pooling example.
+        - 'valid' :
+            Requires an input that is a multiple of the pooling factor
+            (in each direction).
+        - 'ignore_borders' :
+            Same as valid, but will ignore the borders if the shape(s)
+            of the input is not a multiple of the pooling factor(s).
+        - 'wrap_centered' :
+            ?? TODO comment
 
     """
 
@@ -429,7 +427,7 @@ class Images2Neibs(Op):
 
 def images2neibs(ten4, neib_shape, neib_step=None, mode='valid'):
     """
-    Function :func:`images2neibs <theano.sandbox.neighbours.images2neibs>`
+    Function :func:`images2neibs <theano.tensor.nnet.neighbours.images2neibs>`
     allows to apply a sliding window operation to a tensor containing
     images or other two-dimensional objects.
     The sliding window operation loops over points in input data and stores
@@ -455,9 +453,6 @@ def images2neibs(ten4, neib_shape, neib_step=None, mode='valid'):
         By default it is equal to `neib_shape` in other words, the patches are
         disjoint. When the step is greater than `neib_shape`, some elements are
         omitted. When None, this is the same as neib_shape (patch are disjoint).
-        .. note:: Currently the step size should be chosen in the way that the
-            corresponding dimension :math:`i` (width or height) is equal to
-            :math:`n * step\_size_i + neib\_shape_i` for some :math:`n`
     mode : {'valid', 'ignore_borders', 'wrap_centered'}
         ``valid``
             Requires an input that is a multiple of the
@@ -489,6 +484,13 @@ def images2neibs(ten4, neib_shape, neib_step=None, mode='valid'):
              these for loops, they're just the easiest way to describe the
              output pattern.
 
+    Notes
+    -----
+    .. note::
+        Currently the step size should be chosen in the way that the
+        corresponding dimension :math:`i` (width or height) is equal
+        to :math:`n * step\_size_i + neib\_shape_i` for some :math:`n`.
+
     Examples
     --------
 
@@ -524,7 +526,7 @@ def neibs2images(neibs, neib_shape, original_shape, mode='valid'):
 
     Parameters
     ----------
-    neibs: matrix
+    neibs : 2d tensor
         Like the one obtained by
         :func:`images2neibs <theano.sandbox.neigbours.neibs2images>`.
     neib_shape