testcode for tensor/nnet/nnet.txt

doc/library/tensor/nnet/nnet.txt

@@ -42,8 +42,10 @@
 
    Example:
 
-   .. code-block:: python
-
+   .. testcode::
+       
+       import theano.tensor as T
+       
        x,y,b = T.dvectors('x','y','b')
        W = T.dmatrix('W')
        y = T.nnet.sigmoid(T.dot(W,x) + b)
@@ -102,7 +104,7 @@
 
    .. note:: The underlying code will return an exact 0 if an element of x is too small.
 
-   .. code-block:: python
+   .. testcode::
 
        x,y,b = T.dvectors('x','y','b')
        W = T.dmatrix('W')
@@ -124,14 +126,14 @@
        optimize this by inserting the softmax op itself.  The code of
        the softmax op is more numeriacaly stable by using this code:
 
-       .. code-block:: python
+       .. testcode::
 
            e_x = exp(x - x.max(axis=1, keepdims=True))
            out = e_x / e_x.sum(axis=1, keepdims=True)
 
    Example of use:
 
-   .. code-block:: python
+   .. testcode::
 
        x,y,b = T.dvectors('x','y','b')
        W = T.dmatrix('W')
@@ -155,7 +157,7 @@
    to the binary cross-entropy (note that this assumes that x will
    contain values between 0 and 1):
 
-   .. code-block:: python
+   .. testcode::
 
        x, y, b = T.dvectors('x', 'y', 'b')
        W = T.dmatrix('W')
@@ -191,7 +193,7 @@
        correct class (which is typically the training criterion in
        classification settings).
 
-   .. code-block:: python
+   .. testcode::
 
        y = T.nnet.softmax(T.dot(W, x) + b)
        cost = T.nnet.categorical_crossentropy(y, o)