Merge pull request #4947 from ritheshkumar95/docfix

doc/tutorial/conv_arithmetic.txt

@@ -93,8 +93,8 @@ of value
 
 slides across the input feature map. At each location, the product between each
 element of the kernel and the input element it overlaps is computed and the
-results are summed up to obtain the output in the current location. The final 
-output of this procedure is a matrix called *output feature map* (in green). 
+results are summed up to obtain the output in the current location. The final
+output of this procedure is a matrix called *output feature map* (in green).
 
 This procedure can be repeated using different kernels to form as many output
 feature maps (a.k.a. *output channels*) as desired. Note also that to keep the
@@ -114,7 +114,7 @@ If there are multiple input and output feature maps, the collection of kernels
 form a 4D array (``output_channels, input_channels, filter_rows,
 filter_columns``). For each output channel, each input channel is convolved with
 a distinct part of the kernel and the resulting set of feature maps is summed
-elementwise to produce the corresponding output feature map. The result of this 
+elementwise to produce the corresponding output feature map. The result of this
 procedure is a set of output feature maps, one for each output channel, that is
 the output of the convolution.
 
@@ -627,7 +627,7 @@ for the other elements of the image, giving rise to the following relationship:
 
     .. code-block:: python
 
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, filter_shape=(c1, c2, k1, k2), border_mode=(0, 0),
             subsample=(1, 1))
         # input.shape[2] == output.shape[2] + (k1 - 1)
@@ -667,7 +667,7 @@ Formally, the following relationship applies for zero padded convolutions:
 
     .. code-block:: python
 
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, filter_shape=(c1, c2, k1, k2), border_mode=(p1, p2),
             subsample=(1, 1))
         # input.shape[2] == output.shape[2] + (k1 - 1) - 2 * p1
@@ -704,7 +704,7 @@ applies:
 
     .. code-block:: python
 
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, filter_shape=(c1, c2, k1, k2), border_mode='half',
             subsample=(1, 1))
         # input.shape[2] == output.shape[2]
@@ -740,7 +740,7 @@ the transpose of a fully padded convolution is a non-padded convolution:
 
     .. code-block:: python
 
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, filter_shape=(c1, c2, k1, k2), border_mode='full',
             subsample=(1, 1))
         # input.shape[2] == output.shape[2] - (k1 - 1)
@@ -799,7 +799,7 @@ of :math:`s`. In that case, the following relationship holds:
 
     .. code-block:: python
 
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, filter_shape=(c1, c2, k1, k2), border_mode=(0, 0),
             subsample=(s1, s2))
         # input.shape[2] == s1 * (output.shape[2] - 1) + k1
@@ -832,7 +832,7 @@ combining :ref:`Relationship 8 <Relationship8>` and
 
         o_prime1 = s1 * (output.shape[2] - 1) + k1 - 2 * p1
         o_prime2 = s2 * (output.shape[3] - 1) + k2 - 2 * p2
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, input_shape=(b, c1, o_prime1, o_prime2),
             filter_shape=(c1, c2, k1, k2), border_mode=(p1, p2),
             subsample=(s1, s2))
@@ -867,7 +867,7 @@ between the :math:`s` different cases that all lead to the same :math:`i'`:
 
         o_prime1 = s1 * (output.shape[2] - 1) + a1 + k1 - 2 * p1
         o_prime2 = s2 * (output.shape[3] - 1) + a2 + k2 - 2 * p2
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, input_shape=(b, c1, o_prime1, o_prime2),
             filter_shape=(c1, c2, k1, k2), border_mode=(p1, p2),
             subsample=(s1, s2))
@@ -934,6 +934,6 @@ Quick reference
 
     .. code-block:: python
 
-        input = theano.tensor.nnet.conv2d_grad_wrt_inputs(
+        input = theano.tensor.nnet.abstract_conv.conv2d_grad_wrt_inputs(
             output, filters, input_shape=(9, 9), filter_shape=(c1, c2, 4, 4),
             border_mode='valid', subsample=(2, 2))