add pdf figures to conv_arith tutorial for pdf doc

doc/tutorial/conv_arithmetic.txt

@@ -77,7 +77,7 @@ in the input).
 
 Here is an example of a discrete convolution:
 
-.. figure:: conv_arithmetic_figures/numerical_no_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/numerical_no_padding_no_strides.*
     :figclass: align-center
 
 The light blue grid is called the *input feature map*. A *kernel* (shaded area)
@@ -149,7 +149,7 @@ For instance, here is a :math:`3 \times 3` kernel applied to a
 :math:`5 \times 5` input padded with a :math:`1 \times 1` border of zeros using
 :math:`2 \times 2` strides:
 
-.. figure:: conv_arithmetic_figures/numerical_padding_strides.gif
+.. figure:: conv_arithmetic_figures/numerical_padding_strides.*
     :figclass: align-center
 
 The analysis of the relationship between convolutional layer properties is eased
@@ -206,7 +206,7 @@ The simplest case to analyze is when the kernel just slides across every
 position of the input (i.e., :math:`s = 1` and :math:`p = 0`).
 Here is an example for :math:`i = 4` and :math:`k = 3`:
 
-.. figure:: conv_arithmetic_figures/no_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/no_padding_no_strides.*
     :figclass: align-center
 
 One way of defining the output size in this case is by the number of possible
@@ -265,7 +265,7 @@ relationship:
 
 Here is an example for :math:`i = 5`, :math:`k = 4` and :math:`p = 2`:
 
-.. figure:: conv_arithmetic_figures/arbitrary_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/arbitrary_padding_no_strides.*
     :figclass: align-center
 
 Special cases
@@ -305,7 +305,7 @@ be a desirable property:
 This is sometimes referred to as *half* (or *same*) padding. Here is an example
 for :math:`i = 5`, :math:`k = 3` and (therefore) :math:`p = 1`:
 
-.. figure:: conv_arithmetic_figures/same_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/same_padding_no_strides.*
     :figclass: align-center
 
 Note that half padding also works for even-valued :math:`k` and for :math:`s >
@@ -347,7 +347,7 @@ possible partial or complete superimposition of the kernel on the input feature
 map is taken into account. Here is an example for :math:`i = 5`, :math:`k = 3`
 and (therefore) :math:`p = 2`:
 
-.. figure:: conv_arithmetic_figures/full_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/full_padding_no_strides.*
     :figclass: align-center
 
 No zero padding, non-unit strides
@@ -359,7 +359,7 @@ the analysis, let's momentarily ignore zero padding (i.e., :math:`s > 1` and
 :math:`p = 0`). Here is an example for :math:`i = 5`, :math:`k = 3` and :math:`s
 = 2`:
 
-.. figure:: conv_arithmetic_figures/no_padding_strides.gif
+.. figure:: conv_arithmetic_figures/no_padding_strides.*
     :figclass: align-center
 
 Once again, the output size can be defined in terms of the number of possible
@@ -428,13 +428,13 @@ that this ambiguity applies only for :math:`s > 1`.
 Here is an example for :math:`i = 5`, :math:`k = 3`, :math:`s = 2` and :math:`p
 = 1`:
 
-.. figure:: conv_arithmetic_figures/padding_strides.gif
+.. figure:: conv_arithmetic_figures/padding_strides.*
     :figclass: align-center
 
 Here is an example for :math:`i = 6`, :math:`k = 3`, :math:`s = 2` and :math:`p
 = 1`:
 
-.. figure:: conv_arithmetic_figures/padding_strides_odd.gif
+.. figure:: conv_arithmetic_figures/padding_strides_odd.*
     :figclass: align-center
 
 Interestingly, despite having different input sizes these convolutions share the
@@ -478,7 +478,7 @@ Convolution as a matrix operation
 Take for example the convolution presented in the *No zero padding, unit
 strides* subsection:
 
-.. figure:: conv_arithmetic_figures/no_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/no_padding_no_strides.*
     :figclass: align-center
 
 If the input and output were to be unrolled into vectors from left to right, top
@@ -572,7 +572,7 @@ Let's consider the convolution of a :math:`3 \times 3` kernel on a :math:`4
 :math:`k = 3`, :math:`s = 1` and :math:`p = 0`). As depicted in the convolution
 below, this produces a :math:`2 \times 2` output:
 
-.. figure:: conv_arithmetic_figures/no_padding_no_strides.gif
+.. figure:: conv_arithmetic_figures/no_padding_no_strides.*
     :figclass: align-center
 
 The transpose of this convolution will then have an output of shape :math:`4
@@ -585,7 +585,7 @@ a :math:`2 \times 2` input padded with a :math:`2 \times 2` border of zeros
 using unit strides (i.e., :math:`i' = 2`, :math:`k' = k`, :math:`s' = 1` and
 :math:`p' = 2`), as shown here:
 
-.. figure:: conv_arithmetic_figures/no_padding_no_strides_transposed.gif
+.. figure:: conv_arithmetic_figures/no_padding_no_strides_transposed.*
     :figclass: align-center
 
 Notably, the kernel's and stride's sizes remain the same, but the input of the
@@ -646,7 +646,7 @@ padded with *less* zeros.
 It is indeed the case, as shown in here for :math:`i = 5`, :math:`k = 4` and
 :math:`p = 2`:
 
-.. figure:: conv_arithmetic_figures/arbitrary_padding_no_strides_transposed.gif
+.. figure:: conv_arithmetic_figures/arbitrary_padding_no_strides_transposed.*
     :figclass: align-center
 
 Formally, the following relationship applies for zero padded convolutions:
@@ -713,7 +713,7 @@ applies:
 Here is an example for :math:`i = 5`, :math:`k = 3` and (therefore) :math:`p =
 1`:
 
-.. figure:: conv_arithmetic_figures/same_padding_no_strides_transposed.gif
+.. figure:: conv_arithmetic_figures/same_padding_no_strides_transposed.*
     :figclass: align-center
 
 Full padding, transposed
@@ -749,7 +749,7 @@ the transpose of a fully padded convolution is a non-padded convolution:
 Here is an example for :math:`i = 5`, :math:`k = 3` and (therefore) :math:`p =
 2`:
 
-.. figure:: conv_arithmetic_figures/full_padding_no_strides_transposed.gif
+.. figure:: conv_arithmetic_figures/full_padding_no_strides_transposed.*
     :figclass: align-center
 
 No zero padding, non-unit strides, transposed
@@ -763,7 +763,7 @@ intuition, which is why transposed convolutions are sometimes called
 
 Here is an example for :math:`i = 5`, :math:`k = 3` and :math:`s = 2`:
 
-.. figure:: conv_arithmetic_figures/no_padding_strides_transposed.gif
+.. figure:: conv_arithmetic_figures/no_padding_strides_transposed.*
     :figclass: align-center
 
 This should help understand what fractional strides involve: zeros
@@ -840,7 +840,7 @@ combining :ref:`Relationship 8 <Relationship8>` and
 Here is an example for :math:`i = 5`, :math:`k = 3`, :math:`s = 2` and :math:`p
 = 1`:
 
-.. figure:: conv_arithmetic_figures/padding_strides_transposed.gif
+.. figure:: conv_arithmetic_figures/padding_strides_transposed.*
     :figclass: align-center
 
 The constraint on the size of the input :math:`i` can be relaxed by introducing
@@ -875,7 +875,7 @@ between the :math:`s` different cases that all lead to the same :math:`i'`:
 Here is an example for :math:`i = 6`, :math:`k = 3`, :math:`s = 2` and :math:`p
 = 1`:
 
-.. figure:: conv_arithmetic_figures/padding_strides_odd_transposed.gif
+.. figure:: conv_arithmetic_figures/padding_strides_odd_transposed.*
     :figclass: align-center
 
 .. [#] Dumoulin, Vincent, and Visin, Francesco. "A guide to convolution