!35669 Fix the formula in the docs of deformable_conv2d

Merge pull request !35669 from YuJianfeng/code_docs

docs/api/api_python/ops/mindspore.ops.func_deformable_conv2d.rst

@@ -3,12 +3,14 @@ mindspore.ops.deformable_conv2d
 
 .. py:function:: mindspore.ops.deformable_conv2d(x, weight, offsets, kernel_size, strides, padding, bias=None, dilations=(1, 1, 1, 1), groups=1, deformable_groups=1, modulated=True)
 
-    给定4D的Tensor输入`x` ， `weight` 和 `offsets` ，计算一个2D的可变形卷积。可变形卷积运算可以表达如下：
+    给定4D的Tensor输入 `x` ， `weight` 和 `offsets` ，计算一个2D的可变形卷积。可变形卷积运算可以表达如下：
     可变形卷积v1：
+
     .. math::
         y(p)=\sum_{k=1}^{K}w_{k}\cdot x(p+p_{k}+\Delta{p_{k}})
 
     可变形卷积v2：
+
     .. math::
         y(p)=\sum_{k=1}^{K}w_{k}\cdot x(p+p_{k}+\Delta{p_{k}})\cdot \Delta{m_{k}}
 
@@ -31,6 +33,7 @@ mindspore.ops.deformable_conv2d
     **返回：**
 
     Tensor，一个四维Tensor，表示输出特征图。数据类型与 `x` 相同，数据格式为"NCHW"，shape为 :math:`(N, C_{out}, H_{out}, W_{out})` 。
+
     .. math::
         \begin{array}{ll} \\
             H_{out} = \left \lfloor{\frac{H_{in} + padding[0] + padding[1] - (H_{f} - 1) \times

mindspore/python/mindspore/ops/function/nn_func.py

@@ -277,10 +277,12 @@ def deformable_conv2d(x, weight, offsets, kernel_size, strides, padding, bias=No
     Given 4D tensor inputs `x`, `weight` and `offsets`, compute a 2D deformable convolution. The deformable convolution
     operation can be expressed as follow:
     Deformable Convolution v1:
+
     .. math::
         y(p)=\sum_{k=1}^{K}w_{k}\cdot x(p+p_{k}+\Delta{p_{k}})
 
     Deformable Convolution v2:
+
     .. math::
         y(p)=\sum_{k=1}^{K}w_{k}\cdot x(p+p_{k}+\Delta{p_{k}})\cdot \Delta{m_{k}}
 
@@ -317,6 +319,7 @@ def deformable_conv2d(x, weight, offsets, kernel_size, strides, padding, bias=No
     Returns:
         Tensor, A 4D Tensor of output feature map. With the same type as `x`. With the format "NCHW",
         the shape is :math:`(N, C_{out}, H_{out}, W_{out})`.
+
         .. math::
             \begin{array}{ll} \\
                 H_{out} = \left \lfloor{\frac{H_{in} + padding[0] + padding[1] - (H_{f} - 1) \times