!49855 fix deform_convd docs

Merge pull request !49855 from zhangyinxia/master

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

@@ -50,9 +50,3 @@ mindspore.ops.deformable_conv2d
 
     .. note::
         - 这是一个实验性质的接口，将来有可能被修改或删除。
-        - 在Ascend平台上，目前仅支持AI-CORE的实现，因此有如下条件限制：
-
-          - :math:`C_{in}` 能被8整除。
-          - `deformable_groups` 必须等于1。
-          - `offsets` 的数据是浮点数类型（即需要包含小数部分）。
-          - `kernel_size` 需要满足 :math:`3 * kernel\_size[0] * kernel\_size[1] > 8`。

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

@@ -2597,13 +2597,6 @@ def deformable_conv2d(x, weight, offsets, kernel_size, strides, padding, bias=No
 
     Note:
         - This is an experimental interface that is subject to change or deletion.
-        - For Ascend platform, only AI-CORE kernel is implemented, which has the following limitations:
-
-          - :math:`C_{in}` cannot be divisible by 8 is not supported, e.g. `x` is :math:`(N, 2, H_{in}, W_{in})`.
-          - `deformable_groups` must equal to 1.
-          - `offsets` value is float which does not contain a decimal part is not supported, e.g. `offsets` is assigned
-            with "numpy.ones()".
-          - `kernel_size` should meet the requirement::math:`3 * kernel\_size[0] * kernel\_size[1] > 8`.
 
     Supported Platforms:
         ``Ascend`` ``GPU`` ``CPU``