!49333 modify adaptivemaxpool3d docs

Merge pull request !49333 from 范吉斌/code_docs_maxpool

docs/api/api_python/nn/mindspore.nn.AdaptiveMaxPool3d.rst

@@ -3,10 +3,10 @@ mindspore.nn.AdaptiveMaxPool3d
 
 .. py:class:: mindspore.nn.AdaptiveMaxPool3d(output_size, return_indices=False)
 
-    对输入Tensor，提供三维自适应最大池化操作。对于任何输入尺寸，输出的大小为 :math:`(D, H, W)` 。输出特征的数量与输入特征的数量相同。
+    对输入Tensor执行三维自适应最大池化操作。对于任何输入尺寸，输出的size为 :math:`(D, H, W)` 。
 
     参数：
-        - **output_size** (Union[int, tuple]) - 表示输出特征图的尺寸，输入可以是tuple :math:`(D, H, W)`，也可以是一个int值D来表示输出尺寸为 :math:`(D, D, D)` 。:math:`D` ， :math:`H` 和 :math:`W` 可以是int型整数或者None，其中None表示输出大小与对应的输入的大小相同。
+        - **output_size** (Union[int, tuple]) - 指定输出的size。可以用一个整数统一表示输出的深度、高度和宽度，或者用一个整数三元组来分别表示输出的深度、高度和宽度。指定的值必须是正整数。如果是None则表示对应维度输出和输入size相同。
         - **return_indices** (bool) - 如果 `return_indices` 为True，将会输出最大值对应的索引，否则不输出索引。默认为False。
 
     输入：

docs/api/api_python/ops/mindspore.ops.func_adaptive_max_pool3d.rst

@@ -3,11 +3,11 @@ mindspore.ops.adaptive_max_pool3d
 
 .. py:function:: mindspore.ops.adaptive_max_pool3d(input, output_size, return_indices=False)
 
-    对由多个平面组成的的输入Tensor，应用三维的自适应最大池化操作。对于任何输入尺寸，指定输出的尺寸都为 :math:`(D, H, W)`，但是输入和输出特征的数目不会变化。
+    对输入Tensor执行三维的自适应最大池化操作。对于任何输入尺寸，指定输出的size都为 :math:`(D, H, W)`。
 
     参数：
         - **input** (Tensor) - shape为 :math:`(C, D, H, W)` 或 :math:`(N，C, D, H, W)` 的Tensor，支持的数据类型包括int8、int16、int32、int64、uint8、uint16、uint32、uint64、float16、float32、float64。
-        - **output_size** (Union[int, tuple]) - 表示输出特征图的尺寸，输入可以是个tuple :math:`(D, H, W)`，也可以是一个int值D来表示输出尺寸为 :math:`(D, D, D)` 。:math:`D` ， :math:`H` 和 :math:`W` 可以是int型整数或者None，其中None表示输出大小与对应的输入的大小相同。
+        - **output_size** (Union[int, tuple]) - 指定输出的size。可以用一个整数统一表示输出的深度、高度和宽度，或者用一个整数三元组来分别表示输出的深度、高度和宽度。指定的值必须是正整数。如果是None则表示对应维度输出和输入size相同。
         - **return_indices** (bool，可选) - 如果 `return_indices` 为True，将会输出最大值对应的索引，否则不输出索引。默认值为False。
 
     返回：

mindspore/python/mindspore/nn/layer/pooling.py

@@ -1131,16 +1131,14 @@ class AdaptiveMaxPool2d(Cell):
 
 class AdaptiveMaxPool3d(Cell):
     r"""
-    Applies a 3D adaptive max pooling over an input signal composed of several input planes.
-
-    The output is of size :math:`(D, H, W)`, for any input size.
-    The number of output features is equal to the number of input planes.
+    Calculates the 3D adaptive max pooling for an input Tensor.
+    That is, for any input size, the size of the specified output is :math:`(D, H, W)`.
 
     Args:
-        output_size (Union[int, tuple]): The target output size is :math:`(D, H, W)`.
-            `ouput_size` can be a tuple with 3 elements, or a single D for :math:`(D, D, D)`. :math:`D`,
-            :math:`H` and :math:`W` can be int or None which means the output size is the same as that of
-            the input.
+        output_size (Union[int, tuple]): The specified output size, which is an integer that represents depth,
+            height and width, or a tuple of three int numbers that represent depth, height and width respectively.
+            The value must be a positive integer. If it is None, the output size and input size of the corresponding
+            dimension are the same.
         return_indices (bool): If `return_indices` is True, the indices of max value would be output.
             Default: False.
 

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

@@ -706,17 +706,16 @@ def adaptive_max_pool2d(input, output_size, return_indices=False):
 
 def adaptive_max_pool3d(input, output_size, return_indices=False):
     r"""
-    Applies a 3D adaptive max pooling over an input signal composed of several input planes.
-
-    The output is of size :math:`(D, H, W)`, for any input size.
-    The number of output features is equal to the number of input planes.
+    Calculates the 3D adaptive max pooling for an input Tensor.
+    That is, for any input size, the size of the specified output is :math:`(D, H, W)`.
 
     Args:
         input (Tensor): Tensor, with shape :math:`(C, D, H, W)` or :math:`(N, C, D, H, W)`, which support int8, int16,
             int32, int64, uint8, uint16, uint32, uint64, float16, float32 or float64 data type.
-        output_size (Union[int, tuple]): The target output size. `ouput_size` can be a tuple :math:`(D, H, W)`,
-            or an int D for :math:`(D, D, D)`. :math:`D`, :math:`H` and :math:`W` can be int or None
-            which means the output size is the same as that of the input.
+        output_size (Union[int, tuple]): The specified output size, which is an integer that represents depth,
+            height and width, or a tuple of three int numbers that represent depth, height and width respectively.
+            The value must be a positive integer. If it is None, the output size and input size of the corresponding
+            dimension are the same.
         return_indices (bool, optional): If `return_indices` is True, the indices of max value would be output,
             else would not be output. Default: False.