diff --git a/imperative/python/megengine/functional/nn.py b/imperative/python/megengine/functional/nn.py
index f2e9656f..4e724838 100644
--- a/imperative/python/megengine/functional/nn.py
+++ b/imperative/python/megengine/functional/nn.py
@@ -697,20 +697,19 @@ def avg_pool2d(
     Refer to :class:`~.AvgPool2d` for more information.
 
     Args:
-        inp: input tensor of shape :math:`(N, C, H_{in}, W_{in})`.
+        inp: input tensor of shape :math:`(N, C, H_{\text{in}}, W_{\text{in}})` .
         kernel_size: size of the window used to calculate the average value.
-        stride: stride of the window. If not provided, its value is set to ``kernel_size``.
-            Default: ``None``
-        padding: implicit zero padding added on both sides. Default: :math:`0`
+        stride: stride of the window. Default value is ``kernel_size``.
+        padding: implicit zero padding added on both sides. Default: 0.
         mode: whether to include the padding values while calculating the average, set
             to "average" will do counting.
             Default: "average_count_exclude_padding"
 
     Returns:
-        output tensor of shape `(N, C, H_{out}, W_{out})`.
+        output tensor of shape :math:`(N, C, H_{\text{out}}, W_{\text{out}})`.
 
     Examples:
-        >>> input = tensor(np.arange(1 * 1 * 3 * 4).astype(np.float32).reshape(1, 1, 3, 4))
+        >>> input = Tensor(np.arange(1 * 1 * 3 * 4).astype(np.float32).reshape(1, 1, 3, 4))
         >>> F.avg_pool2d(input, kernel_size=2, stride=2, padding=[1,0], mode="average")
             Tensor([[[[0.25 1.25]
              [6.5  8.5 ]]]], device=xpux:0)
diff --git a/imperative/python/megengine/module/pooling.py b/imperative/python/megengine/module/pooling.py
index e52987ba..f089ea95 100644
--- a/imperative/python/megengine/module/pooling.py
+++ b/imperative/python/megengine/module/pooling.py
@@ -69,9 +69,9 @@ class MaxPool2d(_PoolNd):
 class AvgPool2d(_PoolNd):
     r"""Applies a 2D average pooling over an input.
 
-    For instance, given an input of the size :math:`(N, C, H, W)` and
+    For instance, given an input of the size :math:`(N, C, H_{\text{in}}, W_{\text{in}})` and
     :attr:`kernel_size` :math:`(kH, kW)`, this layer generates the output of
-    the size :math:`(N, C, H_{out}, W_{out})` through a process described as:
+    the size :math:`(N, C, H_{\text{out}}, W_{\text{out}})` through a process described as:
 
     .. math::
 
@@ -83,10 +83,10 @@ class AvgPool2d(_PoolNd):
 
     Args:
         kernel_size: the size of the window.
-        stride: the stride of the window. Default value is kernel_size。
-        padding: implicit zero padding to be added on both sides.
-        mode: whether to count padding values. "average" mode will do counting and
-            "average_count_exclude_padding" mode won't do counting.
+        stride: the stride of the window. Default value is ``kernel_size``.
+        padding: implicit zero padding to be added on both sides.Default: 0.
+        mode: whether to include the padding values while calculating the average, set
+            to "average" will do counting.
             Default: "average_count_exclude_padding"
     """