Fix MaxPool default pad documentation (#59404)

Varal7 · facebook-github-bot · commit c769300301e8 · 2021-06-04T08:32:03.000-07:00
Summary: Fixes #33384 Pull Request resolved: #59404 Reviewed By: albanD Differential Revision: D28879049 Pulled By: Varal7 fbshipit-source-id: 03a86cd347d53ac2d06028b3f213c5b5d5ab7e91
diff --git a/torch/nn/modules/pooling.py b/torch/nn/modules/pooling.py
@@ -105,7 +105,7 @@ class MaxPool2d(_MaxPoolNd):
                                                    \text{stride[1]} \times w + n)
         \end{aligned}
 
-    If :attr:`padding` is non-zero, then the input is implicitly zero-padded on both sides
+    If :attr:`padding` is non-zero, then the input is implicitly padded with negative infinity on both sides
     for :attr:`padding` number of points. :attr:`dilation` controls the spacing between the kernel points.
     It is harder to describe, but this `link`_ has a nice visualization of what :attr:`dilation` does.
 
@@ -179,7 +179,7 @@ class MaxPool3d(_MaxPoolNd):
                                                              \text{stride[1]} \times h + m, \text{stride[2]} \times w + n)
         \end{aligned}
 
-    If :attr:`padding` is non-zero, then the input is implicitly zero-padded on both sides
+    If :attr:`padding` is non-zero, then the input is implicitly padded with negative infinity on both sides
     for :attr:`padding` number of points. :attr:`dilation` controls the spacing between the kernel points.
     It is harder to describe, but this `link`_ has a nice visualization of what :attr:`dilation` does.
 
