提交 f9aa6177 authored 作者: Gijs van Tulder's avatar Gijs van Tulder

Fix pooling documentation.

上级 19c1624f
......@@ -13,3 +13,4 @@
.. autofunction:: theano.tensor.signal.pool.pool_2d
.. autofunction:: theano.tensor.signal.pool.max_pool_2d_same_size
.. autofunction:: theano.tensor.signal.pool.pool_3d
......@@ -347,7 +347,7 @@ def pad_dims(input, leftdims, rightdims):
Examples
--------
Given input of shape (3, 5, 7), ``pad_dims(input, 2, 2)``
adds a singleton dimension and reshapes to (3, 1, 5, 7).
adds a singleton dimension and reshapes to (1, 3, 5, 7).
Given that output from pad_dims, ``unpad_dims(output, input, 2, 2)``
reshapes back to (3, 5, 7).
......@@ -355,10 +355,10 @@ def pad_dims(input, leftdims, rightdims):
does not reshape and returns output with shape (3, 5, 7, 9).
Given input of shape (3, 5, 7, 9, 11), ``pad_dims(input, 2, 2)``
combines the first two dimensions and reshapes to (8, 7, 9, 11).
combines the first two dimensions and reshapes to (15, 7, 9, 11).
Given input of shape (3, 5, 7, 9), ``pad_dims(input, 2, 3)``
adds a singleton dimension and reshapes to (3, 1, 5, 7, 9).
adds a singleton dimension and reshapes to (1, 3, 5, 7, 9).
"""
assert input.ndim >= rightdims
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论