From 2cdfd2e25ca73f1a6a60d57d220298446167de27 Mon Sep 17 00:00:00 2001 From: suytingwan Date: Sat, 28 Dec 2019 15:25:59 +0800 Subject: [PATCH] Fix doc for pool op. (#1689) --- doc/fluid/api_guides/low_level/layers/pooling.rst | 4 ++-- doc/fluid/api_guides/low_level/layers/pooling_en.rst | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/doc/fluid/api_guides/low_level/layers/pooling.rst b/doc/fluid/api_guides/low_level/layers/pooling.rst index 32a2e97ba..56d90c190 100644 --- a/doc/fluid/api_guides/low_level/layers/pooling.rst +++ b/doc/fluid/api_guides/low_level/layers/pooling.rst @@ -20,7 +20,7 @@ PaddlePaddle中有针对定长图像特征的二维(pool2d)、三维卷积(pool3 - ``num_channels``\ : 用来确定输入的\ ``channel``\ 数量，如果未设置参数或设置为\ ``None``\ ，其实际值将自动设置为输入的\ ``channel``\ 数量。 -- ``pooling_type``\ : 接收\ ``avg``\ 和\ ``max``\ 2种类型之一作为pooling的方式，默认值为\ ``max``\ 。其中\ ``max``\ 意为最大池化，即计算池化\ ``filter``\ 区域内的数据的最大值作为输出；而\ ``avg``\ 意为平均池化，即计算池化\ ``filter``\ 区域内的数据的平均值作为输出。 +- ``pool_type``\ : 接收\ ``avg``\ 和\ ``max``\ 2种类型之一作为pooling的方式，默认值为\ ``max``\ 。其中\ ``max``\ 意为最大池化，即计算池化\ ``filter``\ 区域内的数据的最大值作为输出；而\ ``avg``\ 意为平均池化，即计算池化\ ``filter``\ 区域内的数据的平均值作为输出。 - ``pool_stride``\ : 意为池化的\ ``filter``\ 在输入特征图上移动的步长。 @@ -77,4 +77,4 @@ api汇总： api汇总： -- :ref:`cn_api_fluid_layers_sequence_pool` \ No newline at end of file +- :ref:`cn_api_fluid_layers_sequence_pool` diff --git a/doc/fluid/api_guides/low_level/layers/pooling_en.rst b/doc/fluid/api_guides/low_level/layers/pooling_en.rst index f6eea1696..d7fcb53db 100755 --- a/doc/fluid/api_guides/low_level/layers/pooling_en.rst +++ b/doc/fluid/api_guides/low_level/layers/pooling_en.rst @@ -20,7 +20,7 @@ PaddlePaddle has two-dimensional (pool2d), three-dimensional convolution (pool3d - ``num_channels`` : It is used to determine the number of ``channel`` of input. If it is not set or is set to ``None``, its actual value will be automatically set to the ``channel`` quantity of input. -- ``pooling_type`` : It receives one of ``agg`` and ``max`` as the pooling method. The default value is ``max`` . ``max`` means maximum pooling, i.e. calculating the maximum value of the data in the pooled ``filter`` area as output; and ``avg`` means averaging pooling, i.e. calculating the average of the data in the pooled ``filter`` area as output. +- ``pool_type`` : It receives one of ``agg`` and ``max`` as the pooling method. The default value is ``max`` . ``max`` means maximum pooling, i.e. calculating the maximum value of the data in the pooled ``filter`` area as output; and ``avg`` means averaging pooling, i.e. calculating the average of the data in the pooled ``filter`` area as output. - ``pool_stride`` : It is the stride size in which the pooling ``filter`` moves on the input feature map. @@ -77,4 +77,4 @@ one of ``average``, ``sum``, ``sqrt`` and ``max`` to be used as the pooling met related API: -- :ref:`api_fluid_layers_sequence_pool` \ No newline at end of file +- :ref:`api_fluid_layers_sequence_pool` -- GitLab