1220 improve cnapi #509
Merged
1220 improve cnapi #509
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fseasy
suggested changes
Dec 20, 2018
| 该函数在神经网络中建立一个全连接层。 它可以同时将多个tensor作为自己的输入，并为每个输入的tensor创立一个变量，称为“权”（weights），等价于一个从每个输入单元到每个输出单元的全连接权矩阵。FC层用每个tensor和它对应的权相乘得到输出tensor。如果有多个输入tensor，那么多个乘法运算将会加在一起得出最终结果。如果 ``bias_attr`` 非空，则会新创建一个偏向变量（bias variable），并把它加入到输出结果的运算中。最后，如果 ``act`` 非空，它也会加入最终输出的计算中。 | ||
| 该函数在神经网络中建立一个全连接层。 它可以同时将多个tensor（ ``input`` 可使用多个tensor组成的一个list，详见参数说明）作为自己的输入，并为每个输入的tensor创立一个变量，称为“权”（weights），等价于一个从每个输入单元到每个输出单元的全连接权矩阵。FC层用每个tensor和它对应的权相乘得到输出tensor。如果有多个输入tensor，那么多个乘法运算将会加在一起得出最终结果。如果 ``bias_attr`` 非空，则会新创建一个偏向变量（bias variable），并把它加入到输出结果的运算中。最后，如果 ``act`` 非空，它也会加入最终输出的计算中。 | ||
| 这个过程可以通过如下公式表现： |
There was a problem hiding this comment.
我认为这个公式没有说得特别清楚：
（1）如果X是一个tensor的list，那么应该明确X是tensor列表，X_i 是列表中一个tensor； 对应的 W是权值列表，W_i 是列表中的一个权值（就是这里很疑惑，现在公式里W_i 与 X_i 做矩阵乘法，但是下面说W又是权值，而不是权值列表）
（2）如果X是一个tensor，这种情况下的公式是怎样的呢？或者说，介绍里说“可以同时是tensor列表”，那是否可以不是“tensor列表”，如果不是，公式是怎样的呢，我觉得需要说清楚
Contributor
|
is PaddlePaddle/Paddle#15681 fix the English version? @haowang101779990 |
Co-Authored-By: haowang101779990 <[email protected]>
shanyi15
approved these changes
Mar 12, 2019
shanyi15
pushed a commit
to shanyi15/FluidDoc
that referenced
this pull request
Mar 22, 2019
* 1220 update cnapi * Apply suggestions from code review Co-Authored-By: haowang101779990 <[email protected]>
shanyi15
added a commit
that referenced
this pull request
Mar 22, 2019
* fix layers. ==> fluid.layers. (#688) * fix data_reader_cn and dataset_cn (#685) * fix textual content * fix issue #682 3 3.2 * fix issues in conv * Fix io_cn (#597) * routine bug fix * update text info * fix io_cn all * 持久性变量=>长期变量 * 1220 improve cnapi (#509) * 1220 update cnapi * Apply suggestions from code review Co-Authored-By: haowang101779990 <[email protected]> * refine reader doc (#686) * update VisualDL README to add more details (#694) * improve save_load_variables cn (#689) * improve save_load_variables * Update save_load_variables.rst * fix typo of models (#698) * fix typo of models * fix en * Fix arguments according to 1.3 en + ceil,floor 翻译 +operator 翻译 (#695) * Fix arguments according to 1.3 en + ceil,floor trans +operator trans * fix LoDTensorArray spell * update_reading_data (#699) * add api_guides low_level backward parameter program_en (#696) * add api_guides low_level backward parameter program_en * Apply suggestions from code review Co-Authored-By: zy0531 <[email protected]> * Apply suggestions from code review Co-Authored-By: zy0531 <[email protected]> * Update backward_en.rst * Update parameter_en.rst * Update program_en.rst * Update doc/fluid/api_guides/low_level/program_en.rst
RichardWooSJTU
pushed a commit
to RichardWooSJTU/docs
that referenced
this pull request
Apr 8, 2022
RichardWooSJTU
pushed a commit
to RichardWooSJTU/docs
that referenced
this pull request
Apr 8, 2022
RichardWooSJTU
pushed a commit
to RichardWooSJTU/docs
that referenced
this pull request
Apr 8, 2022
Follow-on update that I missed adding into PR 509.
RichardWooSJTU
pushed a commit
to RichardWooSJTU/docs
that referenced
this pull request
Apr 8, 2022
Follow-on update that I missed adding into PR 509.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
一些说明的优化