Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

lstmemory这个layer的输出是什么样子？ #451

Closed
tj554121946 opened this issue Nov 13, 2016 · 3 comments
Closed

lstmemory这个layer的输出是什么样子？ #451

tj554121946 opened this issue Nov 13, 2016 · 3 comments
Labels
question

Comments

@tj554121946
Copy link

看了代码没有看的太懂，所以想问问lstmemory这个layer的输出是什么？我理解的是，根据公式，在某个时间t，lstm的输出就是一个浮点数，其维度为1没错吧？然后输入一个时间序列x的话，输出的就是一个1维的时间序列y，通过maxpooling之后得到的就是得到的就是max(y)，也只有1维，就是一个浮点数，请问有理解错吗？
@pengli09
Copy link
Contributor

您的理解是不对的，公式里的输入、输出都是向量表示，并不是单个数，此类写法在deep learning相关论文中是比较普遍的。相应的，lstmemory在每个时间步t的输出是一个向量，而非一个数。

@tj554121946
Copy link
Author

@pengli09 谢谢您的回答，我刚刚看了一下lstm的公式http://www.paddlepaddle.org/doc/ui/api/trainer_config_helpers/layers.html#lstmemory
最后的输出是三个点乘加上一个偏置之后经过一个激活函数。为什么这样的输出会是一个向量呢，可否解答一下，谢谢。

@pengli09
Copy link
Contributor

公式里的x_t是向量，不是一个数，W_*都是矩阵。这种向量化的符号表示参见http://ufldl.stanford.edu/wiki/index.php/%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C 中的例子

zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
@shanyi15
[cp2dev]Add avx info 1.1 (PaddlePaddle#279) (PaddlePaddle#451)
544ac47 
* Add avx info 1.1 (PaddlePaddle#279)

* refine avx info representation

* refine avx info representation

* refine avx info representation

* updatetoavx

* fix_AVX
zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
@shanyi15
update_1.2 (PaddlePaddle#464)
41e6a03 
* add_api_cn (PaddlePaddle#437)

* add gpu benchmark page (PaddlePaddle#436)

* add gpu benchmark

* fix comments

* add chinese link in gen_doc.py (PaddlePaddle#439)

* modified gen_doc.py

* Update gen_doc.py

* update gen_doc.py

* Update mobile doc (PaddlePaddle#440)

* update_en_structure

* update_Paddle_commitid

* delete_DS

* update_mobile_doc

* Update book commit (PaddlePaddle#438)

* update_en_structure

* update_Paddle_commitid

* delete_DS

* update_book_commit_id

* update_api_rst

* Adjust structure of advanced usage (PaddlePaddle#442)

* adjust_structure_of_advanced_usage

* Update paddle_gpu_benchmark.md

* adjust_toctree_hidden

* fix_api_guide

* Update index.rst

* fix deadlinkes (PaddlePaddle#443)

* add_toctree (PaddlePaddle#445)

* adjust_beginners_structure (PaddlePaddle#446)

* adjust_beginners_structure

* Update index.rst

* update install_doc for python3 (PaddlePaddle#418)

* update install_doc for python3

* update python3.5+ info,test=develop

* fix review, test=develop

* fix_pic (PaddlePaddle#447)

* delete en2zn link

* update lod_tensor

* 1207

 1.english api reference links removed
2. formatted

* update transpiler

* update profilse_cn

* Update docker-image instroduce, test=develop (PaddlePaddle#459)

* fix_bug (PaddlePaddle#460)

* [cp2dev]Add avx info 1.1 (PaddlePaddle#279) (PaddlePaddle#451)

* Add avx info 1.1 (PaddlePaddle#279)

* refine avx info representation

* refine avx info representation

* refine avx info representation

* updatetoavx

* fix_AVX

* update_en_api (PaddlePaddle#461)

* update api guides for cn (PaddlePaddle#462)

* Update commit_id of Paddle (PaddlePaddle#463)

* update_en_api

* update_again

* Fix bug (PaddlePaddle#465)

* update_en_api

* update_again

* bug_fix

* fix_2nd
zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
@shanyi15
update_1.2 (PaddlePaddle#467)
51117e4 
* add_api_cn (PaddlePaddle#437)

* add gpu benchmark page (PaddlePaddle#436)

* add gpu benchmark

* fix comments

* add chinese link in gen_doc.py (PaddlePaddle#439)

* modified gen_doc.py

* Update gen_doc.py

* update gen_doc.py

* Update mobile doc (PaddlePaddle#440)

* update_en_structure

* update_Paddle_commitid

* delete_DS

* update_mobile_doc

* Update book commit (PaddlePaddle#438)

* update_en_structure

* update_Paddle_commitid

* delete_DS

* update_book_commit_id

* update_api_rst

* Adjust structure of advanced usage (PaddlePaddle#442)

* adjust_structure_of_advanced_usage

* Update paddle_gpu_benchmark.md

* adjust_toctree_hidden

* fix_api_guide

* Update index.rst

* fix deadlinkes (PaddlePaddle#443)

* add_toctree (PaddlePaddle#445)

* adjust_beginners_structure (PaddlePaddle#446)

* adjust_beginners_structure

* Update index.rst

* update install_doc for python3 (PaddlePaddle#418)

* update install_doc for python3

* update python3.5+ info,test=develop

* fix review, test=develop

* fix_pic (PaddlePaddle#447)

* delete en2zn link

* update lod_tensor

* 1207

 1.english api reference links removed
2. formatted

* update transpiler

* update profilse_cn

* Update docker-image instroduce, test=develop (PaddlePaddle#459)

* fix_bug (PaddlePaddle#460)

* [cp2dev]Add avx info 1.1 (PaddlePaddle#279) (PaddlePaddle#451)

* Add avx info 1.1 (PaddlePaddle#279)

* refine avx info representation

* refine avx info representation

* refine avx info representation

* updatetoavx

* fix_AVX

* update_en_api (PaddlePaddle#461)

* update api guides for cn (PaddlePaddle#462)

* Update commit_id of Paddle (PaddlePaddle#463)

* update_en_api

* update_again

* Fix bug (PaddlePaddle#465)

* update_en_api

* update_again

* bug_fix

* fix_2nd

* add_release_note
thisjiang pushed a commit to thisjiang/Paddle that referenced this issue Oct 28, 2021
@hp03
c++ compatible using abseil-cpp (PaddlePaddle#451)
c2894b8 
* c++14 compatible using abseil-cpp
AnnaTrainingG pushed a commit to AnnaTrainingG/Paddle that referenced this issue Sep 19, 2022
@lzzyzlbb
Fix benchmark (PaddlePaddle#451)
32132fa 
* fix benchmark

* add fomm and stylegan benchmark
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@pengli09 @qingqing01 @tj554121946