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.

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

Paddle使用求助:预测模型 #465

Closed
liuzongquan opened this issue Nov 14, 2016 · 2 comments
Closed

Paddle使用求助:预测模型 #465

liuzongquan opened this issue Nov 14, 2016 · 2 comments
Assignees
Labels

Comments

@liuzongquan
Copy link

大咖们,
我在使用paddle解决一个预测模型时遇到一些,期望得到大家的帮助和回复,先谢谢大家了。
我的问题是这样的:
train.dat如下
col_1,col_2,col_3,col_4,col_5,col_6,col_7,col_8,label
0.6004053786,0.955187599926,2,3,0.991455200062,0.508602067761,0.088945346,0.044968775,0.3596
0.6004053786,0.955187599926,1,1,0.991455200062,0.508602067761,0.06316632,0.023484437,0.1584
0.6004053786,0.955187599926,2,3,0.991455200062,0.508602067761,0.087739105,0.044656454,0.2072
......

由于不确定输入的feature跟label之间的关系到底是什么样的,所以决定选用神经网络跑一下看看。训练数据集很大,大概有上亿条记录。
我在使用paddle的时候,打算创建一个三层的神经网络,输入层->全连接隐层(使用fc_layer)->输出层,然后使用regression_cost()计算误差,最后输出模型。

我的问题是,从fc_layer到输出之间的这个层我不确定应该使用什么?
我看了paddle.org/doc中所有页面,还是没能找到一个合适的layer将一个number list映射到一个number。所以期望得到大家的帮助和指导,再次感谢!

@zhouxiao-coder
Copy link
Contributor

不知道我有没有理解错你的问题,你是想说:如何从你图上的 col1 - col8 的输入得到最后的 1维 output score?

如果是的话,答案也非常简单:只要把最后输出层的宽度设为1即可。 这里有一个简单的例子 供参考。

针对你的例子来讲,就像这样:

output_layer = fc_layer(input=hidden##你的隐层##, param_attr=ParamAttr(name='w'), size=1, act=LinearActivation(), bias_attr=ParamAttr(name='b'))
cost = regression_cost(input=output_layer, label=y##目标label##)
outputs(cost)

@liuzongquan
Copy link
Author

赞!是的,这正是我想要的~ 非常感谢!

zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
* update_en_api

* update_again

* bug_fix

* fix_2nd
zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
* 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
* 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
Meiyim pushed a commit to Meiyim/Paddle that referenced this issue May 21, 2021
thisjiang pushed a commit to thisjiang/Paddle that referenced this issue Oct 28, 2021
* meta op transpose

* using const&

* fix attr

* add layout infer for transpose

* add infer shape test for transpose

* opt meta ops

Co-authored-by: wangone <2279939962@qq.com>
gglin001 added a commit to graphcore/Paddle-fork that referenced this issue Mar 17, 2022
* update python api

* update UTs

* fix UT
wwbitejotunn pushed a commit to wwbitejotunn/Paddle that referenced this issue Jun 21, 2024
)

* fix name.

* set inv function.

* add map back function.

* handle gqa.

* add type annotation to avoid confusion.

* fix docstr.

* test inverse remap logic.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants