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

【Question】请问paddle支持用RNN+LSTM进行text generation吗？在例子中没有找到。。。 #1191

Closed
sillybowen opened this issue Jan 19, 2017 · 3 comments
Closed

【Question】请问paddle支持用RNN+LSTM进行text generation吗？在例子中没有找到。。。 #1191

sillybowen opened this issue Jan 19, 2017 · 3 comments

Comments

@sillybowen
Copy link

sillybowen commented Jan 19, 2017 •
edited
Loading

假设我有一组电商评论数据，想要训练生成类似的短信息。

在例子中只看到了基于翻译的seqToSeq

Lstm只看到了分类的例子
@sillybowen sillybowen changed the title 请问paddle支持用RNN+LSTM进行text generation吗？在例子中没有找到。。。 【Question】请问paddle支持用RNN+LSTM进行text generation吗？在例子中没有找到。。。 Jan 19, 2017
@luotao1
Copy link
Contributor

luotao1 commented Jan 19, 2017

请问“基于翻译的seqToSeq”和你需要的“RNN+LSTM”差别具体在哪里呢？可以在配置中任意指定需要的layer。

@sillybowen
Copy link
Author

sillybowen commented Jan 19, 2017 •
edited
Loading

多谢回复。

我实际是想做一个类似：
http://mxnet.io/tutorials/python/char_lstm.html
的功能，比较一下paddle和mxnet的performance

SeqToSeq 我的理解是根据输入的Seq生成一个match的Seq。
而我要做的是，输入seq的起始，根据概率生成固定长度的seq。

请问该用哪些layer啊？
或者有没有哪个例子我能借鉴的？

多谢。

@kuke
Copy link
Contributor

kuke commented Jul 28, 2017

Closed because of inactivity

@kuke kuke closed this as completed Jul 28, 2017
zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
@liupluswei @cyj1986
deprecate paddle.fluid.memory_optimize API (PaddlePaddle#1191)
aa8ded2 
* deprecate paddle.fluid.memory_optimize

* fix comment

* fix comment
wangxicoding pushed a commit to wangxicoding/Paddle that referenced this issue Dec 9, 2021
@huhuiwen99
Add AutoModel (PaddlePaddle#1191)
8f0a0b6 
* modify transforner-rst

* modify roformer tokenizer

* delete modifications

* modify chunk

* delete changes

* first modify

* modify auto

* modify automapping

* modify automapping

* modify baseautomodel

* add tokenizer file

* add tokenizer

* update tokenizer

* modify tokenizer

* update

* modify auto modeling

* test modeling

* update

* modify automodel

* test auto

* update

* test tokenizer

* add diffs

* update

* fix errors

* test

* update

* modify some errors

* fix errors

* update

* updat4e

* add task_choice

* update

* update

* update

* add causal lm mapping

* remove dir

* update

* update

* add models

* delete print

* task para

* task para

* task para

* fix errors

* update

* ernie-gen

* update

* update
lizexu123 pushed a commit to lizexu123/Paddle that referenced this issue Feb 23, 2024
@ceci3
update auto compress classication readme (PaddlePaddle#1191)
9a07386
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@sillybowen @kuke @luotao1