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

Show and Tell: A Neural Image Caption Generator #1056

Closed
VamWolf opened this issue Jan 3, 2017 · 4 comments
Closed

Show and Tell: A Neural Image Caption Generator #1056

VamWolf opened this issue Jan 3, 2017 · 4 comments

Comments

@VamWolf
Copy link

VamWolf commented Jan 3, 2017

https://github.com/tensorflow/models/blob/master/im2txt/g3doc/show_and_tell_architecture.png

paddle 实现这个结构,是不是
image embeding 一层
word embeding 一层
两层连接,concat_layer
然后,作为lstm 的输入,lstm层 得到encoded vector.
decode ,参考seqToseq 的解码部分就可以了

@Zrachel
Copy link
Contributor

Zrachel commented Jan 3, 2017

有一点不一样,
两层连接,应该用SequenceConcatLayer (concat_layer是指两个拼起来的size是两个相加的size)

@VamWolf
Copy link
Author

VamWolf commented Jan 3, 2017

SequenceConcatLayer 在 trainer_config_helpers 里目前没有,./trainer/config_parser.py 里有,应该是可以按照 paddle v1 的方式使用???

@Zrachel
Copy link
Contributor

Zrachel commented Jan 4, 2017

是的

@Yancey1989
Copy link
Contributor

这issue太久没更新了,如果有更新再打开吧,多谢。

wangxicoding pushed a commit to wangxicoding/Paddle that referenced this issue Dec 9, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants