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

找不到human body parsing 相关教程和模型 #3248

Closed
1 task done
KelvinHong opened this issue May 5, 2023 · 2 comments
Closed
1 task done

找不到human body parsing 相关教程和模型 #3248

KelvinHong opened this issue May 5, 2023 · 2 comments
Assignees
Labels
question Further information is requested

Comments

@KelvinHong
Copy link

KelvinHong commented May 5, 2023

问题确认 Search before asking

  • 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

我想用PaddleSeg API来做 human body parsing, 我在相关的paper中发现这个用法,很符合我的需求

image

我翻找了几个教程,包括这个(face parsing) [不太符合我的需求,需要的是对半身或全身 parsing]
https://aistudio.baidu.com/aistudio/projectdetail/5326422
和这个 (portrait and body segmentation) [很靠近,不过目前只有人-背景分割,并没有如paper内的可以对身体不同部位细分割]
https://aistudio.baidu.com/aistudio/projectdetail/4504982

对于body segmentation, 我尝试run code, 发现Predictor 的 get_output_handle 会return 一个shape (1, 2, 256, 144) 的tensor, 当我把两个部分分别当 masks 作图后,得到黑白两个mask。 以下是原图和得到的两个masks。
img2
mask1
mask2
如图,并没有human body parsing 那般的细分。

想请问有什么教程是关于human body parsing 的吗?

@KelvinHong KelvinHong added the question Further information is requested label May 5, 2023
@juncaipeng
Copy link
Collaborator

你需要human body parsing的数据集进行训练,才可以对输入图像进行人体部件分割。

@juncaipeng juncaipeng self-assigned this May 6, 2023
@KelvinHong
Copy link
Author

好的,那我明白了,感谢解答。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants