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

【疑似bug】框架内部会自动给用户输入升维? #803

Closed
xixiaoyao opened this issue Aug 18, 2020 · 2 comments
Closed

【疑似bug】框架内部会自动给用户输入升维? #803

xixiaoyao opened this issue Aug 18, 2020 · 2 comments
Assignees
Labels
question Further information is requested

Comments

@xixiaoyao
Copy link

xixiaoyao commented Aug 18, 2020

如图,client端的feed dict为如下元素和形状:
image

即包含两个样本的bert输入。

但是如图所示,

image

server端收到输入并经过fluid.embedding之后,本应该得到[2,9,1024](经过了1024维度的embedding),结果莫名其妙的变成了[1,2,9,1024],前面不知道从哪里多了一个size为1的维度。这是paddle serving框架内部自动添加的维度吗?

@xixiaoyao
Copy link
Author

我发现仅仅是将feed中的元素从numpy array变成python list,报错都变了。。。tolist之后变成这样的报错了

image

client对feed输入的处理策略到底是怎样的呢?

@bjjwwang bjjwwang self-assigned this Aug 19, 2020
@bjjwwang
Copy link
Collaborator

目前一个batch需要做成list [dict]的形式,每个dict是一条样本。否则做成一条样本目前会自动加batch维度,这部分接口在修改,预计下周提测。

@TeslaZhao TeslaZhao added the question Further information is requested label Aug 31, 2020
@paddle-bot paddle-bot bot closed this as completed Mar 5, 2024
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

3 participants