We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
如图,client端的feed dict为如下元素和形状:
即包含两个样本的bert输入。
但是如图所示,
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?
The text was updated successfully, but these errors were encountered:
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
client对feed输入的处理策略到底是怎样的呢?
Sorry, something went wrong.
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。
bjjwwang
No branches or pull requests
如图,client端的feed dict为如下元素和形状:
即包含两个样本的bert输入。
但是如图所示,
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?
The text was updated successfully, but these errors were encountered: