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

Modify model conversion interfaces and model load methods #1358

Merged
merged 2 commits into from
Aug 20, 2021

Conversation

TeslaZhao
Copy link
Collaborator

@TeslaZhao TeslaZhao commented Aug 19, 2021

  1. 修改非加密模型转换接口,不使用save_inference_model做模型转换,因该接口会加入sacle op导致fetch结果与导出的prototxt结构不一致。不强制将模型名称改成__params__和__model__,只生成prototxt文件。
  • *.pdiparams + .pdmodel 同时存在时,serving_server目录下模型名称保持不变,仍为.pdiparams 和 *.pdmodel 。
  • model + __params__同时存在时,serving_server目录下模型名称保持不变,仍为 modelparams
  • model + 散列参数文件时,serving_server目录下模型名称为*.pdiparams 和 *.pdmodel,此时的fetch名称与之前可能不同

2.修复Pipeline Local_predict模式中predictor获取推理结果异常的bug。当有多个fetch结果且使用save_inference_model做模型转换时,此处的结果顺序有问题。

3.Pipeline_client接口中增加『pipeline_grpc』的交互模式,提供Pipeline 之间的网络交互,如多机分布式训练(MP + PP)的模型可以使用此模式。

4.修改Pipeline的Op::process函数,增加入参和返回结果,以便于异常时的问题记录

@paddle-bot-old
Copy link

Thanks for your contribution!

Copy link
Collaborator

@bjjwwang bjjwwang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@bjjwwang bjjwwang merged commit d2d9590 into PaddlePaddle:develop Aug 20, 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

Successfully merging this pull request may close these issues.

None yet

2 participants