PaddlePaddle / PaddlePaddle/FastDeploy

使用FastDeploy搭建PP-OCRv3模型服务后怎么配置参数

Open
#1,891 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
756
Avg merge
19h 28m
Merged PRs (30d)
4

Description

系统环境/System Environment:docker
版本号/Version: fastdeploy:1.0.4-cpu-only-21.10

小白一个,目前服务部署起来了,但是我想配置一下文本框识别数量上限这种参数。小白凭个人猜测对着det_postprocess文件夹下的config.pbtxt文件改了两下会报错。求大神指点该怎么写,怎么配置……
image

尝试在config.pbtxt中直接加入max_candidates: 2

[libprotobuf ERROR /tmp/tritonbuild/tritonserver/build/_deps/repo-third-party-build/grpc-repo/src/grpc/third_party/protobuf/src/google/protobuf/text_format.cc:317] Error parsing text-format inference.ModelConfig: 46:27: Message type "inference.ModelConfig.ParametersEntry" has no field named "max_candidates".
E0430 23:07:12.852829 210 model_repository_manager.cc:1890] Poll failed for model directory 'det_postprocess': failed to read text proto from /opt/tritonserver/FastDeploy/examples/vision/ocr/PP-OCR/serving/fastdeploy_serving/models/det_postprocess/config.pbtxt

尝试加入parameters {max_candidates: 2}

[libprotobuf ERROR /tmp/tritonbuild/tritonserver/build/_deps/repo-third-party-build/grpc-repo/src/grpc/third_party/protobuf/src/google/protobuf/text_format.cc:317] Error parsing text-format inference.ModelConfig: 46:27: Message type "inference.ModelConfig.ParametersEntry" has no field named "max_candidates".
E0430 23:07:12.852829 210 model_repository_manager.cc:1890] Poll failed for model directory 'det_postprocess': failed to read text proto from /opt/tritonserver/FastDeploy/examples/vision/ocr/PP-OCR/serving/fastdeploy_serving/models/det_postprocess/config.pbtxt

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with models/det_postprocess/config.pbtxt in the PP-OCR serving example and review how its Triton model configuration is structured. Reproduce the reported parsing error, then identify the supported configuration path for the requested text-box limit and document the valid setting and an example that lets the service start successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker
Domain
devops, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.