PaddlePaddle / PaddlePaddle/FastDeploy

范例vision/detection/paddledetection/serving无法跑通

Open
#1,920 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

环境

  • 【FastDeploy版本】:fastdeploy:1.0.4-gpu-cuda11.4-trt8.5-21.10
  • 【系统平台】: Linux x64(Ubuntu 18.04)
  • 【硬件】: Nvidia GPU 1060

已完全按照 https://github.com/PaddlePaddle/FastDeploy/blob/develop/examples/vision/detection/paddledetection/serving/README_CN.md 文档部署

使用Gradio执行报

Error: [400] in ensemble 'ppdet', Failed to process the request(s) for model instance 'preprocess_0', message: Stub process is not healthy.�

在终端使用paddledet_grpc_client.py执行报

root@7B89:/FastDeploy/vision/detection/paddledetection/serving# python3 paddledet_grpc_client.py
tm: name: "INPUT"
datatype: "UINT8"
shape: -1
shape: -1
shape: -1
shape: 3

Traceback (most recent call last):
  File "paddledet_grpc_client.py", line 103, in <module>
    result = runner.Run([im, ])
  File "paddledet_grpc_client.py", line 73, in Run
    results = self._client.infer(
  File "/usr/local/lib/python3.8/dist-packages/tritonclient/grpc/__init__.py", line 1469, in infer
    raise_error_grpc(rpc_error)
  File "/usr/local/lib/python3.8/dist-packages/tritonclient/grpc/__init__.py", line 75, in raise_error_grpc
    raise get_error_grpc(rpc_error) from None
tritonclient.utils.InferenceServerException: [StatusCode.INTERNAL] in ensemble 'ppdet', Failed to process the request(s) for model instance 'preprocess_0', message: Stub process is not healthy.

visualDL 日志报

[ERROR] fastdeploy/pybind/main.cc(142)::PyArrayToCvMat	Require rank of array to be 3 with HWC format while converting it to cv::Mat.
E0509 09:31:38.142933 1099 python.cc:1942] Stub process is unhealthy and it will be restarted.
[INFO] fastdeploy/vision/common/processors/transform.cc(45)::FuseNormalizeCast	Normalize and Cast are fused to Normalize in preprocessing pipeline.
[INFO] fastdeploy/vision/common/processors/transform.cc(93)::FuseNormalizeHWC2CHW	Normalize and HWC2CHW are fused to NormalizeAndPermute  in preprocessing pipeline.
[INFO] fastdeploy/vision/common/processors/transform.cc(159)::FuseNormalizeColorConvert	BGR2RGB and NormalizeAndPermute are fused to NormalizeAndPermute with swap_rb=1�

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 examples/vision/detection/paddledetection/serving/README_CN.md and paddledet_grpc_client.py, then reproduce the request through Gradio or the gRPC client while checking the VisualDL logs. Trace why preprocess_0 receives an array with the wrong rank and verify that the serving example completes inference without the Stub process becoming unhealthy.

Written by the indexing model from the issue text.

Assessment

Tech stack
grpc, python
Domain
backend-api-design, devops
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.