PaddlePaddle / PaddlePaddle/FastDeploy

FuseNormalizeHWC2CHW Normalize and HWC2CHW are fused to NormalizeAndPermute in preprocessing pipeline.

Open
#1,953 2 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


温馨提示:根据社区不完全统计,按照模板提问,可以加快回复和解决问题的速度


环境

  • 【FastDeploy版本】: 1.0.2
  • 【编译命令】如果您是自行编译的FastDeploy,请说明您的编译方式(参数命令)
  • 【系统平台】: Linux x64(Ubuntu 20.04)
  • 【硬件】: AMD
  • 【编译语言】: Python(3.9)

问题日志及出现问题的操作流程

安装说明替换模型 使用ov 报错如下
python benchmark_ppcls.py --model ResNet50_vd_old --image 2.jpeg --cpu_num_thread 8 --iter_num 2000 --backend ov
[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

Reproduce the reported command with ResNet50_vd_old and the OpenVINO backend, then inspect the output around the messages from fastdeploy/vision/common/processors/transform.cc at lines 93 and 159. The issue does not include the actual error beyond these INFO messages, so first determine whether those messages are expected and identify the failing behavior before defining completion.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.