Skip to content

picodet交叉编译后部署在arm上四核推理,量化后的模型反而推理速度更慢了 #9290

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

Open
1 task done
Hknight514880265 opened this issue Jan 22, 2025 · 0 comments
Assignees

Comments

@Hknight514880265
Copy link

问题确认 Search before asking

  • 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

  • 版本、环境信息:
       1)配置版本:paddlepaddle2.3.2、paddleDetection2.6、paddlelite2.14rc、paddleslim2.3.0
       2)系统环境:ubuntu交叉编译,arm上部署
  • 模型信息
       1)模型名称:picodet
  • 复现信息:
       1)训练配置:-c configs/picodet/picodet_xs_320_voc_lcnet.yml
       2)训练量化:--slim_config configs/slim/quant/picodet_xs_320_lcnet_quant.yml
       3)转换量化:paddle_lite_opt --model_dir=infer_model_params/picodet_xs_320_lcnet_quant --optimize_out_type=naive_buffer --quant_model=true --quant_type=QUANT_INT8 --valid_targets=arm --optimize_out=lite_model/model_quant
       4)无量化模型部署信息
    model.nb文件大小3.0M
    单核Prediction time: 196.392800 ms
    四核Prediction time: 63.681800 ms
       5)量化后模型部署信息
    model.nb文件大小1.3M
    单核Prediction time: 182.649800 ms
    四核Prediction time: 73.184100 ms
  • 问题描述:
    量化后模型参数量确实缩小了很多,单核的检测速率也有所提升(提升幅度较小,并没有达到说明文档里提速>30%的效果),但四核的检测速率反而下降了很多,希望大佬解答一下是哪个环节出问题了导致量化后速率没有明显提升。
@Hknight514880265 Hknight514880265 changed the title picodet部署在arm上四核推理,量化后的模型反而推理速度更慢了 picodet交叉编译后部署在arm上四核推理,量化后的模型反而推理速度更慢了 Jan 22, 2025
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

No branches or pull requests

3 participants