PaddlePaddle / PaddlePaddle/FastDeploy
测试rvm Pfld Pipnet 感觉都有点问题
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
-
【FastDeploy版本】： 说明具体的版本，如fastdeploy-osx-arm64-1.0.7
-
【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】: Mac OSX arm(14.0)
-
【硬件】： 说明具体硬件型号，如 Nvidia GPU 3080TI， CUDA 11.2 CUDNN 8.3
-
【编译语言】： C++
-
【模型精度问题】
使用rvm明显把头像切了部分，手出现也不完整，和原版比质量差了很多
Pfld Pipnet 人脸识别点位置都乱了，而且乱跳，是不是有问题需要确认下
还有 MobileNetV2SE68 这个能都加下效果更好的
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by collecting the missing FastDeploy version, build command, and exact hardware details, then reproduce the reported RVM, Pfld, and Pipnet output differences on macOS ARM. Compare the results with the referenced original models and document whether the quality and landmark instability are reproducible; the MobileNetV2SE68 addition is a separate scope to clarify.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100