PaddlePaddle / PaddlePaddle/FastDeploy
jetson上pptinypose输出异常
@jiangjiajun is already working on this.
Since Aug 5, 2024.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
环境:jetpack5.1.3,包括cuda11.4, cudnn8.6.0, tensorrt5.2.2
编译按照官方文档,编译时没有加上paddle_backend,编译过程正常
在jetson上使用fastdeploy跑tinypose模型输出关键点全为0.0000000,置信度很低
同样的代码在windows上跑正常,windows环境cuda11.6, cudnn8.6, tensorrt5.3.1,windows上的fastdeploy是官方下的
我逐步排查发现可能是没有permute的原因,在windows上使用参数disable_permute()后输出结果与jetson上一致,也就是说本来模型需要的是[1,3,256,192]但是现在传的是[1,256,192,3]
我又查看fastdploy源码,添加代码打印了在传入推理前的数据维度并编译,发现输出是[1,3,256,192],这个是正常的
同样的,我部署mot模型,里面也有permute操作,但是在jetson上输出正常
个人猜测是不是tensorrt转算子不支持permute(这方面不是太了解),希望得到大神解答
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.
Assessment
This issue has not been assessed yet.