PaddlePaddle / PaddlePaddle/FastDeploy
PP-LiteSeg分割模型在核显跑不通
Open
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-win-x64-1.0.7.zip
- 【系统平台】: Windows x64(Windows10)
- 【硬件】： i9-9900k 核显Intel(R) UHD Graphics 630
- 【编译语言】： C++
问题日志及出现问题的操作流程
- 附上详细的问题日志有助于快速定位分析
- 【分割模型在核显跑不通】
-
- 跑PP-LiteSeg模型 只设置CPU 模型可以正常推理
-
- 在增加了核显参数
- --option.openvino_option.SetDevice("HETERO:GPU,CPU")；
- --shape_info_seg["x"] = { 1, 3, 320, 320 };
- --option.openvino_option.SetShapeInfo(shape_info_seg);
- --option.openvino_option.SetCpuOperators({ "MulticlassNms" })
- -在auto model = fastdeploy::vision::segmentation::PaddleSegModel(model_filename, params_filename, cfg_file, option);报错
- -报错截图如下
-
- 【ppyoloe模型在核显能正常跑通】
-
-
- 调用库及环境应该没问题
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
Reproduce PP-LiteSeg with FastDeploy's vision::segmentation::PaddleSegModel on Windows x64 and the Intel UHD 630, first comparing CPU-only execution with the listed HETERO:GPU,CPU OpenVINO settings. Inspect the constructor failure and the shape and CPU-operator configuration shown in the report. Done means identifying the cause and confirming a fix or documented workaround.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100