PaddlePaddle / PaddlePaddle/FastDeploy
PaddleOCR通过FastDeploy部署到rv1126上遇到的问题
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
目标：使用PaddleOCR部署到瑞芯微rv1126上面
-
【FastDeploy版本】： master
-
【编译命令】
-
【系统平台】: Linux x64(Ubuntu 18.04) 交叉编译到rv1126平台
-
【硬件】：rv1126
-
【编译语言】： C++
-
【模型跑不通】
我用的是rv1126，它不是rknpu2，如果使用FastDeploy 以-DWITH_TIMVX=ON的方式进行编译。模型格式该是什么呢(不是rknn或者onnx吧？)？如何转换？
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 checking FastDeploy's TIM-VX build path and the documented model formats and conversion workflow for rv1126. Confirm which format is supported when building with -DWITH_TIMVX=ON and whether rv1126 is supported; done means documenting the compatible format and conversion steps, or clearly identifying the unsupported configuration.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, linux, ubuntu
- Domain
- embedded-iot
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100