PaddlePaddle / PaddlePaddle/FastDeploy
python推理部署怎么处理fd.vision.ocr.PPStructureV2Table.predict(im)的result？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 756
- Avg merge
- 19h 28m
- Merged PRs (30d)
- 4
Description
使用python example代码可以正常推理
但是结果result我将如何处理成可以操作的数据结构呢？
python下，result是<class 'fastdeploy.libs.fastdeploy_main.vision.OCRResult'>对象，属性只有ocr的一些结果
但是我查看c++源码，OCRResult结构体是有table_html, table_structure属性的
但是在python下无法访问这些属性
所以我应该如何处理fd.vision.ocr.PPStructureV2Table.predict(im)返回的结果？拿到表格结构？
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 with the Python example calling fd.vision.ocr.PPStructureV2Table.predict(im), then inspect the Python binding for OCRResult and compare it with the C++ OCRResult fields shown in the issue. Check whether table_html and table_structure are exposed or documented, and verify the result object after inference; done means Python users can access the table structure or the supported handling is clearly documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100