按照yolov8的ncnn推理，在web上部署运行很慢，如何优化
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 23.8k
- Forks
- 4.5k
- Avg merge
- 2d 20h
- Merged PRs (30d)
- 37
Description
detail | 详细描述 | 詳細な説明
使用了ncnn项目中提供的yolov8推理代码，在web上跑推理很慢
ex.input("in0", in_pad);
std::vector<Object> proposals;
// stride 32
{
ncnn::Mat out;
ex.extract("out0", out);
这个转化耗时了800ms，如何进一步优化
Contributor guide
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 profiling the ncnn YOLOv8 web inference path around ex.extract("out0", out), which the issue reports taking 800 ms. Compare the extraction and surrounding inference steps to identify the bottleneck; done would require a measured improvement and a documented optimization path, but the issue provides no target or test case.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, web-dev
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100