在Ubuntu上可以正确加载PPYOLOE模型，在Android上点击app闪退。

Open
#3,945 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
25/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
android, cpp
Domain
computer-vision, mobile-dev

Research direction

Start with the README and the ncnn-android-ppyoloe project, then reproduce the crash using the model files in app/src/main/assets. Obtain the Android crash log and compare model loading with the Ubuntu and Windows runs. Done means identifying the Android-specific loading failure and documenting a verified fix or a precise missing requirement.

Written by the indexing model from the issue text.

Description

error log | 日志或报错信息 | ログ

我不太了解安卓开发，不知道怎么看报错信息。

context | 编译/运行环境 | バックグラウンド

Android

how to reproduce | 复现步骤 | 再現方法

大佬们好！我在ncnn(Ubuntu)上成功导出PPYOLOE算法，并成功预测了。但是在安卓上一加载模型就闪退，求帮忙看看！

PPYOLOE算法导出ncnn、并成功在Ubuntu和windows上预测，步骤请看
https://zhuanlan.zhihu.com/p/532518260

安卓项目源码 https://github.com/miemie2013/ncnn-android-ppyoloe
参考了 https://github.com/FeiGeChuanShu/ncnn-android-yolox 的实现。
下载好源码后把上述得到的模型文件ppyoloe_crn_s_300e_coco.param、ppyoloe_crn_s_300e_coco.bin、ppyoloe_crn_m_300e_coco.param、ppyoloe_crn_m_300e_coco.bin放在app/src/main/assets目录下。按照README编译出apk文件，安装，点击之后就闪退了。

more | 其他 | その他

通过注释掉部分代码，发现是因为ncnn加载模型就闪退。

Dominant language
C++
Stars
23.8k
Forks
4.5k
Avg merge
2d 20h
Merged PRs (30d)
37

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from Tencent/ncnn

All issues in Tencent/ncnn

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.