Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

使用PaddleDetection训练出了yolo3_mobileNet_v3模型后,通过paddle-lite-demo中的yolo-detection-demo来运行,运行环境是荣耀9的安卓真机。 #1737

Open
NeTChengGH opened this issue Oct 5, 2023 · 0 comments
Assignees

Comments

@NeTChengGH
Copy link

描述问题

将paddleDetection-2.6训练出来的yolo3_mobileNet_v3模型,放到paddle-lite-demo中yolo-detection-demo项目中运行时报错。
但是我使用从github中下载下来的paddleX GUI训练出来的yolo3_mobileNet_v3模型,却可以正常在yolo-detection-demo项目中运行。

复现

1、我使用PaddleDetection-2.6的tools/train.py通过gpu模式训练出yolo3_mobileNet_v3模型,并通过paddleDetection的delopy/python/infer.py测试过模型是正常可预测图片的。预测结果如下所示:
image

infer_cfg.yml文件内容如下:
image

2、然后使用opt工具(保持window端和安卓部署端的版本号一致,2.10rc0的版本)将模型转换成.nb后缀的模型
image

3、将.nb模型和labels.txt标签内容对应的替换到paddle-lite-demo的项目中,同时修改了preprocess方法内容,运行预测时就报错了。
替换后的文件目录如下:
image
image

错误如下:
image

部署环境

荣耀9的安卓真机。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants