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

nanodet plus 1152*768 转换成功,结果不匹配 #5819

Open
Yindong-Zhang opened this issue Dec 11, 2024 · 2 comments
Open

nanodet plus 1152*768 转换成功,结果不匹配 #5819

Yindong-Zhang opened this issue Dec 11, 2024 · 2 comments

Comments

@Yindong-Zhang
Copy link

Yindong-Zhang commented Dec 11, 2024

error log | 日志或报错信息 | ログ

context | 编译/运行环境 | バックグラウンド

how to reproduce | 复现步骤 | 再現方法

more | 其他 | その他

很奇怪,使用各种方式转换nanodet-plus 1152*768 输入,输出都不对,目前在python脚本测试,相同输入图片和预处理,确认转换成torch2onnx是对的,onnx2pnnx是错的, torchscript2pnnx也是错的,人麻了,这么古老的模型怎么会出错,可以上传onnx 文件用于确认,希望好心人看到给给建议

@Yindong-Zhang
Copy link
Author

Yindong-Zhang commented Dec 11, 2024

是形状的问题吗?模型训练是 1152x768 的,转换和推理也是 1152x768,难道只支持方形,还是其他问题?

@Yindong-Zhang
Copy link
Author

wiki 中的 wrong result 也检查过了

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

1 participant