-
Notifications
You must be signed in to change notification settings - Fork 52
为什么我的可以跑通,但是没有任何预测结果? #3
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
Comments
你的onnx文件,是从哪里来的 |
我遇到了一样的问题,用大佬的onnx模型能跑通,用/WongKinYiu/yolov7/models/export.py导出的onnx模型没有预测结果,大佬能指点下是哪里的问题吗 |
请问导出时需要加 --make-gird 么
要加的。看opencv部署的代码,在forward之后,并没有做make_grid和decode,说明这个步骤在onnx文件里做的 |
在官方代码https://github.com/WongKinYiu/yolov7/blob/main/models/yolo.py 里,看截图里的红色框里的这一段代码, 这些在onnx文件里的,其实看opencv部署的代码,在forward之后操作也能看出来的 |
本仓库里提供的onnx文件和您自己转的onnx文件,在netron网站可视化,比较一下,可以看出差异,进而分析出原因 |
如果onnx文件里不包含make_grid和decode,那需要修改opencv部署的代码,在forward之后,添加make_grid和decode的操作 |
谢谢大神,用u5那个可以了,但是遇到了一个新的问题就是用了nvida的显卡之后检测时间更慢了,查了一些资料说是opencv对nvida的显卡不友好,如果用intel的显卡就没事了,请问有什么办法解决呢? |
Is it possible to use the onnx model in matlab? |
No description provided.
The text was updated successfully, but these errors were encountered: