-
Notifications
You must be signed in to change notification settings - Fork 52
我这里直接用yolov7导出的onnx格式,为什么和你的不太一样啊。求解答 #9
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
我转出来也是这样,搞不懂为什么。。。你知道原因了吗 |
我是在google drive里找到onnx文件的,源头这里, |
我把那个 not opt.grid 的not去掉了,但是还是有问题,在readnet的时候直接报错了 |
仓库里新添加了export.py转换脚本,转换时加上--grid参数 |
能添加个联系方式吗?q522257762 |
我使用grid为true的onnx导出方法,可以forward,但是输出的为三个检测头的5维结果,使用yolov4的处理方案分别读取检测结果得到的output确实为对应类别维度,但是里面detection【5:】里面发现,position参数及class参数均异常,为负值无合理含义,而使用grid为false的onnx导出方法,确实可以得到与作者再goolge上下载得到的模型相同的3维数据,但是无法forward,我使用的为opencv4.5.5 |
现在就是dnn不能正常使用,导出的输出是1x25200x7,dnn报错start <= (int)shape.size() && end <= (int)shape.size() && start <= end in function 'total', onnxruntime正常使用 |
The text was updated successfully, but these errors were encountered: