-
Notifications
You must be signed in to change notification settings - Fork 77
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
您好,tensorrt c++代码:关键点为2的数据集合训练后导出onnx,c++推理报cuda failure 700错误,请问可能是什么原因? #3
Comments
你给个onnx给我试下,加群,发我 |
请问群号是多少,非常感谢! |
871797331 qq群 |
链接: https://pan.baidu.com/s/1pfnonWjCKXmCsMfbUl88Ww 密码: g8aj |
请问这样直接分享可以吗 我还在Linux上,随后我再加群,多谢您! |
onnx 推理试过吗,结果对吗 |
推理报错,报错的地方在[02/23/2023-19:18:43] [W] [TRT] TensorRT was linked against cuBLAS/cuBLAS LT 11.6.3 but loaded cuBLAS/cuBLAS LT 11.1.0 |
我说的是onnxruntime 推理 |
还没有测试。同样的训练代码和同样的推理代码,类别数都为2,一个关键点个数为4,一个关键带你个数为2,前者可以,后者报错,我现在测试一下onnxruntime. |
四个关键点的模型参数为:[info][simple_yolo.cu:2281]:Input shape is 1 x 3 x 1024 x 1024 |
两类关键点的模型参数为[info][simple_yolo.cu:2281]:Input shape is 1 x 3 x 1024 x 1024 |
唯一个区别在于输出维数的第三维:19和13,但是doInference_cu这个函数跑就是有区别。 |
等会加我说吧,要给我张图,我测试下,跑一下看看 |
好的,多谢您! |
您好,tensorrt部分的代码关键点的个数为4的时候正常运行,但是关键点为2的数据集合训练后导出onnx,c++推理报cuda failure 700错误,请问可能是什么原因?非常感谢!
The text was updated successfully, but these errors were encountered: