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

Model preservation and transformation problems(模型保存和转换的问题) #964

Open
CvBokchoy opened this issue Oct 26, 2024 · 7 comments

Comments

@CvBokchoy
Copy link

How do I save the model trained with the example as a pt file or something else and convert it to an onnx model。
(请问如何将用示例训练好的模型保存为pt文件或者其他,并且转换为onnx模型??)

@josef821
Copy link

hi, i use this code to my unet;
after running my model with this code:
outputs = model(IMGDATA)
i use this code for export to onnx
torch.onnx.export(model,IMGDATA,"model.onnx")

@CvBokchoy
Copy link
Author

hi, i use this code to my unet; after running my model with this code: outputs = model(IMGDATA) i use this code for export to onnx torch.onnx.export(model,IMGDATA,"model.onnx")

thank you very much!

@CvBokchoy
Copy link
Author

hi, i use this code to my unet; after running my model with this code: outputs = model(IMGDATA) i use this code for export to onnx torch.onnx.export(model,IMGDATA,"model.onnx")

Could you share your C++ tensorRT pre-deployment and post-deployment code snippets, I'm having a little trouble here. thank you

@josef821
Copy link

josef821 commented Nov 8, 2024

im not coding in c++

@CvBokchoy
Copy link
Author

im not coding in c++

Can you help me? i need a C++ tensorrt version inference this model sample. thank you very much!

1 similar comment
@CvBokchoy
Copy link
Author

im not coding in c++

Can you help me? i need a C++ tensorrt version inference this model sample. thank you very much!

@josef821
Copy link

i don't have any source code of c++ tensorrt.

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