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.

Sign up for GitHub

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

Jump to bottom

how can I load dynamic Tensorrt model? #8571

Closed
1 task done
WangxuP opened this issue Jul 14, 2022 · 1 comment · Fixed by #8526
Closed
1 task done

how can I load dynamic Tensorrt model? #8571

WangxuP opened this issue Jul 14, 2022 · 1 comment · Fixed by #8526
Labels
question Further information is requested

Comments

@WangxuP
Copy link

WangxuP commented Jul 14, 2022

Search before asking

Question

how can I load dynamic Tensorrt model?
when I use trtexec export dynamic engine file, But can not get correct predict, That's why I asked this question

yolov5 export onnx model as below:

python3 export.py --weights dymc.pt --include onnx --dynamic

trtexec export model as below:

trtexec --onnx=dymc.onnx --minShapes=images:1x3x640x640  --optShapes=images:10x3x640x640 --maxShapes=images:10x3x640x640 --saveEngine=dynmc-trt.engine --fp16

Additional

No response
@WangxuP WangxuP added the question Further information is requested label Jul 14, 2022
@glenn-jocher glenn-jocher linked a pull request Jul 15, 2022 that will close this issue
Dynamic batch size support for TensorRT #8526
Merged
@glenn-jocher
Copy link
Member

@WangxuP try PR #8526

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
question Further information is requested
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Dynamic batch size support for TensorRT democat3457/yolov5
2 participants
@WangxuP @glenn-jocher