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

Add YOLO11 Model Support #573

Open
lakshanthad opened this issue Oct 6, 2024 · 11 comments
Open

Add YOLO11 Model Support #573

lakshanthad opened this issue Oct 6, 2024 · 11 comments

Comments

@lakshanthad
Copy link

Hello @marcoslucianops,

Great work on DeepStream-Yolo!

With the release of the latest Ultralytics YOLO11 models, it would be great to have DeepStream support for these models.

Thank you.

@neilyoung
Copy link

+1

@neilyoung
Copy link

@lakshanthad Oh, I see that the V8 converter also works for yolo11 models

@githubwalt
Copy link

What do you mean by "V8 converter"?

@neilyoung
Copy link

neilyoung commented Oct 12, 2024

python3 utils/export_yoloV8.py -w yolo11s.pt

use the resulting onnx model then

@lakshanthad
Copy link
Author

Great @neilyoung. However, it would be nice to have a separate section for YOLO11.

Btw, please refer to the below instructions for YOLOv8. Still waiting for merge:
#551

@neilyoung
Copy link

@lakshanthad Thanks for making me aware of this.

@worstshit
Copy link

python3 utils/export_yoloV8.py -w yolo11s.pt

use the resulting onnx model then

I tried this but it doesn't work. It will come into an AttributeError:
Can't get attribute 'C3k2' on <module 'ultralytics.nn.modules.block' from ....>
Can you please help tell how to fix this problem? Thank you.

@neilyoung
Copy link

@worstshit Well, I downloaded the weights from here and ran the script as shown

wget https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s.pt

@jugal-sheth
Copy link

jugal-sheth commented Oct 14, 2024

@worstshit Kindly install updated ultralytics[export] package

pip3 install ultralytics[export]
pip3 install cmake
pip3 install onnxsim

@worstshit
Copy link

worstshit commented Oct 18, 2024

@worstshit Well, I downloaded the weights from here and ran the script as shown

wget https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s.pt

@neilyoung I'm sorry to ask again, i still failed with this export yolov11 model to onnx. I use jetson nx 16GB and tried as follows:
first, run the command pip3 install ultralytics[export], pip3 install cmake, pip3 install onnxsim.
second, git clone https://github.com/marcoslucianops/DeepStream-Yolo
cd DeepStream-Yolo
thirdly, wget https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s.pt
finally, python3 utils/export_yoloV8.py -w yolo11n.pt
and I come into the same error:
Can't get attribute 'C3k2' on <module 'ultralytics.nn.modules.block' from ....>
Can you please help tell is there missing some steps or something wrong? thank you.

@neilyoung
Copy link

Launch a clean Ubuntu 22.04 VM, install this repo and deps there and do the conversion

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

5 participants