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

Maybe something outdate when quantizing YOLO11 #2493

Open
weiyusheng opened this issue Oct 30, 2024 · 0 comments
Open

Maybe something outdate when quantizing YOLO11 #2493

weiyusheng opened this issue Oct 30, 2024 · 0 comments

Comments

@weiyusheng
Copy link

not a bug firstly

English is not my native language; please excuse typing errors.

I just try to quantizing YOLO11n along with "notebooks/quantizing-model-with-accuracy-control/yolov8-quantization-with-accuracy-control.ipynb" and it simply fails.

Then, I notice that this file uses "ultralytics==8.1.42" which does not support YOLO11.

After updating the version of ultralytics, errors come from another part -- Run quantization with accuracy control.

image

I try to solve it and find a simple way.

Before the "Run quantization with accuracy control" part, there is a function called validation_ac in which describes validator.stats with "tp_m,tp,conf,pred_cls,target_cls". But the soource code of ultralytics describes validator.stats with "tp,conf,pred_cls,target_cls,target_img". So I just change the description and it works.

before:

image

validator.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[])

after:

image

validator.stats = dict(tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])

I'm writing this issue to ask if you'd like to update the file to support new YOLO models.

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

1 participant