NUS-HPC-AI-Lab/InfoBatch

Some questions If I plug it into yolov8 and use it,pls

crisych opened this issue · 6 comments

Hi,if i use it in yolov8,What would happen?
I mean, will the parameters decrease or will just increase the speed of training and shorten the reasoning time?
Also, could you show me how to use it in yolov8,thanks.

Hi, thank you for the interest. We are currently working on the public example. Previously our contributor has verified it on private data; we will release the public example this week or next.

Thanks for your reply, I will stay tuned

Hi, take the liberty of asking, when will the example about yolov8 be released?I can't wait to study

Sorry, just got to be suddenly busy and miss the time. I will continue on it next week.

The same questions, when will the example about yolov8 be released?
thx

@Zhou2019 @crisych @tiandunx I have adapted the loss and training run for ultralytics YOLO. See https://github.com/henryqin1997/ultralytics-infobatch . Do you have hyperparameters so that I can test whether it reproduce lossless result with reported saving? I will update the document this weekend to show how I adapt it. Right now one can find it in study_case.ipynb and commit records.