search

Deci-AI / super-gradients

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
https://www.supergradients.com
Apache License 2.0
4.54k stars 496 forks source link

Training recommendations for QAT #1189

Closed lpkoh closed 1 year ago

lpkoh commented 1 year ago

💡 Your Question

The notebooks: https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/qat_ptq_yolo_nas.md https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/ptq_qat.md https://colab.research.google.com/drive/1yHrHkUR1X2u2FjjvNMfUbSXTkUul6o1P?usp=sharing describes a normal training -> PTQ -> QAT pipeline. Do you have recommendations for 'normal training' and 'QAT'? I observe it uses the same datasets. But should we have same epochs? Should the first stage of normal training use relatively fewer epochs?

Versions

No response

spsancti commented 1 year ago

Hi! Please check out QATRecipeModificationCallback, its default parameters implement rules of thumb on how to perform QAT given you have a "normal" training recipe.

harpreetsahota204 commented 1 year ago

Hi @lpkoh -

Thanks for opening an issue for SG. I'm gathering some feedback on SuperGradients and YOLO-NAS.

Would you be down for a quick call to chat about your experience?

If a call doesn't work for you, no worries. I've got a short survey you could fill out: https://bit.ly/sgyn-feedback.

I know you’re super busy, but your input will help us shape the direction of SuperGradients and make it as useful as possible for you.

I appreciate your time and feedback. Let me know what works for you.

Cheers,

Harpreet