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

Training a quantized int8 version of yolo #24

Closed
nezarelkadyy opened this issue Jul 6, 2023 · 3 comments · Fixed by #49
Closed

Training a quantized int8 version of yolo #24

nezarelkadyy opened this issue Jul 6, 2023 · 3 comments · Fixed by #49
Assignees
Labels
enhancement New feature or request

Comments

@nezarelkadyy
Copy link

How to make train a quantized int 8 version using the train script?

@naseemap47
Copy link
Owner

Hi @nezarelkadyy ,
Currently I didn't added int8 quantisation.
I am still searching on how to do that.
If I finds, I will let you know. or If you find any, please let me know.
Thank you.

@naseemap47 naseemap47 self-assigned this Jul 10, 2023
@naseemap47 naseemap47 added the enhancement New feature or request label Jul 10, 2023
@naseemap47
Copy link
Owner

Hi @nezarelkadyy ,
I completed the development #49
I am facing issue while running QAT.
NameError: name 'SelectiveQuantizer' is not defined Deci-AI/super-gradients#1205 (comment)
They will fix this issue in the upcoming release. (Deci-AI/super-gradients#1205 (comment))
If you find any solution, please let me know.
Thank you.

@naseemap47 naseemap47 linked a pull request Oct 2, 2023 that will close this issue
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants