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.

Sign up for GitHub

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

Jump to bottom

the model precision drop from 90% to 51% when quantize from float32 to int8. (AIV-559) #105

Closed
cab1211 opened this issue Nov 1, 2022 · 1 comment
Closed

the model precision drop from 90% to 51% when quantize from float32 to int8. (AIV-559) #105

cab1211 opened this issue Nov 1, 2022 · 1 comment

Comments

@cab1211
Copy link

cab1211 commented Nov 1, 2022

the model precision drop from 90% to 51% when quantize from float32 to int8， but didn't drop with the int16.
@github-actions github-actions bot changed the title the model precision drop from 90% to 51% when quantize from float32 to int8. the model precision drop from 90% to 51% when quantize from float32 to int8. (AIV-559) Nov 1, 2022
@sun-xiangyu
Copy link
Collaborator

please try esp-ppq

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@cab1211 @sun-xiangyu