-
Notifications
You must be signed in to change notification settings - Fork 74k
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
Optimize graph & graph transform tools do not support NCHW #15034
Comments
Could you provide a reproducible test case of what exactly you tried to do? Generally speaking, I think a lot of the tooling after training requires NHWC, as that was the only format when those were written. If you could provide a reproducible test case, we could work to improve it. @petewarden, do you have any other comments? |
I tried:
and
In both cases, the error occurred in fused batchnorm. The frozen model worked well, but the optimized model and transformed model emitted error. |
It has been 14 days with no activity and this issue has an assignee.Please update the label and/or status accordingly. |
Nagging Assigneee: It has been 14 days with no activity and this issue has an assignee. Please update the label and/or status accordingly. |
Nagging Assignee: It has been 14 days with no activity and this issue has an assignee. Please update the label and/or status accordingly. |
I tried optimizing graph using both Graph transform tool and Optimize graph for inference. Both cases produced the same error because the fused batchnorm used not NCHW, but NHWC. I've got the error like this:
Although NCHW is faster than NHWC in GPU environment, why the tools do not support NCHW?
The text was updated successfully, but these errors were encountered: