-
Notifications
You must be signed in to change notification settings - Fork 3.6k
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
Confused about AveragePool op ceil_mode attribute #3314
Comments
Hi @blacklong28, |
For reference - I had a similar question about ceil mode in MaxPool #2971 |
@kraiskil @jcwchen out_shape[i] = int(
np.ceil(
float(
input_spatial_shape[i])
/ float(
strides_spatial[i]))) from the https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/core/providers/cpu/nn/pool_attributes.h,
The two places don't mesh well
|
HI @kraiskil @blacklong28, We will update here once @onnx/sig-operators has finalized the decision. It is definitely something needs to be clear in the document/ONNX test code. Thank you for bringing this up! |
Is this still relevant? If so, what is blocking it? Is there anything you can do to help move it forward? This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. |
Reopen it since this issue hasn't been resolved yet. |
Ask a Question
Question
When I was study the AveragePool op, I am confused about the ceil_mode attr.
What I see at AveragePool
But I notice when auto_pad is set,
it only uses ceil to compute the output shape.
Is the ceil_mode attr only used when auto_pad is 'NOTSET'?
Further information
Who can help me? Thanks very much.
The text was updated successfully, but these errors were encountered: