You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For special case when adaptive pooling used to collapse the output dimension completely (output_size=(1,1)) we should just emit GlobalAveragePooling in ONNX. And complain otherwise.
The text was updated successfully, but these errors were encountered:
Hi @dzhulgakov !
Is there any updates about this issue?
I have just the same problem - I use nn.AdaptiveMaxPool2d((1, 1)) and model becomes unconvertable. It would be great, if you post any hack to solve this problem.
Thanks!
For special case when adaptive pooling used to collapse the output dimension completely (output_size=(1,1)) we should just emit GlobalAveragePooling in ONNX. And complain otherwise.
The text was updated successfully, but these errors were encountered: