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
you are probably using tensorrt10, INetworkDefinition.add_padding() is changed to INetworkDefinition.add_padding_nd()
Im using torch2trt 0.5.0 and trt 10.0.1, and have the same issue, after reimplementing the pad convert using add_padding_nd(), not it fail on shaping issue, looks like padding_nd outputs dynamic shaping. Any idea how to resolve this?
Hi all, when I run conversion of the following operation:
I get the error below:
Do you know any way to circumvent this issue? Thanks in advance 🙏
The text was updated successfully, but these errors were encountered: