I have tried to make a 3D convolutional layer with the following parameters:
padding='same' and groups='in_channels' and l get an AssertionError. Either with
tltorch.FactorizedConv() or tltorch.FactorizedConv.from_conv()
It seems that padding='same' with groups is not supported in tensorly.
I have tried to make a 3D convolutional layer with the following parameters:
padding='same'
andgroups='in_channels'
and l get anAssertionError.
Either withtltorch.FactorizedConv()
ortltorch.FactorizedConv.from_conv()
It seems that
padding='same'
withgroups
is not supported in tensorly.padding='same'
in pytorch pytorch doc on paddinggroups= in_channels
in pytorch groups in convThank you for your help.