Robin Lobel
Robin Lobel
Ok, the trick was to replace instances of `padding="same"` with `padding=int(dilation * (kernel_size - 1) // 2)`. https://github.com/microsoft/onnxruntime/issues/20582#issuecomment-2099348543
@BtbN Any chance to have Windows Arm64 builds in the coming months ?
Plus one on this feature request, it's must have to search a social platform !
It'd be great is there was another mac alternative to CoreML, which unfortunately cannot run a lot of models... And is still limited to have tensor size dimension