GitHub

[inductor] [cuda] [fake tensor] ConvTranspose behave differently when Input type and weight ...

shaoyuyoung changed the title [inductor] [cuda] [type matching] ConvTranspose behave differently when Input type and weight type is not the same [inductor] [cuda] [type matching] ConvTranspose behave ...
GitHub

AssertionError: Per channel weight observer is not supported yet for ConvTranspose{n}d.

AssertionError: Per channel weight observer is not supported yet for ConvTranspose{n}d. The model is using Conv2DTranspose layers. As per my understanding it should work for other layers. When I ...