Closed vieting closed 1 year ago
The failing tests are the ones from https://github.com/rwth-i6/pytorch-to-returnn/issues/125.
I wonder if this could share some code.
I also wonder whether this is still correct when you operate on other axes, as I mentioned in the other issue.
But anyway, fine for now.
_FunctionalConvNd
is missing a_get_output_shape_from_returnn()
method. It is very similar to the one of_ConvNd
.