Oh… no it’s not. I’m sorry, I missed your point about Batchnorm here.
I don’t thinks it is possible to use the default batchnorm here. You would need to have your input data projected into same size tensors (some interpolation method?).
Oh… no it’s not. I’m sorry, I missed your point about Batchnorm here.
I don’t thinks it is possible to use the default batchnorm here. You would need to have your input data projected into same size tensors (some interpolation method?).