Stateless decoding functionality for Norse, where events in time are
converted to numerical representations. Many of the decoders are simply
mirrors of the
PyTorch Tensor aggregation functions,
with the difference that they typically aggregate the first (temporal) dimension.
They are therefore useful to inject in
modules or situations where you need pickled functions.
- norse.torch.functional.decode.sum_decode(tensor, dimension=0)¶
Sums the input tensor in the first dimension by default.