Mask indices of tensor from binaries (e.g. from Comparison Ops)

Yes, indeed, it destroys the chain. I guess in many contexts this is not a problem.

I think a context where you want to optimize on the mask is more likely to be some kind of RL problem where you have a discrete action space.

Variable.nonzero is not implemented yet as discussed in the link below. However, if it was, I wonder how the backward would be implemented, since it outputs indices…

See an interesting discussion here too:

1 Like