I have a pre-computed co-occurence matrix in shape of [NxN]

I want to utilize this info on the last layer of my multi-label classification of [B, N].

Is dot product the best way to do it? How do I use dot product in Tensor with [B, N] and [N, N]?

  • $\begingroup$ To clarify, you're asking if it is ok to multiply a $B\times N$ matrix with another $N\times N$ matrix? why wouldn't that be possible? $\endgroup$ Sep 27, 2022 at 19:14


You must log in to answer this question.

Browse other questions tagged .