Closed vieting closed 2 years ago
Btw, you need to rebase this such that we get the new behavior version (#93).
Apparently the output still does not match.
Apparently the output still does not match.
This is strange. Can you check at what point it gets wrong? You could also calculate it by hand for some simple values.
The PR can be marked as ready, right? (When all tests are passing now.)
So far, I added a
DotProductAlongDim
module to do the dot product. The rest is done insidetorch.nn.functional.cosine_similarity
using existing functions. However, there is a problem with theDotLayer
:for the layer
with inputs