This repo provides pytorch code which replicates the results of the Matching Networks for One Shot Learning paper on the Omniglot and MiniImageNet dataset
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
bkj opened this issue 6 years ago · comments
On this line you're applying a softmax to the similarities.
Then later you apply cross_entropy, which is a log softmax + NLL loss.
cross_entropy
I think you probably want to remove the first softmax.
~ Ben