On [this line](https://github.com/gitabcworld/MatchingNetworks/blob/master/models/AttentionalClassify.py#L28) you're applying a softmax to the similarities. Then [later](https://github.com/gitabcworld/MatchingNetworks/blob/master/models/MatchingNetwork.py#L88) you apply `cross_entropy`, which is a log softmax + NLL loss. I think you probably want to remove the first softmax. ~ Ben
On this line you're applying a softmax to the similarities.
Then later you apply
cross_entropy, which is a log softmax + NLL loss.I think you probably want to remove the first softmax.
~ Ben