clab/dynet

pickneglogsoftmax for a matrix input

Open

#1,077 opened on 2017年11月20日

GitHub で見る
 (1 comment) (0 reactions) (0 assignees)C++ (701 forks)github user discovery
enhancementhelp wanted

Repository metrics

Stars
 (3,433 stars)
PR merge metrics
 (PR metrics pending)

説明

Hi,

I can understand the input for pickneglogsoftmax needs to be a vector. If the input is a matrix, I currently have to use select_cols in advance to pick the col vector. Is it the only way to do? Or pickneglogsoftmax may support matrix input in the future?

Thanks!

コントリビューターガイド