clab/dynet

pickneglogsoftmax for a matrix input

Open

#1,077 opened on Nov 20, 2017

View on GitHub
 (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)

Description

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!

Contributor guide

Research direction
Examine the pickneglogsoftmax function implementation and extend it to handle matrix inputs by applying along columns or rows.
Tech stack
cpp
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++DyNetsoftmax
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60