LuxDL/Lux.jl

Higher level recurrent layers

Open

#972 opened on Oct 7, 2024

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Julia (700 stars) (84 forks)batch import
good first issue

Description

Hi! While it is relatively straightforward to implement higher level constructions like LSTM and GRU it's also nice to have a layer provided by the library like PyTorch does, having details like bidirectionality and dropout taken care of. Are there any plans to include this in Lux as well?

Thanks!

Contributor guide

Tech stack
None
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.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
unclear
Prerequisites
Julia programmingRecurrent neural networksLux.jl internals
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30
Research direction
Research the existing Lux layer API in the Lux.jl source code to understand how new layers are added. Study PyTorch's RNN implementation for reference on handling bidirectionality and dropout. Engage with maintainers in the issue comments to clarify requirements and expected API design.