LuxDL/Lux.jl

Higher level recurrent layers

Open

#972 建立於 2024年10月7日

在 GitHub 查看
 (2 留言) (0 反應) (0 負責人)Julia (700 star) (84 fork)batch import
good first issue

描述

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!

貢獻者指南

技術棧
無
領域
machine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
over 1 week
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
unclear
前置要求
Julia programmingRecurrent neural networksLux.jl internals
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
30
研究方向
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.
Higher level recurrent layers · LuxDL/Lux.jl#972 | Good First Issue