FluxML/Flux.jl

Optional batch dimension for convolutions

Open

#593 创建于 2019年2月4日

在 GitHub 查看
 (3 评论) (0 反应) (0 负责人)Julia (4,725 star) (619 fork)batch import
help wanted

描述

Currently Conv is the only place a batch dimension is required. It would be nice to check dimensions and reshape as necessary so that it isn't require, for convenience.

#583

贡献者指南

技术栈
无
领域
machine learning
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
half day
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
Familiarity with JuliaBasic Flux knowledgeUnderstanding of convolutions
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
40
研究方向
Review the referenced issue #583 for context on why batch dimension is required. Examine the Conv implementation in the Flux source to understand the current shape expectations. Implement logic to detect batch dimension presence and reshape accordingly, ensuring backward compatibility.