FluxML/Flux.jl

Does Flux support N-dimensional convolutions, where N>3?

Open

#451 创建于 2018年10月22日

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

描述

While this works:

Conv((1,1,1), 1=>1)(rand(1,1,1,1,1)) #3D convolution

This throws an error:

Conv((1,1,1,1), 1=>1)(rand(1,1,1,1,1,1)) #4D convolution
#ERROR: MethodError: no method matching conv!(::Array{Float64,6}, ::Array{Float64,6}, ::Array{Float64,6}; pad=(0, 0, 0, 0), stride=(1, 1, 1, 1), dilation=(1, 1, 1, 1))

I'm running Julia 0.7 and:

[587475ba] Flux v0.6.7+ #master (https://github.com/FluxML/Flux.jl.git)
[872c559c] NNlib v0.4.2+ #master (https://github.com/FluxML/NNlib.jl.git)

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。
4
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。
3-5 days
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
JuliaFluxconvolution operations
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。
30
研究方向
Investigate the conv! function in Flux and NNlib to understand why it only supports up to 3D convolutions. The error indicates no method matching conv! for 6D arrays. Extending the convolution to arbitrary N dimensions would require modifying the underlying implementation to handle dynamic kernel sizes and padding. Look at the existing code for 3D convolutions and generalize it, possibly leveraging broadcast or loop structures. Check if there are any open PRs or discussions in the issue comments for guidance.