FluxML/Flux.jl

Weights shape not validated against kernel, channels

Open

#2,506 创建于 2024年10月25日

在 GitHub 查看
 (5 评论) (1 反应) (0 负责人)Julia (4,725 star) (619 fork)batch import
good first issuehelp wanted

描述

weights = Flux.kaiming_normal()(3, 3, 1)
Conv((3, 3), 1 => 1; pad = (1, 1), init = (_...) -> weights)
# Conv((3,), 3 => 1, pad=1)  # 10 parameters

weights = Flux.kaiming_normal()(3, 3, 1, 1)
Conv((3, 3), 1 => 1; pad = (1, 1), init = (_...) -> weights)
# Conv((3, 3), 1 => 1, pad=1)  # 10 parameters

I wanted to strictly specify the weight init for testing, but encountered this odd result. I think there should be validation to ensure that the weight shape matches the kernel size and input channels, and error if there is a mismatch.

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。
1-3 hours
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。
fresh
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
Understanding of Conv layer weight shape conventions
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。
70
研究方向
Look into the Conv layer initialization code in src/layers/conv.jl. Add validation to check that the provided weight tensor (via init) matches the expected shape based on kernel size and input/output channels. The error should be thrown if there is a mismatch, similar to how other shape mismatches are handled.