FluxML/Flux.jl

Weights shape not validated against kernel, channels

Open

#2,506 opened on Oct 25, 2024

View on GitHub
 (5 comments) (1 reaction) (0 assignees)Julia (619 forks)batch import
good first issuehelp wanted

Repository metrics

Stars
 (4,725 stars)
PR merge metrics
 (Avg merge 3d 6h) (6 merged PRs in 30d)

Description

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.

Contributor guide

Research direction
Inspect the existing Conv initialization code and add validation to ensure that the provided weight tensor dimensions match the expected kernel size and number of input channels.
Tech stack
None
Domain
machine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Juliadeep learning
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70