FluxML/Flux.jl

Optional batch dimension for convolutions

Open

#593 opened on Feb 4, 2019

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Julia (4,725 stars) (619 forks)batch import
help wanted

Description

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

Contributor guide

Tech stack
None
Domain
machine learning
Issue type
feature
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.
half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Familiarity with JuliaBasic Flux knowledgeUnderstanding of convolutions
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40
Research direction
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.