FluxML/Flux.jl

Add max/mean unpooling operations

Open

#395 opened on Sep 11, 2018

View on GitHub
 (5 comments) (6 reactions) (0 assignees)Julia (4,725 stars) (619 forks)batch import
enhancementgood first issuehelp wanted

Description

These are fairly common operations in image2image models (including 3d images) where they go in hand with ConvTranspose layers.

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.
1-2 days
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.
needs investigation
Prerequisites
JuliaFlux.jldeep learningimage2image models
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35
Research direction
Investigate the existing pooling implementation in Flux.jl (likely in src/pooling.jl or similar) to understand the current API. Review the ConvTranspose layers referenced in PR #311 for patterns of inverse operations. Consider adding both max and mean unpooling as separate functions. Check the 5 comments on the issue for additional context and implementation suggestions.