FluxML / FluxML/GeometricFlux.jl

Implementation of E(N)-Equivariant Steerable CNNs

Open
#331 0 comments 1 reaction 0 assignees View on GitHub
Dominant language
Julia
Stars
353
Forks
31
PR merge metrics
No merged PRs in 30d

Description

> [QUVA-Lab/escnn](https://github.com/QUVA-Lab/escnn)
> Ref. [A Program to Build E(N)-Equivariant Steerable CNNs](https://openreview.net/forum?id=WE4qe9xlnQw)

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reviewing the linked escnn repository and the referenced paper, then compare their E(N)-equivariant steerable CNNs with GeometricFlux.jl's existing capabilities. The issue does not name files, tests, or a precise scope; done would require agreeing on and implementing the missing functionality in GeometricFlux.jl.

Written by the indexing model from the issue text.

Assessment

Tech stack
julia
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.