david-knigge/ccnn

Code repository of the paper "Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN" https://arxiv.org/abs/2301.10540.

43
/ 100
Emerging

This project offers a new type of Convolutional Neural Network (CNN) architecture called the Continuous Convolutional Neural Network (CCNN). It allows researchers and practitioners to process various types of data, like sequences, images, or 3D point clouds, using a single model without needing to modify its structure. The CCNN takes in diverse raw data and outputs high-performance predictions, often outperforming existing specialized models, making it ideal for machine learning researchers and data scientists.

183 stars. No commits in the last 6 months.

Use this if you need a flexible CNN model that can handle different data types (1D, 2D, 3D) and resolutions without requiring custom architectural changes for each task.

Not ideal if you are looking for a pre-trained, ready-to-use model for a very specific task, as this project focuses on the underlying architecture for building such models.

Machine Learning Research Computer Vision Signal Processing 3D Data Analysis Neural Network Architecture
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

183

Forks

21

Language

Python

License

MIT

Last pushed

May 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/david-knigge/ccnn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.