ChristophReich1996/Involution

PyTorch reimplementation of the paper "Involution: Inverting the Inherence of Convolution for Visual Recognition" (2D and 3D Involution) [CVPR 2021].

44
/ 100
Emerging

This project provides an alternative to traditional convolutional layers for deep learning models, particularly useful for visual recognition tasks. It takes standard image or 3D volumetric data as input and outputs processed feature maps that can be used in subsequent layers of a neural network. It's intended for deep learning researchers and practitioners who are building or experimenting with novel computer vision architectures.

105 stars. No commits in the last 6 months.

Use this if you are a deep learning engineer or researcher exploring new building blocks for computer vision models and want to integrate Involution layers into your PyTorch projects.

Not ideal if you need the most memory-efficient or fastest possible implementation of Involution, as other CUDA-based implementations might be better suited.

deep-learning-research computer-vision image-analysis 3D-data-processing neural-network-architecture
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

105

Forks

22

Language

Python

License

MIT

Last pushed

Mar 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ChristophReich1996/Involution"

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