Convolutional-KANs
by AntonioTepsich (personal account)
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel. (description from the project’s GitHub page)
Repository facts
- Stars
- 920
- Forks
- 94
- Open issues and pull requests
- 13
- Primary language
- Jupyter Notebook
- License
- MIT License (MIT)
- Owner
- AntonioTepsich · Personal account
- Created
- May 7, 2024
- Last push
- Apr 8, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 790: advimman/lama
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
10,321 starsJupyter NotebookApache-2.0Last push Feb 5, 2025
Rank 5,149: patrick-llgc/Learning-Deep-Learning
Paper reading notes on Deep Learning and Machine Learning
1,279 starsJupyter NotebookNo license file detectedLast push Jun 4, 2026
Rank 5,919: qqlu/Entity
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
1,051 starsJupyter NotebookOther licenseLast push Nov 30, 2023
Rank 6,773: bupt-ai-cz/LLVIP
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
854 starsJupyter NotebookNo license file detectedLast push Aug 9, 2025
Rank 1,284: Hironsan/BossSensor
Hide screen when boss is approaching.
6,290 starsPythonMITLast push Oct 31, 2018
Rank 4,080: dog-qiuqiu/MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB
1,745 starsCOther licenseLast push Feb 6, 2021