ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
-
Updated
Feb 18, 2021 - Python
ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
(NeurIPS-2019 MicroNet Challenge - 3rd Winner) Open source code for "SIPA: A simple framework for efficient networks"
The concept of a small modular adaptive neural network - about 40 MB (a cell with the possibility of scaling) not too big not too small able to handle a small mp4 file.
Add a description, image, and links to the compact-neural-network topic page so that developers can more easily learn about it.
To associate your repository with the compact-neural-network topic, visit your repo's landing page and select "manage topics."