AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
Winner solution of mobile AI (CVPRW 2021).
Binarize convolutional neural networks using pytorch π₯
Pytorch implementation of our paper accepted by NeurIPS 2020 -- Rotated Binary Neural Network
Proximal Mean-field for Neural Network Quantization
AIMET GitHub pages documentation
Caffe implementation of "Learning Compression from Limited Unlabeled Data" (ECCV2018).
[T-PAMI 2022] Quantformer: Learning Extremely Low-precision Vision Transformers
πΆ Explore data compression through music and visuals, creating melodies and graphics using Huffman coding and Run-Length Encoding in this interactive web app.
Add a description, image, and links to the network-quantization topic page so that developers can more easily learn about it.
To associate your repository with the network-quantization topic, visit your repo's landing page and select "manage topics."