quantized-neural-networks topic

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

Zhen-Dong

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

Zhen-Dong

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

tensorflow

An Open-Source Library for Training Binarized Neural Networks

larq

QKeras: a quantization deep learning library for Tensorflow Keras

google

Generate a quantization parameter file for ncnn framework int8 inference

BUG1989

[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework

amirgholami

Mobilenet v1 trained on Imagenet for STM32 using extended CMSIS-NN with INT-Q quantization support

EEESlab

Some recent Quantizing techniques on PyTorch

Enderdead

Contains code for Binary, Ternary, N-bit Quantized and Hybrid CNNs for low precision experiments.

yashkant