quantized-neural-networks topic
BitPack
BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.
HAWQ
Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
larq
An Open-Source Library for Training Binarized Neural Networks
qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
caffe-int8-convert-tools
Generate a quantization parameter file for ncnn framework int8 inference
ZeroQ
[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework
mobilenet_v1_stm32_cmsis_nn
Mobilenet v1 trained on Imagenet for STM32 using extended CMSIS-NN with INT-Q quantization support
Pytorch_Quantize_impls
Some recent Quantizing techniques on PyTorch
quantized-nets
Contains code for Binary, Ternary, N-bit Quantized and Hybrid CNNs for low precision experiments.