Build software better, together

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、reg…

Updated Oct 6, 2021
Python

quic / aimet

Star

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

open-source machine-learning opensource deep-neural-networks compression deep-learning pruning quantization auto-ml network-quantization network-compression

Updated Mar 13, 2023
Python

tensorflow / model-optimization

Star

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

machine-learning sparsity compression deep-learning tensorflow optimization keras ml pruning quantization model-compression quantized-training quantized-neural-networks quantized-networks

Updated Mar 10, 2023
Python

neuralmagic / deepsparse

Star

Inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application

Updated Mar 13, 2023
Python

PaddlePaddle / PaddleSlim

Star

PaddleSlim is an open-source library for deep model compression and architecture search.

sparsity compression detection transformer segmentation pruning quantization nas bert tensorrt distillation ernie yolov5 yolov6 yolov7

Updated Mar 13, 2023
Python

openvinotoolkit / training_extensions

Star

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

machine-learning computer-vision deep-learning pytorch semi-supervised-learning image-classification object-detection transfer-learning image-segmentation quantization action-recognition automl incremental-learning anomaly-detection hyper-parameter-optimization self-supervised-learning openvino neural-networks-compression datumaro

Updated Mar 13, 2023
Python

intel / neural-compressor

Star

Intel® Neural Compressor (formerly known as Intel® Low Precision Optimization Tool), targeting to provide unified APIs for network compression technologies, such as low precision quantization, sparsity, pruning, knowledge distillation, across different deep learning frameworks to pursue optimal inference performance.

sparsity deep-learning pruning quantization knowledge-distillation auto-tuning low-precision quantization-aware-training post-training-quantization

Updated Mar 13, 2023
Python

huggingface / optimum

Star

🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools

training optimization intel transformers inference pytorch quantization onnx onnxruntime graphcore habana

Updated Mar 13, 2023
Python

htqin / awesome-model-quantization

Star

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

awesome deep-learning quantization binarization model-compression model-acceleration binary-network binarized-neural-networks lightweight-neural-network model-quantization efficient-deep-learning

Updated Feb 21, 2023

Xilinx / brevitas

Star

Brevitas: quantization-aware training in PyTorch

text-to-speech fpga pytorch speech-recognition neural-networks image-classification xilinx quantization hardware-acceleration brevitas

Updated Mar 13, 2023
Python

guan-yuan / awesome-AutoML-and-Lightweight-Models

Star

A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.