DNNACAll about acceleration and compression of Deep Neural Networks
Stars: ✭ 29 (-76.8%)
DeephashAn Open-Source Package for Deep Learning to Hash (DeepHash)
Stars: ✭ 417 (+233.6%)
aaai17-cdqThe implementation of AAAI-17 paper "Collective Deep Quantization of Efficient Cross-modal Retrieval"
Stars: ✭ 33 (-73.6%)
Pinto model zooA repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
Stars: ✭ 634 (+407.2%)
Jacinto Ai DevkitTraining & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-60.8%)
neural-compressorIntel® 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.
Stars: ✭ 666 (+432.8%)
DistillerNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Stars: ✭ 3,760 (+2908%)
colorquantGo library for color quantization and dithering
Stars: ✭ 75 (-40%)
fastT5⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Stars: ✭ 421 (+236.8%)
Awesome Automl And Lightweight ModelsA 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.
Stars: ✭ 691 (+452.8%)
Dsqpytorch implementation of "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks"
Stars: ✭ 70 (-44%)
ppqPPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Stars: ✭ 281 (+124.8%)
Awesome EmdlEmbedded and mobile deep learning research resources
Stars: ✭ 554 (+343.2%)
bert-squeeze🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
Stars: ✭ 56 (-55.2%)
FrostnetFrostNet: Towards Quantization-Aware Network Architecture Search
Stars: ✭ 85 (-32%)
ATMC[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”
Stars: ✭ 41 (-67.2%)
BrevitasBrevitas: quantization-aware training in PyTorch
Stars: ✭ 343 (+174.4%)
mmnMoore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks
Stars: ✭ 39 (-68.8%)
Model OptimizationA toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Stars: ✭ 992 (+693.6%)
BitPackBitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.
Stars: ✭ 36 (-71.2%)
FinnDataflow compiler for QNN inference on FPGAs
Stars: ✭ 284 (+127.2%)
quantize🎨 Simple color palette quantization using MMCQ
Stars: ✭ 24 (-80.8%)
ZAQ-codeCVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)
Stars: ✭ 59 (-52.8%)
Libimagequant Rustlibimagequant (pngquant) bindings for the Rust language
Stars: ✭ 17 (-86.4%)
VectorsinsearchDice.com repo to accompany the dice.com 'Vectors in Search' talk by Simon Hughes, from the Activate 2018 search conference, and the 'Searching with Vectors' talk from Haystack 2019 (US). Builds upon my conceptual search and semantic search work from 2015
Stars: ✭ 71 (-43.2%)
KGySoft.DrawingKGy SOFT Drawing is a library for advanced image, icon and graphics handling.
Stars: ✭ 27 (-78.4%)
PaddleslimPaddleSlim is an open-source library for deep model compression and architecture search.
Stars: ✭ 677 (+441.6%)
optimum🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools
Stars: ✭ 567 (+353.6%)
PaddleclasA treasure chest for image classification powered by PaddlePaddle
Stars: ✭ 625 (+400%)
Ntaggerreference pytorch code for named entity tagging
Stars: ✭ 58 (-53.6%)
navecCompact high quality word embeddings for Russian language
Stars: ✭ 118 (-5.6%)
AimetAIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Stars: ✭ 453 (+262.4%)
camalianLibrary used to deal with colors and images. You can extract colors from images.
Stars: ✭ 45 (-64%)
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-9.6%)
pngquantA Python Wrapper of Pngquant
Stars: ✭ 27 (-78.4%)
PngquantLossy PNG compressor — pngquant command based on libimagequant library
Stars: ✭ 4,086 (+3168.8%)
Quantization.mxnetSimulate quantization and quantization aware training for MXNet-Gluon models.
Stars: ✭ 42 (-66.4%)
local-search-quantizationState-of-the-art method for large-scale ANN search as of Oct 2016. Presented at ECCV 16.
Stars: ✭ 70 (-44%)
LibimagequantPalette quantization library that powers pngquant and other PNG optimizers
Stars: ✭ 344 (+175.2%)
PyeprPowerful, automated analysis and design of quantum microwave chips & devices [Energy-Participation Ratio and more]
Stars: ✭ 81 (-35.2%)
sparsezooNeural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Stars: ✭ 264 (+111.2%)
Deephash PapersMust-read papers on deep learning to hash (DeepHash)
Stars: ✭ 302 (+141.6%)
deepvacPyTorch Project Specification.
Stars: ✭ 507 (+305.6%)
SaiSDK for TEE AI Stick (includes model training script, inference library, examples)
Stars: ✭ 28 (-77.6%)
QkerasQKeras: a quantization deep learning library for Tensorflow Keras
Stars: ✭ 254 (+103.2%)
HawqQuantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
Stars: ✭ 108 (-13.6%)
Micronetmicronet, 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、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Stars: ✭ 1,232 (+885.6%)
sparsifyEasy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
Stars: ✭ 138 (+10.4%)