PaddleslimPaddleSlim is an open-source library for deep model compression and architecture search.
Stars: ✭ 677 (+1047.46%)
Model OptimizationA toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Stars: ✭ 992 (+1581.36%)
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 (+1988.14%)
Pretrained Language ModelPretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Stars: ✭ 2,033 (+3345.76%)
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (+91.53%)
Kd libA Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Stars: ✭ 173 (+193.22%)
DistillerNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Stars: ✭ 3,760 (+6272.88%)
HawqQuantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.
Stars: ✭ 108 (+83.05%)
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 (+1071.19%)
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 (-30.51%)
BitPackBitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.
Stars: ✭ 36 (-38.98%)
bert-squeeze🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
Stars: ✭ 56 (-5.08%)
Awesome Ml Model CompressionAwesome machine learning model compression research papers, tools, and learning material.
Stars: ✭ 166 (+181.36%)
Ntaggerreference pytorch code for named entity tagging
Stars: ✭ 58 (-1.69%)
Zeroq[CVPR'20] ZeroQ: A Novel Zero Shot Quantization Framework
Stars: ✭ 150 (+154.24%)
Quantization.mxnetSimulate quantization and quantization aware training for MXNet-Gluon models.
Stars: ✭ 42 (-28.81%)
SaiSDK for TEE AI Stick (includes model training script, inference library, examples)
Stars: ✭ 28 (-52.54%)
Cnn QuantizationQuantization of Convolutional Neural networks.
Stars: ✭ 141 (+138.98%)
Libimagequant Rustlibimagequant (pngquant) bindings for the Rust language
Stars: ✭ 17 (-71.19%)
Ctranslate2Fast inference engine for OpenNMT models
Stars: ✭ 140 (+137.29%)
Awesome Edge Machine LearningA curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.
Stars: ✭ 139 (+135.59%)
PaddleclasA treasure chest for image classification powered by PaddlePaddle
Stars: ✭ 625 (+959.32%)
Dsqpytorch implementation of "Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks"
Stars: ✭ 70 (+18.64%)
Jacinto Ai DevkitTraining & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-16.95%)
Nlp ArchitectA model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks
Stars: ✭ 2,768 (+4591.53%)
AimetAIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Stars: ✭ 453 (+667.8%)
Inq PytorchA PyTorch implementation of "Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights"
Stars: ✭ 147 (+149.15%)
TF2DeepFloorplanTF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.
Stars: ✭ 98 (+66.1%)
DS-Net(CVPR 2021, Oral) Dynamic Slimmable Network
Stars: ✭ 204 (+245.76%)
Lq NetsLQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Stars: ✭ 195 (+230.51%)
DfqPyTorch implementation of Data Free Quantization Through Weight Equalization and Bias Correction.
Stars: ✭ 125 (+111.86%)
PngquantLossy PNG compressor — pngquant command based on libimagequant library
Stars: ✭ 4,086 (+6825.42%)
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 (+974.58%)
NncfPyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference
Stars: ✭ 218 (+269.49%)
Awesome EmdlEmbedded and mobile deep learning research resources
Stars: ✭ 554 (+838.98%)
GraffitistGraph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow
Stars: ✭ 135 (+128.81%)
DeephashAn Open-Source Package for Deep Learning to Hash (DeepHash)
Stars: ✭ 417 (+606.78%)
ZS-F-VQACode and Data for paper: Zero-shot Visual Question Answering using Knowledge Graph [ ISWC 2021 ]
Stars: ✭ 51 (-13.56%)
BrevitasBrevitas: quantization-aware training in PyTorch
Stars: ✭ 343 (+481.36%)
LibimagequantPalette quantization library that powers pngquant and other PNG optimizers
Stars: ✭ 344 (+483.05%)
Pytorch PlaygroundBase pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
Stars: ✭ 2,201 (+3630.51%)
Deephash PapersMust-read papers on deep learning to hash (DeepHash)
Stars: ✭ 302 (+411.86%)
FinnDataflow compiler for QNN inference on FPGAs
Stars: ✭ 284 (+381.36%)
QkerasQKeras: a quantization deep learning library for Tensorflow Keras
Stars: ✭ 254 (+330.51%)
Haq[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Stars: ✭ 247 (+318.64%)
sparsifyEasy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint
Stars: ✭ 138 (+133.9%)
quantize🎨 Simple color palette quantization using MMCQ
Stars: ✭ 24 (-59.32%)
FrostnetFrostNet: Towards Quantization-Aware Network Architecture Search
Stars: ✭ 85 (+44.07%)
colorquantGo library for color quantization and dithering
Stars: ✭ 75 (+27.12%)
TerngradTernary Gradients to Reduce Communication in Distributed Deep Learning (TensorFlow)
Stars: ✭ 168 (+184.75%)
PyeprPowerful, automated analysis and design of quantum microwave chips & devices [Energy-Participation Ratio and more]
Stars: ✭ 81 (+37.29%)
aaai17-cdqThe implementation of AAAI-17 paper "Collective Deep Quantization of Efficient Cross-modal Retrieval"
Stars: ✭ 33 (-44.07%)