sparsezooNeural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes
Stars: ✭ 264 (+91.3%)
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 (+792.75%)
DistillerNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Stars: ✭ 3,760 (+2624.64%)
EfficientnasTowards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906
Stars: ✭ 44 (-68.12%)
AimetAIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Stars: ✭ 453 (+228.26%)
AmlaAutoML frAmework for Neural Networks
Stars: ✭ 119 (-13.77%)
Haq[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Stars: ✭ 247 (+78.99%)
Model OptimizationA toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Stars: ✭ 992 (+618.84%)
Ntaggerreference pytorch code for named entity tagging
Stars: ✭ 58 (-57.97%)
Awesome EmdlEmbedded and mobile deep learning research resources
Stars: ✭ 554 (+301.45%)
BrevitasBrevitas: quantization-aware training in PyTorch
Stars: ✭ 343 (+148.55%)
Awesome Ml Model CompressionAwesome machine learning model compression research papers, tools, and learning material.
Stars: ✭ 166 (+20.29%)
NncfPyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference
Stars: ✭ 218 (+57.97%)
fastT5⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Stars: ✭ 421 (+205.07%)
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 (+359.42%)
PaddleslimPaddleSlim is an open-source library for deep model compression and architecture search.
Stars: ✭ 677 (+390.58%)
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 (-70.29%)
AutogluonAutoGluon: AutoML for Text, Image, and Tabular Data
Stars: ✭ 3,920 (+2740.58%)
PbaEfficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (+234.06%)
Fast AutoaugmentOfficial Implementation of 'Fast AutoAugment' in PyTorch.
Stars: ✭ 1,297 (+839.86%)
PetridishnnCode for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search
Stars: ✭ 112 (-18.84%)
deepvacPyTorch Project Specification.
Stars: ✭ 507 (+267.39%)
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 (+382.61%)
bert-squeeze🛠️ Tools for Transformers compression using PyTorch Lightning ⚡
Stars: ✭ 56 (-59.42%)
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 (+400.72%)
ppqPPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Stars: ✭ 281 (+103.62%)
DartsDifferentiable architecture search for convolutional and recurrent networks
Stars: ✭ 3,463 (+2409.42%)
Kd libA Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Stars: ✭ 173 (+25.36%)
PaddleclasA treasure chest for image classification powered by PaddlePaddle
Stars: ✭ 625 (+352.9%)
Awesome Edge Machine LearningA curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.
Stars: ✭ 139 (+0.72%)
AutoclintA specially designed light version of Fast AutoAugment
Stars: ✭ 171 (+23.91%)
image-classificationA collection of SOTA Image Classification Models in PyTorch
Stars: ✭ 70 (-49.28%)
optimum🏎️ Accelerate training and inference of 🤗 Transformers with easy to use hardware optimization tools
Stars: ✭ 567 (+310.87%)
aws-rekognitionA Laravel Package/Facade for the AWS Rekognition API
Stars: ✭ 20 (-85.51%)
AI-LABThis repository contains a docker image that I use to develop my artificial intelligence applications in an uncomplicated fashion. Python, TensorFlow, PyTorch, ONNX, Keras, OpenCV, TensorRT, Numpy, Jupyter notebook... 🐋🔥
Stars: ✭ 44 (-68.12%)
GFNet[NeurIPS 2021] Global Filter Networks for Image Classification
Stars: ✭ 199 (+44.2%)
autodoOfficial PyTorch code for CVPR 2021 paper "AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation"
Stars: ✭ 19 (-86.23%)
colorquantGo library for color quantization and dithering
Stars: ✭ 75 (-45.65%)
AMP-RegularizerCode for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021
Stars: ✭ 26 (-81.16%)
RMNetRM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.
Stars: ✭ 129 (-6.52%)
Auto-SurpriseAn AutoRecSys library for Surprise. Automate algorithm selection and hyperparameter tuning 🚀
Stars: ✭ 19 (-86.23%)
pytorch2kerasPyTorch to Keras model convertor
Stars: ✭ 788 (+471.01%)
onnx2tensorRttensorRt-inference darknet2onnx pytorch2onnx mxnet2onnx python version
Stars: ✭ 14 (-89.86%)
HSI-Traditional-to-Deep-ModelsPytorch and Keras Implementations of Hyperspectral Image Classification -- Traditional to Deep Models: A Survey for Future Prospects.
Stars: ✭ 72 (-47.83%)
gcp-mlGoogle Cloud Platform Machine Learning Samples
Stars: ✭ 31 (-77.54%)
HugsVisionHugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (+11.59%)
SketchRecognitionModel and Android app for sketch recognition using Google's quickdraw dataset
Stars: ✭ 28 (-79.71%)
live-cctvTo detect any reasonable change in a live cctv to avoid large storage of data. Once, we notice a change, our goal would be track that object or person causing it. We would be using Computer vision concepts. Our major focus will be on Deep Learning and will try to add as many features in the process.
Stars: ✭ 23 (-83.33%)