718 Open source projects that are alternatives of or similar to sparsify

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

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、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

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

针对pytorch模型的自动化模型结构分析和修改工具集，包含自动分析模型结构的模型压缩算法库

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906

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

AutoML frAmework for Neural Networks

[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision

PyTorch Model Compression

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

reference pytorch code for named entity tagging

Embedded and mobile deep learning research resources

Brevitas: quantization-aware training in PyTorch

Awesome machine learning model compression research papers, tools, and learning material.

PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

A 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]

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

[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

Infrastructures™ for Machine Learning Training/Inference in Production.

AutoGluon: AutoML for Text, Image, and Tabular Data

Efficient Learning of Augmentation Policy Schedules

Official Implementation of 'Fast AutoAugment' in PyTorch.

Code for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search

Pruning and quantization for SSD. Model compression.

PyTorch Project Specification.

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.

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

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.

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Differentiable architecture search for convolutional and recurrent networks

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

A treasure chest for image classification powered by PaddlePaddle

A curated list of awesome edge machine learning resources, including research papers, inference engines, challenges, books, meetups and others.

A specially designed light version of Fast AutoAugment

A collection of SOTA Image Classification Models in PyTorch

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

A Laravel Package/Facade for the AWS Rekognition API

Image classifier in Elixir

This 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... 🐋🔥

[NeurIPS 2021] Global Filter Networks for Image Classification

Official PyTorch code for CVPR 2021 paper "AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation"

Go library for color quantization and dithering

Code for our paper "Regularizing Neural Networks via Adversarial Model Perturbation", CVPR2021

Programming assignments, labs and quizzes from all courses in the Coursera AI for Medicine Specialization offered by deeplearning.ai

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

An AutoRecSys library for Surprise. Automate algorithm selection and hyperparameter tuning 🚀

PyTorch to Keras model convertor

tensorRt-inference darknet2onnx pytorch2onnx mxnet2onnx python version

No description or website provided.

about how to use stagesepx in production

No description or website provided.

Pytorch and Keras Implementations of Hyperspectral Image Classification -- Traditional to Deep Models: A Survey for Future Prospects.

Python scripts form performing stereo depth estimation using the HITNET model in ONNX.

Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

Google Cloud Platform Machine Learning Samples

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Model and Android app for sketch recognition using Google's quickdraw dataset

To 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.

No description or website provided.