201 Open source projects that are alternatives of or similar to ATMC

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

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

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

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

Infrastructures™ for Machine Learning Training/Inference in Production.

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

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

(CVPR 2021, Oral) Dynamic Slimmable Network

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

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

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.

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.

[ICLR'21] PyTorch code for our paper "Neural Pruning via Growing Regularization"

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

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration (CVPR 2019 Oral)

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

Pruning and quantization for SSD. Model compression.

PyTorch Model Compression

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

An Open Source Deep Learning Inference Engine Based on FPGA

[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

Easy-to-use UI for automatically sparsifying neural networks and creating sparsification recipes for better inference performance and a smaller footprint

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

A pytorch pruning toolkit for structured neural network pruning and layer dependency maintaining.

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

Embedded and mobile deep learning research resources

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

A curated list of neural network pruning resources.

reference pytorch code for named entity tagging

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

Paper list for neural network compression techniques

[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)

(ICML 2022) Official PyTorch implementation of “Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness”.

Benchmarks for Corruption Invariant Person Re-identification. [NeurIPS 2021 Track on Datasets and Benchmarks]

Sensor data aggregation tool for any numerical sensor data. Robust and privacy-friendly.

Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)

Implementation of the paper "Certifiable Robustness and Robust Training for Graph Convolutional Networks".

A PyTorch implementation of the iterative pruning method described in Han et. al. (2015)

pytorch implementation of Structured Bayesian Pruning

FasterAI: A repository for making smaller and faster models with the FastAI library.

Automatic DNN compression tool with various model compression and neural architecture search techniques

Recentrifuge: robust comparative analysis and contamination removal for metagenomics

QAT(quantize aware training) for classification with MQBench

TF2 Deep FloorPlan Recognition using a Multi-task Network with Room-boundary-Guided Attention. Enable tensorboard, quantization, flask, tflite, docker, github actions and google colab.

PyTorch Project Specification.

Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On implicit filter level sparsity in Convolutional Neural Networks".

Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"

Caffe for Sparse Convolutional Neural Network

Training Low-bits DNNs with Stochastic Quantization

Reachability analysis for closed-loop control systems

State-of-the-art method for large-scale ANN search as of Oct 2016. Presented at ECCV 16.

A research library for pytorch-based neural network pruning, compression, and more.

Observations and notes to understand the workings of neural network models and other thought experiments using Tensorflow

[ICLR 2021] "GANs Can Play Lottery Too" by Xuxi Chen, Zhenyu Zhang, Yongduo Sui, Tianlong Chen

mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

A package to make do Network Slimming a little easier

阿里云MNS