111 Open source projects that are alternatives of or similar to Soft Filter Pruning

Infrastructures™ for Machine Learning Training/Inference in Production.

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

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

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.

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

[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

(CVPR 2021, Oral) Dynamic Slimmable Network

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

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

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

A curated list of neural network pruning resources.

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

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

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

Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers https://arxiv.org/abs/1802.00124

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

Learning both Weights and Connections for Efficient Neural Networks https://arxiv.org/abs/1506.02626

Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据

Your local Flux surgeon

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

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

🛠️ Tools for Transformers compression using PyTorch Lightning ⚡

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).

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

🤖 A machine learning framework for audio, text, image, video, or .CSV files (50+ featurizers and 15+ model trainers).

Learnable Embedding Space for Efficient Neural Architecture Compression

Java interface for fastText

Implement of Dynamic Model Pruning with Feedback with pytorch

OpenMMLab Model Compression Toolbox and Benchmark.

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

Efficient-Computing

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

This repository contains code to replicate the experiments given in NeurIPS 2019 paper "One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers"

Prunable nn layers for pytorch.

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

Remove/Backup – settings & cli for macOS (OS X) – DataGrip, AppCode, CLion, Gogland, IntelliJ, PhpStorm, PyCharm, Rider, RubyMine, WebStorm

Pruning and quantization for SSD. Model compression.

PyTorch implementation of "Pruning Filters For Efficient ConvNets"

Deep Face Model Compression

A PyTorch-based model pruning toolkit for pre-trained language models

pytorch realtime multi person keypoint estimation

Model Compression CLI Tool for Keras.

PyTorch Implementation of Weights Pruning

🔌⚡ Nuxt module to prune html before sending it to the browser (it removes elements matching CSS selector(s)), useful for boosting performance showing a different HTML for bots/audits by removing all the scripts with dynamic rendering

Code for "Co-Evolutionary Compression for Unpaired Image Translation" (ICCV 2019) and "SCOP: Scientific Control for Reliable Neural Network Pruning" (NeurIPS 2020).

pytorch implementation of Structured Bayesian Pruning

It is a blueprint to data science from the mathematics to algorithms. It is not completed.

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Attempting feature map prunning on a CNN trained for Japanese OCR

Group Fisher Pruning for Practical Network Compression(ICML2021)

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

yolov3 by pytorch

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

PyTorch code for our CVPR'20 paper "Collaborative Distillation for Ultra-Resolution Universal Style Transfer"

Programmable Neural Network Compression

Unofficial Pytorch implementation of Deep Compression in CIFAR10

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.

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