139 Open source projects that are alternatives of or similar to Auto-Compression

Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling

A lightweight and easy-to-use deep learning framework with neural architecture search.

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

aw_nas: A Modularized and Extensible NAS Framework

Java interface for fastText

DeepArchitect: Automatically Designing and Training Deep Architectures

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

SGAS: Sequential Greedy Architecture Search (CVPR'2020) https://www.deepgcns.org/auto/sgas

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

A curated list of automated deep learning (including neural architecture search and hyper-parameter optimization) resources.

Implement Differentiable Architecture Search (DARTS) for RNN with fastai

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

Model Compression Based on Geoffery Hinton's Logit Regression Method in Keras applied to MNIST 16x compression over 0.95 percent accuracy.An Implementation of "Distilling the Knowledge in a Neural Network - Geoffery Hinton et. al"

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

AutoML frAmework for Neural Networks

Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.

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

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

This directory contains code necessary to run the GraphNAS algorithm.

[CVPR2020] GhostNet: More Features from Cheap Operations

[CVPR 2020] When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks

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

Automated deep learning algorithms implemented in PyTorch.

Data Efficient Model Compression

[CVPR 2020] MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning

papers about model compression

[ECCV2020] NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

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

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

(CVPR 2021, Oral) Dynamic Slimmable Network

Fast & Simple Resource-Constrained Learning of Deep Network Structure

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

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

Federated Learning Library: https://fedml.ai

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

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

Model Compression CLI Tool for Keras.

Basic implementation of [Neural Architecture Search with Reinforcement Learning](https://arxiv.org/abs/1611.01578).

Efficient-Computing

Differentiable architecture search for convolutional and recurrent networks

PyTorch implementation of PNASNet-5 on ImageNet

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

A curated list of automated machine learning papers, articles, tutorials, slides and projects

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

Reproducible Rapid Research for Neural Architecture Search (NAS)

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

NEATEST: Evolving Neural Networks Through Augmenting Topologies with Evolution Strategy Training

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

Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding. NeurIPS 2020.

pytorch realtime multi person keypoint estimation

Encodings for neural architecture search

PyTorch Implementation of Weights Pruning

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

A curated list of awesome resources combining Transformers with Neural Architecture Search

[InterSpeech 2020] "AutoSpeech: Neural Architecture Search for Speaker Recognition" by Shaojin Ding*, Tianlong Chen*, Xinyu Gong, Weiwei Zha, Zhangyang Wang

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

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

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"