mit-han-lab/tinyml

Stars
755
Rank 60,130 (Top 2 %)
Language
Python
License
MIT License
Created almost 4 years ago
Updated 11 months ago

mit-han-lab/tinyml

mit-han-lab

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Tiny Machine Learning [website]

[News] We refactored MCUNet into a standalone repo: https://github.com/mit-han-lab/mcunet. Please follow the new repo for updates on TinyEngine release!

[News] We actively collaborate with industrial partners for real-world TinyML applications. Our technolgy has successfully influenced many products and deployed on over 100K IoT devices. Feel free to contact Prof. Song Han for more info.

[News] Our projects are covered by: MIT News, WIRED, Morning Brew, Stacey on IoT, Analytics Insight, Techable.

TinyML Projects

Projects	Keywords
MCUNet	Memory-efficient inference, System-algorithm co-design
TinyTL	On-device learning, Memory-efficient transfer learning
NetAug	Training technique for tiny neural networks

About TinyML

Intelligent edge devices with rich sensors (e.g., billions of mobile phones and IoT devices) have been ubiquitous in our daily lives. Combining artificial intelligence (AI) and these edge devices, there are vast real-world applications such as smart home, smart retail, autonomous driving, and so on. However, the state-of-the-art deep learning AI systems typically require tremendous resources (e.g., large labeled dataset, many computational resources, many AI experts), both for training and inference. This hinders the application of these powerful deep learning AI systems on edge devices. The TinyML project aims to improve the efficiency of deep learning AI systems by requiring less computation, fewer engineers, and less data, to facilitate the giant market of edge AI and AIoT.

Demo

Related Projects

MCUNet: Tiny Deep Learning on IoT Devices (NeurIPS'20, spotlight)

TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning (NeurIPS'20)

Once for All: Train One Network and Specialize it for Efficient Deployment (ICLR'20)

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (ICLR'19)

AutoML for Architecting Efficient and Specialized Neural Networks (IEEE Micro)

AMC: AutoML for Model Compression and Acceleration on Mobile Devices (ECCV'18)

HAQ: Hardware-Aware Automated Quantization (CVPR'19, oral)

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

bevfusion

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

temporal-shift-module

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

once-for-all

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

llm-awq

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

proxylessnas

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

torchquantum

A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum computers.

Jupyter Notebook

data-efficient-gans

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.

torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

gan-compression

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

anycost-gan

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

fastcomposer

[IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

pvcnn

[NeurIPS 2019, Spotlight] Point-Voxel CNN for Efficient 3D Deep Learning

lite-transformer

[ICLR 2020] Lite Transformer with Long-Short Range Attention

spvnas

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

distrifuser

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

tiny-training

On-Device Training Under 256KB Memory [NeurIPS'22]

amc

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

dlg

[NeurIPS 2019] Deep Leakage From Gradients

haq

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

offsite-tuning

Offsite-Tuning: Transfer Learning without Full Model

hardware-aware-transformers

[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

litepose

[CVPR'22] Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

inter-operator-scheduler

[MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration

amc-models

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

apq

[CVPR 2020] APQ: Joint Search for Network Architecture, Pruning and Quantization Policy

parallel-computing-tutorial

flatformer

[CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

patch_conv

Patch convolution to avoid large GPU memory usage of Conv2D

6s965-fall2022

Jupyter Notebook

sparsevit

[CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

bnn-icestick

Binary Neural Network on IceStick FPGA.

Jupyter Notebook

e3d

Efficient 3D Deep Learning

neurips-micronet

[JMLR'20] NeurIPS 2019 MicroNet Challenge Efficient Language Modeling, Champion

Jupyter Notebook

spatten-llm

[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

tinychat-tutorial

pruning-sparsity-publications

iccad-tinyml-open

[ICCAD'22 TinyML Contest] Efficient Heart Stroke Detection on Low-cost Microcontrollers

calo-cluster

Jupyter Notebook

ml-blood-pressure

gan-compression-dynamic

data-efficient-gans-dynamic