TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems

05/04/2021

TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems

Robert David, Jared Duke, Advait Jain, Vijay Janapa Reddi, Nat Jeffries, Jian Li, Nick Kreeger, Ian Nappier, Meghna Natraj, Tiezhen Wang, Pete Warden, Rocky Rhodes, Rocky Rhodes

Keywords:

Abstract Paper Similar Papers

Abstract: We introduce TensorFlow (TF) Micro, an open-source machine learning inference framework for running deep-learning models on embedded systems. TF Micro tackles the efficiency requirements imposed by embedded system resource constraints and the fragmentation challenges that make cross-platform interoperability nearly impossible. The framework adopts a unique interpreter-based approach that provides flexibility while overcoming the challenges. This paper explains the design decisions behind TF Micro and describes its implementation. We present an evaluation to demonstrate its low resource requirement and minimal run-time performance overhead.

The video of this talk cannot be embedded. You can watch it here:

https://slideslive.com/38952756

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at MLSYS 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

22/11/2021

TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation

Fengyi Shen, Akhil Gurram, Ahmet Faruk Tuna and
Onay Urfalioglu, Alois C. Knoll

Keywords Paper

domain adaptation, semantic segmentation, autonomous driving, image-to-image translation, unsupervised learning, domain transfer, scene understanding, urban scene segmentation

0

0

0

0

3:08

06/12/2021

Continual Learning via Local Module Composition

Oleksiy Ostapenko, Pau Rodriguez, Massimo Caccia, Laurent Charlin

Keywords Paper

continual learning, transfer learning

1

0

0

1

14:32

06/12/2021

Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection

HanQin Cai, Jialin Liu, Wotao Yin

Keywords Paper

deep learning, machine learning

0

0

0

0

8:07

02/02/2021

Deeplite NeutrinoTM: A BlackBox Framework for Constrained Deep Learning Model Optimization

Anush Sankaran, Olivier Mastropietro, Ehsan Saboori and
Yasser Idris, Davis Sawyer, MohammadHossein AskariHemmat, Ghouthi Boukli Hacene

Keywords Paper

0

0

0

0

18:29

22/09/2020

AutoRec: An automated recommender system

Ting-Hsiang Wang, Xia Hu, Haifeng Jin and
Qingquan Song, Xiaotian Han, Zirui Liu

Keywords Paper

Recommender Systems, Hyperparameter Tuning, Neural Architecture Search, Automated Machine Learning, Model Search

0

0

0

0

3:18

03/05/2021

Dynamic Tensor Rematerialization

Marisa Kirisame, Steven S. Lyubomirsky, Altan Haan and
Jennifer Brennan, Mike He, Jared G Roesch, Tianqi Chen, Zachary Tatlock

Keywords Paper

Runtime Systems, Memory-saving, Rematerialization, Checkpointing

0

0

1

0

10:04

26/04/2020

Gradients as Features for Deep Representation Learning

Fangzhou Mu, Yingyu Liang, Yin Li

Keywords Paper

representation learning, gradient features, deep learning

0

0

0

0

5:07

26/04/2020

Continual Learning with Adaptive Weights (CLAW)

Tameem Adel, Han Zhao, Richard E. Turner

Keywords Paper

Continual learning

0

0

0

0

4:58

07/09/2020

BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation

Xianghui Yang, Bairun Wang, Xinchi Zhou and
Kaige Chen, Shuai Yi, Wanli Ouyang, Luping Zhou

Keywords Paper

Few-shot Semantic Segmentation, Few-shot learning, Semantic Segmentation

0

0

0

0

8:26

02/02/2021

OpEvo: An Evolutionary Method for Tensor Operator Optimization

Xiaotian Gao, Wei Cui, Lintao Zhang, Mao Yang

Keywords Paper

0

0

0

0

16:02

05/04/2021

FLAML: A Fast and Lightweight AutoML Library

Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu

Keywords Paper

0

0

0

0

5:08

05/04/2021

FLAML: A Fast and Lightweight AutoML Library

Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu

Keywords Paper

0

0

0

0

18:23

06/12/2021

Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs

Zihang Meng, Lopamudra Mukherjee, Yichao Wu and
Vikas Singh, Sathya Narayanan Ravi

Keywords Paper

deep learning, optimization

0

0

0

0

13:21

22/11/2021

Mode-Guided Feature Augmentation for Domain Generalization

Muhammad Haris Khan, Syed Muhammad talha Zaidi, Salman Khan, Fahad Shahbaz Khan

Keywords Paper

out-of-domain robustness, domain generalization, domain adaptation, convolutional neural networks, data augmentation, feature augmentation, subspace similarity, covariate shift, in-domain generalization, robust objective function

0

0

0

0

2:56

06/12/2020

Learning Composable Energy Surrogates for PDE Order Reduction

Alex Beatson, Jordan Ash, Geoffrey Roeder and
Tianju Xue, Ryan Adams

Keywords Paper

0

0

0

0

3:18

14/06/2020

Meta-Learning of Neural Architectures for Few-Shot Learning

Thomas Elsken, Benedikt Staffler, Jan Hendrik Metzen, Frank Hutter

Keywords Paper

neural architecture search, meta-learning, automl, few-shot learning, autodl, deep learning

0

0

0

0

5:01

19/01/2020

Partial Type Constructors: Or, Making Ad Hoc Datatypes Less Ad Hoc

Mark Jones, J. Garrett Morris, Richard A. Eisenberg

Keywords Paper

Type constructors, Parametric polymorphism

0

0

0

0

21:37

26/08/2020

AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning

Rizal Fathony, Zico Kolter

Keywords Paper

0

0

0

0

14:49

19/10/2020

Flexible IR pipelines with capreolus

Andrew Yates, Kevin Martin Jose, Xinyu Zhang, Jimmy Lin

Keywords Paper

neural information retrieval, retrieval pipeline, ad hoc ranking

0

0

0

0

10:00

15/11/2020

Unifying Execution of Imperative Generators and Declarative Specifications

Pengyu Nie, Marinela Parovic, Zhiqiang Zang and
Sarfraz Khurshid, Aleksandar Milicevic, Milos Gligoric

Keywords Paper

Imperative generators, declarative specifications, Deuterium

0

0

0

0

14:47

14/06/2020

Adaptive Subspaces for Few-Shot Learning

Christian Simon, Piotr Koniusz, Richard Nock, Mehrtash Harandi

Keywords Paper

subspace, few, shot, meta, learning, classification

0

0

0

0

1:01

03/05/2021

MetaNorm: Learning to Normalize Few-Shot Batches Across Domains

Yingjun Du, Xiantong Zhen, Ling Shao, Cees G Snoek

Keywords Paper

batch normalization, Meta-learning, few-shot domain generalization

0

0

0

0

5:48

06/12/2020

Fast geometric learning with symbolic matrices

Jean Feydy, Joan Glaunès, Benjamin Charlier, Michael Bronstein

Keywords Paper

0

0

0

0

3:16

05/01/2021

Weakly Supervised Instance Segmentation by Deep Community Learning

Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han

Keywords Paper

0

0

0

0

4:14

05/04/2021

ModularNAS: Towards Modularized and Reusable Neural Architecture Search

Yunfeng Lin, Guilin Li, Xing Zhang and
Weinan Zhang, Bo Chen, Ruiming Tang, Zhenguo Li, Jiashi Feng, Yong Yu

Keywords Paper

0

0

0

0

16:07

05/04/2021

ModularNAS: Towards Modularized and Reusable Neural Architecture Search

Yunfeng Lin, Guilin Li, Xing Zhang and
Weinan Zhang, Bo Chen, Ruiming Tang, Zhenguo Li, Jiashi Feng, Yong Yu

Keywords Paper

0

0

0

0

5:07

30/11/2020

Learning Local Feature Descriptors for Multiple Object Tracking

Dmytro Borysenko, Dmytro Mykheievskyi, Viktor Porokhonskyy

Keywords Paper

0

0

0

0

9:42

12/07/2020

Operation-Aware Soft Channel Pruning using Differentiable Masks

Minsoo Kang, Bohyung Han

Keywords Paper

Applications - Computer Vision

0

0

0

0

14:56

16/11/2020

Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems

Sushmita Bhattacharya, Siva Kailas, Sahil Badyal and
Stephanie Gil, Dimitri Bertsekas

Keywords Paper

0

0

0

0

5:04

12/07/2020

Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems

Kaixuan Wei, Angelica I Aviles-Rivero, Jingwei Liang and
Ying Fu, Carola-Bibiane Schönlieb, Hua Huang

Keywords Paper

Deep Learning - Algorithms

0

0

0

0

11:48

06/12/2020

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

Xiaohan Chen, Zhangyang Wang, Siyu Tang, Krikamol Muandet

Keywords Paper

0

0

0

0

3:19

02/02/2021

Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning

Rushang Karia, Siddharth Srivastava

Keywords Paper

0

0

0

0

16:56

05/04/2021

Don't Forget to Sign the Gradients!

Omid Aramoon, Pin-Yu Chen, Gang Qu

Keywords Paper

0

0

0

0

20:37

13/04/2021

ATOL: Measure vectorization for automatic topologically-oriented learning

Martin Royer, Frederic Chazal, Clément Levrard and
Yuhei Umeda, Yuichi Ike

Keywords Paper

0

0

0

0

3:05

18/07/2021

Sparsifying Networks via Subdifferential Inclusion

Sagar Verma, Jean-Christophe Pesquet

Keywords Paper

Optimization, Convex Optimization

0

0

0

0

5:10

02/02/2021

Teaching the Old Dog New Tricks: Supervised Learning with Constraints

Fabrizio Detassis, Michele Lombardi, Michela Milano

Keywords Paper

0

0

0

0

16:58

06/12/2020

Multi-Task Reinforcement Learning with Soft Modularization

Ruihan Yang, Huazhe Xu, YI WU, Xiaolong Wang

Keywords Paper

0

0

0

0

3:18

03/05/2021

Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

Hao Li, Chenxin Tao, Xizhou Zhu and
Xiaogang Wang, Gao Huang, Jifeng Dai

Keywords Paper

Semantic Segmentation, Metric Surrogate, Loss Function Search

0

0

0

0

4:44

15/11/2020

Polymorphic Types and Effects with Boolean Unification

Magnus Madsen, Jaco van de Pol

Keywords Paper

Boolean unification, type inference, polymorphic types and effects

0

0

0

0

16:05