SlideShare une entreprise Scribd logo
1  sur  28
Télécharger pour lire hors ligne
Deep learning
on	microcontrollers
Jan	Jongboom	
IETF	101,	London	
22	March	2018
https://twitter.com/billyd/status/701804370560729089
©	2018	Arm	Limited	3
Machine	learning
©	2018	Arm	Limited	4
Why	machine	learning	on	the	edge?
Sensor fusion
http://www.gierad.com/projects/supersensor/
©	2018	Arm	Limited	5
Why	machine	learning	on	the	edge?
Federated learning
https://research.googleblog.com/2017/04/federated-learning-collaborative.html
©	2018	Arm	Limited	6
Why	machine	learning	on	the	edge?
LPWANs
http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/
©	2018	Arm	Limited	7
Why	machine	learning	on	the	edge?
Offline self-contained systems
https://os.mbed.com/blog/entry/streaming-data-cows-dsa2017/
©	2018	Arm	Limited	8
Edge	vs.	Cloud	
Environmental	data	model	American	Society	of	Heating,	Refrigerating	and	Air-Conditioning	Engineers	(ASHRAE)	RP-884	Adaptive	Model	Project
©	2018	Arm	Limited	9
Microcontrollers
Small (1cm²)
Cheap (~1$)
Efficient (standby: 0.3 μA)
Slow (max. 100 MHz)
Limited memory (max. 256K RAM)
Downsides
2.7cm
©	2018	Arm	Limited	10
uTensor
Machine	learning	for	microcontrollers	
Runs	in	<256K	RAM	
TensorFlow	compatible	
Built	on	top	of	Mbed	OS	5

								(file	systems,	drivers,	150	boards	compatible)	
Open	source,	Apache	2.0	license
©	2018	Arm	Limited	11
uTensor	Team
Neil	Tan	
Arm
Michael	Bartling	
Arm
Dboy	Liao	
Piniko
Kazami	Hsieh	
Academia Sinica
©	2018	Arm	Limited	12
©	2018	Arm	Limited	13
How?
MNIST	data	set	
Training	set:	60,000	images	
Every	drawing	is	downsampled	to	28x28	pixels	
Supervised	learning	through	backpropagation	
https://github.com/uTensor/tf-node-viewer/blob/master/deep_mlp.py
©	2018	Arm	Limited	14
Multi-layer	perceptron	(MLP)	classification
28x28 = 784
Neuron
Output
9
Matrix	multiplication	(weight),	bias,	then	activation	function
Potential	outputs
©	2018	Arm	Limited	15
How?
©	2018	Arm	Limited	16
Quantization
8-bit	integers	instead	of	32-bit	floats	
Only	during	classification	
79.9%	accuracy	vs.	80.3%	accuracy	(CIFAR-10)	
TensorFlow	requires	floating-point	de-quantization	between	layers	(nodes?)	
https://petewarden.com/2016/05/03/how-to-quantize-neural-networks-with-tensorflow/
©	2018	Arm	Limited	17
Memory	usage
Matrix	multiplication	in	first	hidden	layer	dominates	RAM	usage:
		Input	elements:																															784	
		Number	of	neurons	(1st	layer):																128	
		Number	of	weight	(input	to	1st	layer):								128	*	784	
		Resulting	values	(Pre-activation	function):			128	
		Data	type:																																				8-bit	integer	(1	byte)	
1	byte	*	(784	+	(128	*	784)	+	128)	=	98.891	kB
©	2018	Arm	Limited	18
Other	tricks
Paging	of	memory	for	larger	models	(sacrifices	speed)	
Graph	in	ROM	(requires	pre-processing	
Take	advantage	in	sparsity	of	data,	sacrifice	accuracy	(TBD)
©	2018	Arm	Limited	19
Operators
Add,	Subtract	
Min,	Max,	ArgMax	
ReLU,	Matrix	multiplication,	Reshape,	Quantization	
Convolution	(WIP)	
Pooling	(WIP)	
Networked	(TBD)
©	2018	Arm	Limited	20
Tensors
RAM	tensor	
Flash	tensor	
Sparse	tensor	
Networked	tensor	
Tensors	can	be	paged	to	fit	larger	networks
©	2018	Arm	Limited	21
Workflow
Matrix	multiplication	data	
from	trained	model
Tensor	graph
©	2018	Arm	Limited	22
TensorBoard	vs	uTensor
Developing	using	the	simulator
©	2018	Arm	Limited	24
CMSIS-NN
New	neural	network	kernel	functions	
Leverages	the	DSP/SIMD	functions	in	silicon	
See	speedup	of	4-5x	
Hardware	acceleration	for	convolution,	pooling,	etc.	
uTensor	will	be	built	on	top	of	CMSIS-NN
©	2018	Arm	Limited	26
Speed
Measured	on	Cortex-M7	216	MHz,	133	KB	memory	used	
3	convolution	layers,	1	fully	connected	layer,	32x32	color	images
©	2018	Arm	Limited	27
Recap
1. Buy	a	development	board	(http://os.mbed.com/platforms)	
2. Clone	uTensor	(https://github.com/uTensor/uTensor)	
3. ???	
4. PROFIT!!!
©	2018	Arm	Limited	28
https://labs.mbed.com
Jan Jongboom, Arm
Thank you!

Contenu connexe

Tendances

"This Changes Everything — Why Computer Vision Will Be Everywhere," a Present...
"This Changes Everything — Why Computer Vision Will Be Everywhere," a Present..."This Changes Everything — Why Computer Vision Will Be Everywhere," a Present...
"This Changes Everything — Why Computer Vision Will Be Everywhere," a Present...
Edge AI and Vision Alliance
 
Strata Hadoop Talk 2016 August
Strata Hadoop Talk 2016 AugustStrata Hadoop Talk 2016 August
Strata Hadoop Talk 2016 August
Claire Fang
 

Tendances (8)

"This Changes Everything — Why Computer Vision Will Be Everywhere," a Present...
"This Changes Everything — Why Computer Vision Will Be Everywhere," a Present..."This Changes Everything — Why Computer Vision Will Be Everywhere," a Present...
"This Changes Everything — Why Computer Vision Will Be Everywhere," a Present...
 
Fundamentals of IoT - Data Science Africa 2019
Fundamentals of IoT - Data Science Africa 2019Fundamentals of IoT - Data Science Africa 2019
Fundamentals of IoT - Data Science Africa 2019
 
Strata Hadoop Talk 2016 August
Strata Hadoop Talk 2016 AugustStrata Hadoop Talk 2016 August
Strata Hadoop Talk 2016 August
 
HiPEAC 2019 Workshop - Vision Processing
HiPEAC 2019 Workshop - Vision ProcessingHiPEAC 2019 Workshop - Vision Processing
HiPEAC 2019 Workshop - Vision Processing
 
Sharon’ Besser, Net Optics VP of Technology, Net Optics, discusses Lawful Int...
Sharon’ Besser, Net Optics VP of Technology, Net Optics, discusses Lawful Int...Sharon’ Besser, Net Optics VP of Technology, Net Optics, discusses Lawful Int...
Sharon’ Besser, Net Optics VP of Technology, Net Optics, discusses Lawful Int...
 
Innovation Summit 2015 - 7 - IoT Future
Innovation Summit 2015 - 7 - IoT FutureInnovation Summit 2015 - 7 - IoT Future
Innovation Summit 2015 - 7 - IoT Future
 
Mobile IoT Network :Current Status and Future Evolution
Mobile IoT  Network :Current Status and Future EvolutionMobile IoT  Network :Current Status and Future Evolution
Mobile IoT Network :Current Status and Future Evolution
 
Edge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to YouEdge Computing: Bringing the Internet Closer to You
Edge Computing: Bringing the Internet Closer to You
 

Similaire à Deep learning on microcontrollers - IETF 101 - T2TRG

Similaire à Deep learning on microcontrollers - IETF 101 - T2TRG (20)

HKG18-315 - Why the ecosystem is a wonderful thing, warts and all
HKG18-315 - Why the ecosystem is a wonderful thing, warts and allHKG18-315 - Why the ecosystem is a wonderful thing, warts and all
HKG18-315 - Why the ecosystem is a wonderful thing, warts and all
 
Saama Presents Is your Big Data Solution Ready for Streaming
Saama Presents Is your Big Data Solution Ready for StreamingSaama Presents Is your Big Data Solution Ready for Streaming
Saama Presents Is your Big Data Solution Ready for Streaming
 
Open Source for Industry 4.0 – Open IoT Summit NA 2018
Open Source for Industry 4.0 – Open IoT Summit NA 2018Open Source for Industry 4.0 – Open IoT Summit NA 2018
Open Source for Industry 4.0 – Open IoT Summit NA 2018
 
How oneM2M fits into the IoT Landscape - enabling cross vertical domain inter...
How oneM2M fits into the IoT Landscape - enabling cross vertical domain inter...How oneM2M fits into the IoT Landscape - enabling cross vertical domain inter...
How oneM2M fits into the IoT Landscape - enabling cross vertical domain inter...
 
Session 1.3 context information management across smart city knowledge domains
Session 1.3   context information management across smart city knowledge domainsSession 1.3   context information management across smart city knowledge domains
Session 1.3 context information management across smart city knowledge domains
 
Mohamad C
Mohamad CMohamad C
Mohamad C
 
Reinforcement Learning in the Wild and Lessons Learned
Reinforcement Learning in the Wild and Lessons LearnedReinforcement Learning in the Wild and Lessons Learned
Reinforcement Learning in the Wild and Lessons Learned
 
CLOUD-NATIVE NETWORKS FOR THE ADVANCEMENT OF AI/IoT
CLOUD-NATIVE NETWORKS FOR THE ADVANCEMENT OF AI/IoTCLOUD-NATIVE NETWORKS FOR THE ADVANCEMENT OF AI/IoT
CLOUD-NATIVE NETWORKS FOR THE ADVANCEMENT OF AI/IoT
 
Motadata - Unified Product Suite for IT Operations and Big Data Analytics
Motadata - Unified Product Suite for IT Operations and Big Data AnalyticsMotadata - Unified Product Suite for IT Operations and Big Data Analytics
Motadata - Unified Product Suite for IT Operations and Big Data Analytics
 
IRJET- Smart Parking System using IoT
IRJET- Smart Parking System using IoTIRJET- Smart Parking System using IoT
IRJET- Smart Parking System using IoT
 
Understanding IoT Security: How to Quantify Security Risk of IoT Technologies
Understanding IoT Security: How to Quantify Security Risk of IoT TechnologiesUnderstanding IoT Security: How to Quantify Security Risk of IoT Technologies
Understanding IoT Security: How to Quantify Security Risk of IoT Technologies
 
Real User Measurement Insights, NYWebPerf 2018-Aug-09
Real User Measurement Insights, NYWebPerf 2018-Aug-09Real User Measurement Insights, NYWebPerf 2018-Aug-09
Real User Measurement Insights, NYWebPerf 2018-Aug-09
 
IRJET- High Responsive Smart Parking System using IoT
IRJET- High Responsive Smart Parking System using IoTIRJET- High Responsive Smart Parking System using IoT
IRJET- High Responsive Smart Parking System using IoT
 
Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...
Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...
Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...
 
Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...
Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...
Infrastructure predictive monitoring with itoa jean louis baudoin, capgemini-...
 
IoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT Strategy
IoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT StrategyIoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT Strategy
IoT Predictions for 2019 and Beyond: Data at the Heart of Your IoT Strategy
 
Designing Internet Of Things
Designing Internet Of ThingsDesigning Internet Of Things
Designing Internet Of Things
 
Key enabling technologies: 2018-2020
Key enabling technologies: 2018-2020Key enabling technologies: 2018-2020
Key enabling technologies: 2018-2020
 
Testing the Next Generation of Technologies: IoT, Mobile, and Cloud … Oh My!
Testing the Next Generation of Technologies: IoT, Mobile, and Cloud … Oh My!Testing the Next Generation of Technologies: IoT, Mobile, and Cloud … Oh My!
Testing the Next Generation of Technologies: IoT, Mobile, and Cloud … Oh My!
 
Multi Smart Parking System
Multi Smart Parking SystemMulti Smart Parking System
Multi Smart Parking System
 

Plus de Jan Jongboom

Intelligent Edge - Getting started with TinyML for industrial applications
Intelligent Edge - Getting started with TinyML for industrial applicationsIntelligent Edge - Getting started with TinyML for industrial applications
Intelligent Edge - Getting started with TinyML for industrial applications
Jan Jongboom
 
Develop with Mbed OS - The Things Conference 2019
Develop with Mbed OS - The Things Conference 2019Develop with Mbed OS - The Things Conference 2019
Develop with Mbed OS - The Things Conference 2019
Jan Jongboom
 

Plus de Jan Jongboom (20)

TinyML on Arduino - workshop
TinyML on Arduino - workshopTinyML on Arduino - workshop
TinyML on Arduino - workshop
 
Intelligent Edge - Getting started with TinyML for industrial applications
Intelligent Edge - Getting started with TinyML for industrial applicationsIntelligent Edge - Getting started with TinyML for industrial applications
Intelligent Edge - Getting started with TinyML for industrial applications
 
Teaching your sensors new tricks with Machine Learning - Eta Compute webinar
Teaching your sensors new tricks with Machine Learning - Eta Compute webinarTeaching your sensors new tricks with Machine Learning - Eta Compute webinar
Teaching your sensors new tricks with Machine Learning - Eta Compute webinar
 
Get started with TinyML - Embedded online conference
Get started with TinyML - Embedded online conferenceGet started with TinyML - Embedded online conference
Get started with TinyML - Embedded online conference
 
Adding intelligence to your LoRaWAN deployment - The Things Virtual Conference
Adding intelligence to your LoRaWAN deployment - The Things Virtual ConferenceAdding intelligence to your LoRaWAN deployment - The Things Virtual Conference
Adding intelligence to your LoRaWAN deployment - The Things Virtual Conference
 
Get started with TinyML - Hackster webinar 9 April 2020
Get started with TinyML - Hackster webinar 9 April 2020Get started with TinyML - Hackster webinar 9 April 2020
Get started with TinyML - Hackster webinar 9 April 2020
 
Tiny intelligent computers and sensors - Open Hardware Event 2020
Tiny intelligent computers and sensors - Open Hardware Event 2020Tiny intelligent computers and sensors - Open Hardware Event 2020
Tiny intelligent computers and sensors - Open Hardware Event 2020
 
Teaching your sensors new tricks with Machine Learning - CENSIS Tech Summit 2019
Teaching your sensors new tricks with Machine Learning - CENSIS Tech Summit 2019Teaching your sensors new tricks with Machine Learning - CENSIS Tech Summit 2019
Teaching your sensors new tricks with Machine Learning - CENSIS Tech Summit 2019
 
Adding intelligence to your LoRaWAN devices - The Things Conference on tour
Adding intelligence to your LoRaWAN devices - The Things Conference on tourAdding intelligence to your LoRaWAN devices - The Things Conference on tour
Adding intelligence to your LoRaWAN devices - The Things Conference on tour
 
Machine learning on 1 square centimeter - Emerce Next 2019
Machine learning on 1 square centimeter - Emerce Next 2019Machine learning on 1 square centimeter - Emerce Next 2019
Machine learning on 1 square centimeter - Emerce Next 2019
 
17,000 contributions in 32K RAM - FOSS North 2019
17,000 contributions in 32K RAM - FOSS North 201917,000 contributions in 32K RAM - FOSS North 2019
17,000 contributions in 32K RAM - FOSS North 2019
 
Open Hours: Mbed Simulator
Open Hours: Mbed SimulatorOpen Hours: Mbed Simulator
Open Hours: Mbed Simulator
 
Efficient IoT solutions based on LoRaWAN, The Things Network and Mbed OS
Efficient IoT solutions based on LoRaWAN, The Things Network and Mbed OSEfficient IoT solutions based on LoRaWAN, The Things Network and Mbed OS
Efficient IoT solutions based on LoRaWAN, The Things Network and Mbed OS
 
Machine learning on 1 cm2 - Tweakers Dev Summit
Machine learning on 1 cm2 - Tweakers Dev SummitMachine learning on 1 cm2 - Tweakers Dev Summit
Machine learning on 1 cm2 - Tweakers Dev Summit
 
Simulating LoRaWAN devices - LoRa Alliance AMM 2019
Simulating LoRaWAN devices - LoRa Alliance AMM 2019Simulating LoRaWAN devices - LoRa Alliance AMM 2019
Simulating LoRaWAN devices - LoRa Alliance AMM 2019
 
Develop with Mbed OS - The Things Conference 2019
Develop with Mbed OS - The Things Conference 2019Develop with Mbed OS - The Things Conference 2019
Develop with Mbed OS - The Things Conference 2019
 
Firmware Updates over LoRaWAN - The Things Conference 2019
Firmware Updates over LoRaWAN - The Things Conference 2019Firmware Updates over LoRaWAN - The Things Conference 2019
Firmware Updates over LoRaWAN - The Things Conference 2019
 
Faster Device Development - GSMA @ CES 2019
Faster Device Development - GSMA @ CES 2019Faster Device Development - GSMA @ CES 2019
Faster Device Development - GSMA @ CES 2019
 
Mbed LoRaWAN stack: a case study - LoRa Alliance AMM Tokyo
Mbed LoRaWAN stack: a case study - LoRa Alliance AMM TokyoMbed LoRaWAN stack: a case study - LoRa Alliance AMM Tokyo
Mbed LoRaWAN stack: a case study - LoRa Alliance AMM Tokyo
 
Simulating microcontrollers - Arm Research Summit 2018
Simulating microcontrollers - Arm Research Summit 2018Simulating microcontrollers - Arm Research Summit 2018
Simulating microcontrollers - Arm Research Summit 2018
 

Dernier

₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
Diya Sharma
 
Hot Service (+9316020077 ) Goa Call Girls Real Photos and Genuine Service
Hot Service (+9316020077 ) Goa  Call Girls Real Photos and Genuine ServiceHot Service (+9316020077 ) Goa  Call Girls Real Photos and Genuine Service
Hot Service (+9316020077 ) Goa Call Girls Real Photos and Genuine Service
sexy call girls service in goa
 
Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...
Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...
Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...
Call Girls In Delhi Whatsup 9873940964 Enjoy Unlimited Pleasure
 
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Sheetaleventcompany
 
Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝
soniya singh
 
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRLLucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
imonikaupta
 

Dernier (20)

₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
₹5.5k {Cash Payment}New Friends Colony Call Girls In [Delhi NIHARIKA] 🔝|97111...
 
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
 
Russian Call Girls in %(+971524965298 )# Call Girls in Dubai
Russian Call Girls in %(+971524965298  )#  Call Girls in DubaiRussian Call Girls in %(+971524965298  )#  Call Girls in Dubai
Russian Call Girls in %(+971524965298 )# Call Girls in Dubai
 
Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.
Call Now ☎ 8264348440 !! Call Girls in Shahpur Jat Escort Service Delhi N.C.R.
 
Hot Service (+9316020077 ) Goa Call Girls Real Photos and Genuine Service
Hot Service (+9316020077 ) Goa  Call Girls Real Photos and Genuine ServiceHot Service (+9316020077 ) Goa  Call Girls Real Photos and Genuine Service
Hot Service (+9316020077 ) Goa Call Girls Real Photos and Genuine Service
 
Russian Call girl in Ajman +971563133746 Ajman Call girl Service
Russian Call girl in Ajman +971563133746 Ajman Call girl ServiceRussian Call girl in Ajman +971563133746 Ajman Call girl Service
Russian Call girl in Ajman +971563133746 Ajman Call girl Service
 
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call GirlVIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
 
Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...
Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...
Dwarka Sector 26 Call Girls | Delhi | 9999965857 🫦 Vanshika Verma More Our Se...
 
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
Call Girls Service Chandigarh Lucky ❤️ 7710465962 Independent Call Girls In C...
 
On Starlink, presented by Geoff Huston at NZNOG 2024
On Starlink, presented by Geoff Huston at NZNOG 2024On Starlink, presented by Geoff Huston at NZNOG 2024
On Starlink, presented by Geoff Huston at NZNOG 2024
 
Call Girls Dubai Prolapsed O525547819 Call Girls In Dubai Princes$
Call Girls Dubai Prolapsed O525547819 Call Girls In Dubai Princes$Call Girls Dubai Prolapsed O525547819 Call Girls In Dubai Princes$
Call Girls Dubai Prolapsed O525547819 Call Girls In Dubai Princes$
 
Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls In Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
Top Rated Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...
Top Rated  Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...Top Rated  Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...
Top Rated Pune Call Girls Daund ⟟ 6297143586 ⟟ Call Me For Genuine Sex Servi...
 
(+971568250507 ))# Young Call Girls in Ajman By Pakistani Call Girls in ...
(+971568250507  ))#  Young Call Girls  in Ajman  By Pakistani Call Girls  in ...(+971568250507  ))#  Young Call Girls  in Ajman  By Pakistani Call Girls  in ...
(+971568250507 ))# Young Call Girls in Ajman By Pakistani Call Girls in ...
 
Networking in the Penumbra presented by Geoff Huston at NZNOG
Networking in the Penumbra presented by Geoff Huston at NZNOGNetworking in the Penumbra presented by Geoff Huston at NZNOG
Networking in the Penumbra presented by Geoff Huston at NZNOG
 
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRLLucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
Lucknow ❤CALL GIRL 88759*99948 ❤CALL GIRLS IN Lucknow ESCORT SERVICE❤CALL GIRL
 
VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
VVVIP Call Girls In Connaught Place ➡️ Delhi ➡️ 9999965857 🚀 No Advance 24HRS...
 
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
All Time Service Available Call Girls Mg Road 👌 ⏭️ 6378878445
 
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
(INDIRA) Call Girl Pune Call Now 8250077686 Pune Escorts 24x7
 
DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024
DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024
DDoS In Oceania and the Pacific, presented by Dave Phelan at NZNOG 2024
 

Deep learning on microcontrollers - IETF 101 - T2TRG