Tiny ML for spark Fun Edge
https://www.ittraining.com.tw/ittraining/it-elearning/el-ai/ai-tensorflow-lite-for-mcu
TensorFlow Lite for MCU正是專為邊緣裝置設計的TensorFlow模型預測框架,是TensorFlow的精簡版本,讓開發者可以在物聯網與嵌入式裝置中部署微型機器學習模型。 本課程將教授AI模型如何佈署於微控制器,包含模型訓練、模型最佳化以及TensorFlow Lite框架的程式開發等。此外,在實作上以Sparkfun edge board (ARM cortex M4)為例,說明如何以TensorFlow Lite 進行微控制器上面的人工智慧開發專案,包含人臉偵測、關鍵字的字詞偵測、姿態識別、異常偵測等。
Red Bend Software: Separation Using Type-1 Virtualization in Vehicles and Aut...Red Bend Software
Satish Varma from Red Bend Software presents at TI Tech Day Detroit 2013 on how to use Type-1 virtualization to consolidate hardware in automotive ECUs. Panelists included QNX Software Systems and Crank Software.
Tiny ML for spark Fun Edge
https://www.ittraining.com.tw/ittraining/it-elearning/el-ai/ai-tensorflow-lite-for-mcu
TensorFlow Lite for MCU正是專為邊緣裝置設計的TensorFlow模型預測框架,是TensorFlow的精簡版本,讓開發者可以在物聯網與嵌入式裝置中部署微型機器學習模型。 本課程將教授AI模型如何佈署於微控制器,包含模型訓練、模型最佳化以及TensorFlow Lite框架的程式開發等。此外,在實作上以Sparkfun edge board (ARM cortex M4)為例,說明如何以TensorFlow Lite 進行微控制器上面的人工智慧開發專案,包含人臉偵測、關鍵字的字詞偵測、姿態識別、異常偵測等。
Red Bend Software: Separation Using Type-1 Virtualization in Vehicles and Aut...Red Bend Software
Satish Varma from Red Bend Software presents at TI Tech Day Detroit 2013 on how to use Type-1 virtualization to consolidate hardware in automotive ECUs. Panelists included QNX Software Systems and Crank Software.
MVVM в WinForms – DevExpress Way (теория и практика)GoSharp
Из доклада вы узнаете о применении популярного паттерна MVVM для упрощения и ускорения процесса разработки desktop-приложений.
Будут рассмотрены общие проблемы этого паттерна и решения которые мы предлагаем в нашем кроссплатформенном MVVM фреймворке. Упор будет сделан на практические аспекты и техники в условиях использования платформы WinForms и контролов от DevExpress.
I2c interfacing raspberry pi to arduinoMike Ochtman
A complete reference how-to guide to connect and interface a Raspberry Pi and an Arduino over I2C using Python and smbus. Including how to configure both Raspberry Pi and Arduino to start communication over TWI/I2C
Full source code and documentation at https://github.com/MikeOchtman/Pi_Arduino_I2C
A talk I gave at Hackware v1.6 about issues relating to the UART and Bluetooth issues associated with the new Raspberry Pi 3.
The recorded video of this talk can be found here. https://engineers.sg/video/raspberry-pi-3-uart-bluetooth-issues--609
You can also consult my Github Gist on configuring UART and Bluetooth on Arch Linux. https://gist.github.com/yeokm1/d6c3ca927919c61257cd
In this video from the 2015 Stanford HPC Conference, Pavel Shamis from ORNL presents: Preparing OpenSHMEM for Exascale.
"OpenSHMEM is a partitioned global address space (PGAS) one-sided communications library that enables remote memory access (RMA) across processing elements (PEs). Its API allows data to be transferred from one PE memory space to another PE’s symmetric memory space; decoupling the data transfers from synchronizations. OpenSHMEM is useful for applications that are latency driven or that have irregular communication patterns, because its one-sided API can be mapped very efficiently to hardware (e.g. RDMA interconnects, etc), and its one-sided programming model helps the overlapping of communication with computation. Summit is Oak Ridge National Laboratory’s next high performance supercomputer system that will be based on a many core/GPU hybrid architecture. In order to prepare OpenSHMEM for future systems, it is important to enhance its programming model to enable efficient utilization of the new hardware capabilities (e.g. massive multithreaded systems, accesses different type memories, next generation of interconnects, etc). This session will present recent advances in the area of OpenSHMEM extensions, implementations, and tools.”
Watch the video: http://insidehpc.com/2015/02/video-preparing-openshmem-for-exascale/
See more talks in the Stanford HPC Conference Video Gallery: http://wp.me/P3RLHQ-dOO
For the full video of this presentation, please visit:
https://www.edge-ai-vision.com/2020/12/making-edge-ai-inference-programming-easier-and-flexible-a-presentation-from-texas-instruments/
For more information about edge AI and computer vision, please visit:
https://www.edge-ai-vision.com
Manisha Agrawal, Product Marketing Engineer at Texas Instruments, presents the “Making Edge AI Inference Programming Easier and Flexible” tutorial at the September 2020 Embedded Vision Summit.
Deploying an AI model at the edge doesn’t have to be challenging—but it often is. Embedded processing vendors have unique sets of software tools for deploying models. It takes time and investment to learn to use proprietary tools and to optimize the edge implementation to achieve your desired performance. While embedded vendors are providing proprietary tools for model deployment, the open source community is also advancing to standardize the model deployment process and make it hardware agnostic.
Texas Instruments has adopted open source software frameworks to make model deployment easier and more flexible. In this talk, you will learn about the struggles developers face when deploying models for inference on embedded processors and how TI addresses these critical software development challenges. You will also discover how TI enables faster time-to-market using a flexible open source development approach without the need to compromise performance, accuracy or power requirements.
SHARP: In-Network Scalable Hierarchical Aggregation and Reduction Protocolinside-BigData.com
In this deck from the 2019 Stanford HPC Conference, Devendar Bureddy from Mellanox presents: SHARP: In-Network Scalable Hierarchical Aggregation and Reduction Protocol.
"Increased system size and a greater reliance on utilizing system parallelism to achieve computational needs, requires innovative system architectures to meet the simulation challenges. As a step towards a new network class of co-processors intelligent network devices, which manipulate data traversing the data-center network, SHARP technology designed to offload collective operation processing to the network.
This tutorial will provide an overview of SHARP technology, integration with MPI, SHARP software components and live example of running MPI collectives.
Devendar Bureddy is a Staff Engineer at Mellanox Technologies and has been instrumental in building several key technologies like SHARP, HCOLL, etc. Prior to joining Mellanox, he was a software developer at The Ohio State University in network-Based Computing Laboratory led by Dr. D. K. Panda, involved in the design and development of MVAPICH2, an open-source high-performance implementation of MPI over InfiniBand and 10GigE/iWARP.
Devendar received his master’s in Computer Science and Engineering from the Indian Institute of Technology, Kanpur. His research interests include high speed interconnects, parallel programming models and HPC software.
Watch the video: https://youtu.be/_EB2Ixy-cNw
Learn more: http://www.mellanox.com/page/products_dyn?product_family=261&mtag=sharp
and
http://hpcadvisorycouncil.com/events/2019/stanford-workshop/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
AI邊緣運算實作: TensorFlow Lite for MCU
https://bit.ly/3j2fIIt
[1]python程式設計
https://bit.ly/359cz4m
[2]AI機器學習&深度學習
http://bit.ly/2KDZZz4
[3]TensorFlow Lite for MCU
https://bit.ly/3j2fIIt
InfoSec World 2016 – RFIDiggity – Pentester Guide to Hacking HF/NFC and UHF...Bishop Fox
05 April 2016 - DEF CON 23 (2015)
Fran Brown & Shubham Shah - Bishop Fox
https://resources.bishopfox.com/resources/tools/rfid-hacking/
https://www.defcon.org/html/defcon-23/dc-23-speakers.html#Brown
Have you ever attended an RFID hacking presentation and walked away with more questions than answers? This talk will finally provide practical guidance for penetration testers on hacking High Frequency (HF - 13.56 MHz) and Ultra-High Frequency (UHF – 840-960 MHz). This includes Near Field Communication (NFC), which also operates at 13.56 MHz and can be found in things like mobile payment technologies, e.g., Apple Pay and Google Wallet. We’ll also be releasing a slew of new and free RFID hacking tools using Arduino microcontrollers, Raspberry Pis, phone/tablet apps, and even 3D printing.
This presentation will NOT weigh you down with theoretical details or discussions of radio frequencies and modulation schemes. It WILL serve as a practical guide for penetration testers to better understand the attack tools and techniques available to them for stealing and using RFID tag information, specifically for HF and UHF systems. We will showcase the best-of-breed in hardware and software that you’ll need to build an RFID penetration toolkit. Our goal is to eliminate pervasive myths and accurately illustrate RFID risks via live attack DEMOS:
o High Frequency / NFC – Attack Demos:
- HF physical access control systems (e.g., iCLASS and MIFARE DESFire “contactless smart card” product families)
- Credit cards, public transit cards, passports (book), mobile payment systems (e.g., Apple Pay, Google Wallet), NFC loyalty cards (e.g., MyCoke Rewards), new hotel room keys, smart home door locks, and more
o Ultra-High Frequency – Attack Demos:
- Ski passes, enhanced driver’s licenses, passports (card), U.S. Permanent Resident Card (“green card”), trusted traveler cards
Schematics and Arduino code will be released, and 100 lucky audience members will receive one of a handful of new flavors of our Tastic RFID Thief custom PCB, which they can insert into almost any commercial RFID reader to steal badge info or use as a MITM backdoor device capable of card replay attacks. New versions include extended control capabilities via Arduino add-on modules such as Bluetooth low energy (BLE) and GSM/GPRS (SMS messaging) modules
This DEMO-rich presentation will benefit both newcomers to RFID penetration testing as well as seasoned professionals.
DISCLAIMER: This video is intended for pentesting training purposes only.
Embedded Graphics Drivers in Mesa (ELCE 2019)Igalia
By Neil Roberts.
Users of mobile platforms are expecting more and more complex graphics on their devices. This means that taking advantage of the mobile GPUs efficiently is essential. A large part of this efficiency is dependent on the user-space drivers. Unfortunately being in user-space means that many GPU providers can get away with only providing a closed-source driver which hides a lot of the secrets needed to be efficient. This talk presents a project providing an open-source alternative including support for embedded platforms.
Mesa is the standard open-source user-space library providing an implementation of the OpenGL, GLES and Vulkan APIs on Linux platforms. It has drivers for a range of different hardware. This talk will present the project, the user-space graphics stack and the inner workings of Mesa. It will then continue to present the embedded drivers that it supports such as Freedreno for the Adreno platform, Panfrost for Mali Midgard and Bifrost GPUs and the drivers for Broadcom GPUs.
(c) Open Source Summit + Embedded Linux Conference Europe 2019
October 28 - 30, 2019
Citi Centre de Congrès de Lyon (Lyon Convention Centre)
Lyon, France
2015.11.27 工研院 "物聯網發展趨勢、關鍵技術與應用實務" 課程簡報
Internet of things on energy monitor.
using open hardware and open source project to implement IoT in simple way.
MVVM в WinForms – DevExpress Way (теория и практика)GoSharp
Из доклада вы узнаете о применении популярного паттерна MVVM для упрощения и ускорения процесса разработки desktop-приложений.
Будут рассмотрены общие проблемы этого паттерна и решения которые мы предлагаем в нашем кроссплатформенном MVVM фреймворке. Упор будет сделан на практические аспекты и техники в условиях использования платформы WinForms и контролов от DevExpress.
I2c interfacing raspberry pi to arduinoMike Ochtman
A complete reference how-to guide to connect and interface a Raspberry Pi and an Arduino over I2C using Python and smbus. Including how to configure both Raspberry Pi and Arduino to start communication over TWI/I2C
Full source code and documentation at https://github.com/MikeOchtman/Pi_Arduino_I2C
A talk I gave at Hackware v1.6 about issues relating to the UART and Bluetooth issues associated with the new Raspberry Pi 3.
The recorded video of this talk can be found here. https://engineers.sg/video/raspberry-pi-3-uart-bluetooth-issues--609
You can also consult my Github Gist on configuring UART and Bluetooth on Arch Linux. https://gist.github.com/yeokm1/d6c3ca927919c61257cd
In this video from the 2015 Stanford HPC Conference, Pavel Shamis from ORNL presents: Preparing OpenSHMEM for Exascale.
"OpenSHMEM is a partitioned global address space (PGAS) one-sided communications library that enables remote memory access (RMA) across processing elements (PEs). Its API allows data to be transferred from one PE memory space to another PE’s symmetric memory space; decoupling the data transfers from synchronizations. OpenSHMEM is useful for applications that are latency driven or that have irregular communication patterns, because its one-sided API can be mapped very efficiently to hardware (e.g. RDMA interconnects, etc), and its one-sided programming model helps the overlapping of communication with computation. Summit is Oak Ridge National Laboratory’s next high performance supercomputer system that will be based on a many core/GPU hybrid architecture. In order to prepare OpenSHMEM for future systems, it is important to enhance its programming model to enable efficient utilization of the new hardware capabilities (e.g. massive multithreaded systems, accesses different type memories, next generation of interconnects, etc). This session will present recent advances in the area of OpenSHMEM extensions, implementations, and tools.”
Watch the video: http://insidehpc.com/2015/02/video-preparing-openshmem-for-exascale/
See more talks in the Stanford HPC Conference Video Gallery: http://wp.me/P3RLHQ-dOO
For the full video of this presentation, please visit:
https://www.edge-ai-vision.com/2020/12/making-edge-ai-inference-programming-easier-and-flexible-a-presentation-from-texas-instruments/
For more information about edge AI and computer vision, please visit:
https://www.edge-ai-vision.com
Manisha Agrawal, Product Marketing Engineer at Texas Instruments, presents the “Making Edge AI Inference Programming Easier and Flexible” tutorial at the September 2020 Embedded Vision Summit.
Deploying an AI model at the edge doesn’t have to be challenging—but it often is. Embedded processing vendors have unique sets of software tools for deploying models. It takes time and investment to learn to use proprietary tools and to optimize the edge implementation to achieve your desired performance. While embedded vendors are providing proprietary tools for model deployment, the open source community is also advancing to standardize the model deployment process and make it hardware agnostic.
Texas Instruments has adopted open source software frameworks to make model deployment easier and more flexible. In this talk, you will learn about the struggles developers face when deploying models for inference on embedded processors and how TI addresses these critical software development challenges. You will also discover how TI enables faster time-to-market using a flexible open source development approach without the need to compromise performance, accuracy or power requirements.
SHARP: In-Network Scalable Hierarchical Aggregation and Reduction Protocolinside-BigData.com
In this deck from the 2019 Stanford HPC Conference, Devendar Bureddy from Mellanox presents: SHARP: In-Network Scalable Hierarchical Aggregation and Reduction Protocol.
"Increased system size and a greater reliance on utilizing system parallelism to achieve computational needs, requires innovative system architectures to meet the simulation challenges. As a step towards a new network class of co-processors intelligent network devices, which manipulate data traversing the data-center network, SHARP technology designed to offload collective operation processing to the network.
This tutorial will provide an overview of SHARP technology, integration with MPI, SHARP software components and live example of running MPI collectives.
Devendar Bureddy is a Staff Engineer at Mellanox Technologies and has been instrumental in building several key technologies like SHARP, HCOLL, etc. Prior to joining Mellanox, he was a software developer at The Ohio State University in network-Based Computing Laboratory led by Dr. D. K. Panda, involved in the design and development of MVAPICH2, an open-source high-performance implementation of MPI over InfiniBand and 10GigE/iWARP.
Devendar received his master’s in Computer Science and Engineering from the Indian Institute of Technology, Kanpur. His research interests include high speed interconnects, parallel programming models and HPC software.
Watch the video: https://youtu.be/_EB2Ixy-cNw
Learn more: http://www.mellanox.com/page/products_dyn?product_family=261&mtag=sharp
and
http://hpcadvisorycouncil.com/events/2019/stanford-workshop/
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
AI邊緣運算實作: TensorFlow Lite for MCU
https://bit.ly/3j2fIIt
[1]python程式設計
https://bit.ly/359cz4m
[2]AI機器學習&深度學習
http://bit.ly/2KDZZz4
[3]TensorFlow Lite for MCU
https://bit.ly/3j2fIIt
InfoSec World 2016 – RFIDiggity – Pentester Guide to Hacking HF/NFC and UHF...Bishop Fox
05 April 2016 - DEF CON 23 (2015)
Fran Brown & Shubham Shah - Bishop Fox
https://resources.bishopfox.com/resources/tools/rfid-hacking/
https://www.defcon.org/html/defcon-23/dc-23-speakers.html#Brown
Have you ever attended an RFID hacking presentation and walked away with more questions than answers? This talk will finally provide practical guidance for penetration testers on hacking High Frequency (HF - 13.56 MHz) and Ultra-High Frequency (UHF – 840-960 MHz). This includes Near Field Communication (NFC), which also operates at 13.56 MHz and can be found in things like mobile payment technologies, e.g., Apple Pay and Google Wallet. We’ll also be releasing a slew of new and free RFID hacking tools using Arduino microcontrollers, Raspberry Pis, phone/tablet apps, and even 3D printing.
This presentation will NOT weigh you down with theoretical details or discussions of radio frequencies and modulation schemes. It WILL serve as a practical guide for penetration testers to better understand the attack tools and techniques available to them for stealing and using RFID tag information, specifically for HF and UHF systems. We will showcase the best-of-breed in hardware and software that you’ll need to build an RFID penetration toolkit. Our goal is to eliminate pervasive myths and accurately illustrate RFID risks via live attack DEMOS:
o High Frequency / NFC – Attack Demos:
- HF physical access control systems (e.g., iCLASS and MIFARE DESFire “contactless smart card” product families)
- Credit cards, public transit cards, passports (book), mobile payment systems (e.g., Apple Pay, Google Wallet), NFC loyalty cards (e.g., MyCoke Rewards), new hotel room keys, smart home door locks, and more
o Ultra-High Frequency – Attack Demos:
- Ski passes, enhanced driver’s licenses, passports (card), U.S. Permanent Resident Card (“green card”), trusted traveler cards
Schematics and Arduino code will be released, and 100 lucky audience members will receive one of a handful of new flavors of our Tastic RFID Thief custom PCB, which they can insert into almost any commercial RFID reader to steal badge info or use as a MITM backdoor device capable of card replay attacks. New versions include extended control capabilities via Arduino add-on modules such as Bluetooth low energy (BLE) and GSM/GPRS (SMS messaging) modules
This DEMO-rich presentation will benefit both newcomers to RFID penetration testing as well as seasoned professionals.
DISCLAIMER: This video is intended for pentesting training purposes only.
Embedded Graphics Drivers in Mesa (ELCE 2019)Igalia
By Neil Roberts.
Users of mobile platforms are expecting more and more complex graphics on their devices. This means that taking advantage of the mobile GPUs efficiently is essential. A large part of this efficiency is dependent on the user-space drivers. Unfortunately being in user-space means that many GPU providers can get away with only providing a closed-source driver which hides a lot of the secrets needed to be efficient. This talk presents a project providing an open-source alternative including support for embedded platforms.
Mesa is the standard open-source user-space library providing an implementation of the OpenGL, GLES and Vulkan APIs on Linux platforms. It has drivers for a range of different hardware. This talk will present the project, the user-space graphics stack and the inner workings of Mesa. It will then continue to present the embedded drivers that it supports such as Freedreno for the Adreno platform, Panfrost for Mali Midgard and Bifrost GPUs and the drivers for Broadcom GPUs.
(c) Open Source Summit + Embedded Linux Conference Europe 2019
October 28 - 30, 2019
Citi Centre de Congrès de Lyon (Lyon Convention Centre)
Lyon, France
2015.11.27 工研院 "物聯網發展趨勢、關鍵技術與應用實務" 課程簡報
Internet of things on energy monitor.
using open hardware and open source project to implement IoT in simple way.
https://youtu.be/RHvROP94qZ0
AI邊緣運算實作: TensorFlow Lite for MCU
https://bit.ly/3j2fIIt
[1]python程式設計
https://bit.ly/359cz4m
[2]AI機器學習&深度學習
http://bit.ly/2KDZZz4
[3]TensorFlow Lite for MCU
https://bit.ly/3j2fIIt
10. 軟體架構 -智慧門鈴系統
NFC_Check
NFC (pn-532)
IT Ring Door
(Main function)
HTTP server (Tornado)
UART
RF(CC2500)
Web UI
Camera
User
Space
Device
Driver
Hardware
Data Collection
(Python)
SPI
Libnfc
SMTP MJPEG
PIC(CC2500)
GPIO USB
Door button
Door Lock
E-mail
with
photo
11. 軟體架構 – 即時數劇更新
NFC_Check
NFC (pn-532)
IT Ring Door
(Main function)
HTTP server (Tornado)
UART
RF(CC2500)
Web UI
Camera
User
Space
Hardware
Data Collection
(Python)
SPI
Libnfc
SMTP MJPEG
PIC(CC2500)
GPIO USB
Door button
Door LockData
Device
Driver
12. 軟體架構 – 即時遠端控制
NFC_Check
NFC (pn-532)
IT Ring Door
(Main function)
HTTP server (Tornado)
UART
RF(CC2500)
Web UI
Camera
User
Space
Hardware
Data Collection
(Python)
SPI
Libnfc
SMTP MJPEG
PIC(CC2500)
GPIO USB
Door button
Door Lock
Command
Command
Device
Driver
13. 軟體架構 - NFC
NFC_Check
NFC (pn-532)
IT Ring Door
(Main function)
HTTP server (Tornado)
UART
RF(CC2500)
Web UI
Camera
User
Space
Hardware
Data Collection
(Python)
SPI
Libnfc
SMTP MJPEG
PIC(CC2500)
GPIO USB
Door button
Door Lock
NFC UID
Check ok
Device
Driver
14. PIC 功能方塊圖
UART1 I/O UART2
CCP1 Micro chip PIC18F46J50 SPI
USB I2C ADC RTCC I/O CCP2
Si7020
CC2500
Power
LED
Relay
IR
Button
七段顯示器
PL2303
UART TO USB
Bluetooth
VR
19. • 每個通訊裝置都有不同的識別 ID
• 無線通訊的連線需要分辨發送端(SID)、接收端(TID)
• 拓樸架構相同的網路需不同的群組(GID)識別
2.4G RF 無線通訊
– 封包設計
TID SID GID TP PAYLOAD
1: RESET
2: GET
3: SET
4: REPLY
5: ACK
TID : Target ID
SID : Source ID
GID: Group ID
TP : Type command
20. 無線通訊的控制封包
1 8 7 3 1
1 8 7 3 1
燈具 ID 主機 ID 群組 ID SET ONMaster 送出開燈具的封包
8 1 7 5 1
主機 ID 燈具 ID 群組 ID ACK ON
Slave 回傳 ACK 封包