Artificial Intelligence (AI)

The Coral USB Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port. Features Supported host OS: Debian Linux, macOS, Windows 10 Compatible with Raspberry Pi boards Supported Framework: TensorFlow Lite Performs high-speed ML inferencing The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power-efficient manner. Supports all major platforms Connects via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10. Supports TensorFlow Lite No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU. Supports AutoML Vision Edge Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge. Specifications ML accelerator Google Edge TPU coprocessor:4 TOPS (int8); 2 TOPS per watt Connector USB 3.0 Type-C (data/power) Dimensions 65 x 30 mm Downloads/Documentation Datasheet Get started with the USB Accelerator Model compatibility on the Edge TPU Edge TPU inferencing overview Run multiple models with multiple Edge TPUs Pipeline a model with multiple Edge TPUs PyCoral API (Python) Libcoral API (C++) Libedgetpu API (C++) Edge TPU compiler Pre-compiled models All software downloads

Read more less

Ready to start developing Artificial Intelligence (AI) applications? The NVIDIA Jetson Nano Developer Kit makes the power of modern AI accessible to makers, developers, and students. When you think of NVIDIA, you probably think about graphics cards and GPUs, and rightfully so. Nvidia's track record guarantees that the Jetson Nano has enough power to run even the most demanding of tasks. The NVIDIA Jetson Nano Developer Kit is compatible with Nvidia's JetPack SDK and enables image classification and object detection amongst many applications. Applications The NVIDIA Jetson Nano Developer Kit can run multiple neural networks in parallel for applications like: Image classification Segmentation Object detection Speech processing Specifications GPU 128-core Maxwell CPU Quad-core ARM A57 @ 1.43 GHz Memory 4 GB 64-bit LPDDR4 25.6 GB/s Storage microSD (not included) Video Encode 4K @ 30 | 4x 1080p @ 30 | 9x 720p @ 30 (H.264/H.265) Video Decode 4K @ 60 | 2x 4K @ 30 | 8x 1080p @ 30 | 18x 720p @ 30 (H.264/H.265) Camera 1 x MIPI CSI-2 DPHY lanes Connectivity Gigabit Ethernet, M.2 Key E Display HDMI 2.0 and eDP 1.4 USB 4x USB 3.0, USB 2.0 Micro-B Interfaces GPIO, I²C, I²S, SPI, UART Dimensions 100 x 80 x 29 mm Included NVIDIA Jetson Nano module and carrier board Small paper card with quick start and support information Folded paper stand Downloads JetPack SDK Documentation Tutorials Online course Wiki

Read more less

Features Dual-Core 64-bit RISC-V RV64IMAFDC (RV64GC) CPU / 400Mhz(Normal) Dual Independent Double Precision FPU 8MiB 64bit width On-Chip SRAM Neural Network Processor(KPU) / 0.8Tops Field-Programmable IO Array (FPIOA) AES, SHA256 Accelerator Direct Memory Access Controller (DMAC) Micropython Support Firmware encryption support On-board Hardware: Flash: 16M Camera :OV7740 2x Buttons Status Indicator LED External storage: TF card/Micro SD Interface: HY2.0/compatible GROVE Applications Face recognition/detection Object detection/classification Obtain the size and coordinates of the target in real-time Obtain the type of detected target in real-time Shape recognition Video recorder Included 1x UNIT-V(include 20cm 4P cable and USB-C cable)

Read more less

Do you need a simple AI camera to enhance your projects?  The HuskyLens AI Camera intuitive design allows the user to control different aspects of the camera just by pressing buttons. You can start and stop learning new objects and even switch between algorithms from the device. To further reduce the need to be connected to a PC the HuskyLens AI Camera comes with a 2-inch display so you can see what's going on in real time. Specifications Processor: Kendryte K210 Image Sensor: OV2640 (2.0 Megapixel Camera) Supply Voltage: 3.3~5.0 V Current Consumption (TYP): 320 mA @ 3.3 V, 230 mA @ 5.0 V (face recognition mode; 80% backlight brightness; fill light off) Connection Interface: UART, I²C Display: 2.0-inch IPS screen with 320x240 resolution Built-in Algorithms: Face Recognition, Object Tracking, Object Recognition, Line Tracking, Color Recognition, Tag Recognition  Dimension: 52 x 44.5 mm (2.05 x 1.75') Included 1x HuskyLens Mainboard 6x M3 Screws 6x M3 Nuts 1x Small Mounting Bracket 1x Heightening Bracket 1x Gravity 4-Pin Sensor Cable

Read more less

Seeed Studio XIAO ESP32S3 Sense integrates a camera sensor, digital microphone, and SD card support. Combining embedded ML computing power and photography capability, this development board can be your great tool to get started with intelligent voice and vision AI. Seeed Studio XIAO ESP32S3 Sense is built around a highly-integrated, Xtensa processor ESP32-S3R8 SoC, which supports 2.4 GHz WiFi and low-power Bluetooth BLE 5.0 dual-mode for multiple wireless applications. It has lithium battery charge management capability. As the advanced version of Seeed Studio XIAO ESP32S3, this board comes with a plug-in OV2640 camera sensor for displaying full 1600x1200 resolution. The base of it is even compatible with OV5640 for supporting up to 2592x1944 resolution. The digital microphone is also carried with the board for voice sensing and audio recognition. SenseCraft AI provides various pre-trained Artificial Intelligence (AI) models and no-code deployment to XIAO ESP32S3 Sense. With powerful SoC and built-in sensors, this development board has 8 MB PSRAM and 8 MB Flash on the chip, an additional SD card slot for supporting up to 32 GB FAT memory. These allow the board for more programming space and bring even more possibilities into embedded ML scenarios. Features Powerful MCU Board: Incorporate the ESP32S3 32-bit, dual-core, Xtensa processor chip operating up to 240 MHz, mounted multiple development ports, Arduino/MicroPython supported Advanced Functionality: with OV5640 camera sensor, integrating additional digital microphone Great Memory for more Possibilities: Offer 8 MB PSRAM and 8 MB Flash, supporting SD card slot for external 32 GB FAT memory Outstanding RF performance: Support 2.4 GHz Wi-Fi and BLE dual wireless communication, support 100m+ remote communication when connected with U.FL antenna Thumb-sized Compact Design: 21 x 17.5 mm, adopting the classic form factor of XIAO, suitable for space-limited projects like wearable devices Pretrained Al model from SenseCraft Al for no-code deployment Applications Image processing Speech Recognition Video Monitoring Wearable devices Smart Homes Health monitoring Education Low-Power (LP) networking Rapid prototyping Specifications Processor ESP32-S3R8 Xtensa LX7 dual-core, 32-bit processor that operates at up to 240 MHz Wireless Complete 2.4 GHz Wi-Fi subsystem BLE: Bluetooth 5.0, Bluetooth mesh Built-in Sensors oV2640 camera sensor for 1600x1200 Digital Microphone Memory On-chip 8 MB PSRAM & 8 MB Flash Onboard SD Card Slot, supporting 32 GB FAT lnterface 1x UART, 1x I²C, 1x I²S, 1x SPI, 11x GPIOs (PWM), 9x ADC, 1x User LED, 1x Charge LED, 1x B2B Connector (with 2 additional GPIOs) 1x Reset button, 1x Boot button Dimensions 21 x 17.5 x 15 mm (with expansion board) Power Input voltage (Type-C): 5 V lnput voltage (BAT): 4.2 V Circuit operating Voltage (ready to operate): - Type-C: 5 V @ 38.3 mA - BAT: 3.8 V @ 43.2 mA (with expansion board) Webcam Web application: Type-C: - Average power consumption: 5 V/138 mA - Photo moment: 5 V/341 mA Battery: - Average power consumption: 3.8 V/154 mA - Photo moment: 3.8 V/304 mA Microphone recording & SD card writing: Type-C: - Average power consumption: 5 V/46.5 mA - Peak power consumption: 5 V/89.6 mA Battery: - Average power consumption: 3.8 V/54.4 mA - Peak power consumption: 3.8 V/108 mA Charging battery current: 100 mA Low Power Consumption Model (Supply Power: 3.8 V) Modem Sleep Model: ~44 mA Light Sleep Model: ~5 mA Deep Sleep Model: ~3 mA Wi-Fi Enabled Power Consumption Active Model: ~ 110 mA (with expansion board) BLE Enabled Power Consumption Active Model: ~ 102 mA (with expansion board) Included 1x XIAO ESP32S3 1x Plug-in camera sensor board 1x Antenna Downloads GitHub

Read more less

Solving Real-World Problems with Embedded Machine LearningEdge AI is transforming the way computers interact with the real world, allowing IoT devices to make decisions using the 99% of sensor data that was previously discarded due to cost, bandwidth, or power limitations. With techniques like embedded machine learning, developers can capture human intuition and deploy it to any target—from ultra-low power microcontrollers to embedded Linux devices.This practical guide gives engineering professionals, including product managers and technology leaders, an end-to-end framework for solving real-world industrial, commercial, and scientific problems with edge AI. You'll explore every stage of the process, from data collection to model optimization to tuning and testing, as you learn how to design and support edge AI and embedded ML products. Edge AI is destined to become a standard tool for systems engineers. This high-level road map helps you get started. Develop your expertise in AI and ML for edge devices Understand which projects are best solved with edge AI Explore key design patterns for edge AI apps Learn an iterative workflow for developing AI systems Build a team with the skills to solve real-world problems Follow a responsible AI process to create effective products Downloads Errata GitHub

Read more less

The Waveshare Jetson Nano Development Kit, based on AI computers Jetson Nano (with 16 GB eMMC) and Jetson Xavier NX, provides almost the same IOs, size, and thickness as the Jetson Nano Developer Kit (B01), more convenient for upgrading the core module. By utilizing the power of the core module, it is qualified for fields like image classification, object detection, segmentation, speech processing, etc., and can be used in sorts of AI projects. Specifications GPU 128-core Maxwell CPU Quad-core ARM A57 @ 1.43 GHz RAM 4 GB 64-bit LPDDR4 25.6 GB/s Storage 16 GB eMMC + 64 GB TF Card Video encoder 250 MP/s 1x 4K @ 30 (HEVC) 2x 1080p @ 60 (HEVC) 4x 1080p @ 30 (HEVC) Video decoder 500 MP/s 1x 4K @ 60 (HEVC) 2x 4K @ 30 (HEVC) 4x 1080p @ 60 (HEVC) 8x 1080p @ 30 (HEVC) Camera 1x MIPI CSI-2 D-PHY lanes Connectivity Gigabit Ethernet, M.2 Key E expansion connector Display HDMI USB 1x USB 3.2 Gen 1 Type A 2x USB 2.0 Type A 1x USB 2.0 Micro-B Interfaces GPIO, I²C, I²S, SPI, UART Dimensions 100 x 80 x 29 mm Included 1x JETSON-NANO-LITE-DEV-KIT (carrier + Nano + heatsink) 1x AC8265 dual-mode NIC 1x Cooling fan 1x USB cable (1.2 m) 1x Ethernet cable (1.5 m) 1x 5 V/3 A power adapter (EU) 1x 64 GB TF Card 1x Card reader Documentation Wiki

Read more less

This AI Edge Computing Development Kit is based on the Jetson Orin Nano Module providing rich peripheral interfaces such as M.2, DP, USB, etc. This kit also comes with a pre-installed AW-CB375NF wireless network card that supports Bluetooth 5.0 and dual-band WIFI, with two additional PCB antennas, for providing high-speed and reliable wireless network connection and Bluetooth communication. Specifications AI performance 40 TOPS GPU 1024-core N-VIDIA Ampere architecture GPU with 32 Tensor Cores GPU frequency 625 MHz (max) CPU 6-core Arm Cortex-A78AE v8.2 64-bit CPU, 1.5 MB L2 + 4 MB L3 CPU frequency 1.5 GHz (max) RAM 8 GB 128-bit LPDDR5, 68 GB/s Storage 128 GB NVMe Solid State Drive Power 7~15 W PCIE M.2 Key M slot with x4 PCIe Gen3 M.2 Key M slot with x2 PCIe Gen3 M.2 Key E slot USB USB Type-A: 4x USB 3.2 Gen2 USB Type-C (UFP) CSI camera 2x MIPI CSI-2 camera connector Video encode 1080p30 supported by 1-2 CPU cores Video decode 1x 4K60 (H.265) 2x 4K30 (H.265) 5x 1080p60 (H.265) 11x 1080p30 (H.265) Display 1x DisplayPort 1.2 (+MST) connector Interfaces 40-Pin Expansion Header (UART, SPI, I²S, I²C, GPIO), 12-pin button header, 4-pin fan header, DC power jack Networking 1x GbE connector Dimensions 103 x 90.5 x 34 mm Included Waveshare Orin Nano development kit 1x Jetson Orin Nano Module (8 GB) 1x JETSON-ORIN-IO-BASE 1x Cooling Fan 1x 128 GB NVMe Solid State Drive (assembled) 1x Wireless network card (assembled) 1x USB Type A to Type-C cable (1 m) 1x Ethernet cable (1.5 m) 1x Jumper 1x Power adapter (EU) Documentation Wiki

Read more less