artificial intelligence

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on Mini-ITX motherboard combines AMD Ryzen Embedded R2314 SoC with two InferX X1 AI accelerators

Mini-ITX motherboard combines AMD Ryzen Embedded R2314 SoC with two InferX X1 AI accelerators

InferX Hawk Mini-ITX motherboard AMD AI accelerators

Flex Logix has just announced the InferX Hawk mini-ITX motherboard equipped with an AMD Ryzen Embedded R2314 SoC and two InferX X1 AI accelerators from the company in order to help customers customize, build and deploy edge and embedded AI systems easily and quickly. The motherboard features up to 32GB RAM, supports SATA and M.2 MVMe/SATA storage, provides dual Gigabit Ethernet and optional WiFi/4F LTE connectivity, plus the usual USB 3.2, DisplayPort, and serial interfaces, and is meant to compete directly against solutions based on NVIDIA Jetson AGX Xavier.   InferX Hawk specifications: SoC – AMD Ryzen Embedded R2314 quad-core processor @ 2.1/3.5 GHz (Turbo) with hexa-core Radeon Vega graphics; TDP: 12 to 35W AI accelerators – 2x InferX X1 accelerators System Memory – 2x DDR4 SO-DIMM up to 32GB capacity Storage M.2 M Key socket for NVMe or SATA SSD SATA 3.0 connector Video Output – 2x DisplayPort Networking […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on Ztachip open-source RISC-V AI accelerator performs up to 50 times faster

Ztachip open-source RISC-V AI accelerator performs up to 50 times faster

Ztachip RISC-V AI accelerator

Ztachip is an open-source RISC-V accelerator for vision and AI edge applications running on low-end FPGA devices or custom ASIC that is said to perform 20 to 50 times faster than on non-accelerated RISC-V implementations, and is also better than RISC-V cores with vector extensions (no numbers were provided here). Ztachip, pronounced zeta-chip, is not tied to a particular architecture, but the example code features a RISC-V core based on the VexRiscv implementation and can accelerate common computer vision tasks such as edge detection, optical flow, motion detection, color conversion, as well as TensorFlow AI models without retraining. The open-source AI accelerator has been tested on Digilent ArtyA7-100T FPGA board in combination with a PMOD VGA module to connect to a display and an OV7670 VGA camera module. You can then build the sample found on Github with the Xilinx Vivado Webpack free edition and flash it to the board […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 3 Comments on Sipeed MetaSense RGB ToF 3D depth cameras are made for MCUs & ROS Robots (Crowfunding)

Sipeed MetaSense RGB ToF 3D depth cameras are made for MCUs & ROS Robots (Crowfunding)

Sipeed MetaSense RGB ToF 3D Depth Cameras

We’ve just written about the Arducam ToF camera to add depth sensing to Raspberry Pi, but there are now more choices, as Sipeed has just introduced its MetaSense ToF (Time-of-Flight) camera family for microcontrollers and robots running ROS with two models offering different sets of features and capabilities. The MetaSense A075V USB camera offers 320×240 depth resolution plus an extra RGB sensor, an IMU unit, and a CPU with built-in NPU that makes it ideal for ROS 1/2 robots, while the lower-end MetaSense A010 ToF camera offers up to 100×100 resolution, integrates a 1.14-inch LCD display to visualize depth data in real-time and can be connected to a microcontroller host, or even a Raspberry Pi, through UART or USB. MetaSense A075V specifications: SoC – Unnamed quad-core Arm Cortex-A7 processor @ 1.5 GHz with 0.4 TOPS NPU System Memory – 128 MB RAM Storage – 128MB flash Cameras 800×600 @ 30 […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on GENE-ADP6 – An 3.5-inch SBC with Intel 12th Gen Alder Lake-P processor, DDR5 RAM

GENE-ADP6 – An 3.5-inch SBC with Intel 12th Gen Alder Lake-P processor, DDR5 RAM

3.5-inch Alder Lake-P SBC

AAEON GENE-ADP6 is a 3.5-inch SBC equipped with a choice of Intel 12th Gen Alder Lake-P (and Alder Lake-U) processors and the first from the company to support DDR5 memory, of which up to 64GB can be installed through two SO-DIMM sockets. The single board computer also supports SATA and NVMe storage, up to two 8K displays (and up to four independent displays), 2.5GbE networking, USB 3.2 ports, four RS232/RS422/RS485 interfaces, and further expansion through three M.2 sockets for wireless connectivity (WiFi, 5Gm, 4G LTE…) as well as the already mentioned NVMe SSD storage. GENE-ADP6 SBC specifications: Intel Alder Lake-P SoC (one or the other) Core i7-1270PE 12-core/16-thread processor @ 3.30GHz / 4.50GHz (Turbo) with 96EU Intel Xe graphics – PBP: 28W, up to 64W MTP Core i7-1265UE 10-core/12-thread processor @ 3.50GHz / 4.70GHz (Turbo) with 96EU Intel Xe graphics – PBP: 15W, up 55W MTP Core i5-1250PE 12-core/16-thread processor […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 3 Comments on Odyssey Blue mini PC bundle ships with Frigate open-source NVR, Coral USB AI accelerator

Odyssey Blue mini PC bundle ships with Frigate open-source NVR, Coral USB AI accelerator

Frigate NVR Odyssey Blue mini PC

Odyssey Blue mini PC based on the ODYSSEY-X86J4125 SBC is now offered as part of a bundle with Frigate open-source NVR platform with support for real-time local object detection, and an Coral USB AI accelerator. The Odyssey Blue mini PC is equipped with an Intel Celeron J4125 quad-core Gemini Lake Refresh processor, 8GB RAM, and a 128GB SSD preloaded with an unnamed Linux OS (probably Debian 11) and Frigate Docker container. The solution can run over object detection at 100+ FPS when equipped with a Coral USB accelerator. Since the hardware is not exactly new, and we’ve covered it in detail in the past, even reviewing the earlier generation SBC with Celeron J4105 processor and Re_Computer enclosure, I’ll focus on the software, namely Frigate NVR in this post. Frigate is an open-source NVR program designed for Home Assistant with AI-powered object detection that runs as a Docker container and uses […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on NVIDIA Jetson Xavier NX fanless embedded box PC features four HDMI input ports

NVIDIA Jetson Xavier NX fanless embedded box PC features four HDMI input ports

NVIDIA Xavier NX embedded box pc four HDMI inputs

AAEON BOXER-8256AI is a fanless embedded box PC equipped with an NVIDIA Jetson Xavier NX system-on-module, offering four HDMI input ports – two Full HD, two 4K capable -, as well as two HDMI outputs for smart healthcare equipment, digital signage, and entertainment. The embedded computer comes with 8GB RAM and a 16GB flash provided by the NVIDIA module, supports M.2 NVMe and SATA storage, Gigabit Ethernet, plus optional WiFI, 4G, and 5G cellular connectivity through M.2 sockets.   BOXER-8256AI specifications: SoM – NVIDIA Jetson Xavier NX with CPU – 6-core NVIDIA Carmel Armv8.2 64-bit CPU GPU – 384-core NVIDIA Volta GPU with 48 Tensor Cores AI accelerator – 2x NVDLA deep learning accelerators AI performance – Up to 21 TOPS at 15 Watts System Memory – 8GB LPDDR4x Storage – 16GB eMMC flash Storage – MicroSD Slot, M.2 NVMe SSD socket, SATA III port Display Interfaces – 2x HDMI […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on Intel Loihi 2 high-efficiency neuromorphic chip works with the Lava open-source framework

Intel Loihi 2 high-efficiency neuromorphic chip works with the Lava open-source framework

Intel Loihi 2

Neuromorphic AI accelerator chips relying on spiking neural networks (SNN), which we’ve seen from companies such as Innatera or Brainchip, will be used more and more in the future as they provide much higher efficiency compared to traditional deep neural networks (DNN) solutions. Intel is also working on SNN, and recently announced the Loihi 2 second-generation neuromorphic research chip with up to 1 million neurons (the human brain has 86 billion of those on average) that delivers up to 175x lower energy to learn a new object instance with similar or better speed and accuracy compared to conventional methods running on a central processing unit (CPU). The new Loihi 2 neuromorphic chip offers the following improvement over the first generation Loihi: Up to 10x faster processing capability (2x for simple neuron state, 5x for synaptic operations, 10x for spike generation) Up to 60x more inter-chip bandwidth achieved through a combination […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on $7 Lolin S3 ESP32-S3 board ships with MicroPython firmware

$7 Lolin S3 ESP32-S3 board ships with MicroPython firmware

Lolin S3 ESP32-S3 board

Lolin S3 is the first ESP32-S3 board from the company, but instead of using the more compact D1 mini form factor, the board features a longer design with two rows of 20 pins offering up to 31 GPIOs. Based on ESP32-S3-WROOM-1 module, the board features 16MB QSPI flash, 8MB SPRAM, two USB Type-C OTG and UART ports, a Lolin I2C port, an RGB LED, as well as Reset and user buttons. Lolin S3 specifications: Wireless module – ESP32-S3-WROOM-1 module with: Espressif Systems ESP32-S3 dual-core Tensilica LX7 @ up to 240 MHz with vector instructions for AI acceleration, 512KB RAM, 2.4 GHz WiFi 4 and Bluetooth 5.0 LE with support for long-range, up to 2Mbps data rate, mesh networking 16MB QSPI flash 8MB PSRAM PCB antenna USB – 2x USB Type-C ports, one OTG port, one UART port for programming and debugging Expansion 2x 20-pin headers with up to 31x GPIO, […]