artificial intelligence

Posted on by Debashis Das - No Comments on Renesas AIK-RA4E1 and AIK-RA6M3 reference kits are designed for accelerated AI/ML development

Renesas AIK-RA4E1 and AIK-RA6M3 reference kits are designed for accelerated AI/ML development

Renesas AIK RA4E1 and AIK RA6M3 reference

Renesas AIK-RA4E1 and AIK-RA6M3 are two new development boards based on RA-series 32-bit microcontrollers. These new dev boards have multiple reconfigurable connectivity functions to accelerate AI and ML design and development time. Both boards appear similar, but the AIK-RA4E1 uses the R7FA4E110D2CFM MCU, features three Pmod ports, and has no Ethernet support. On the other hand, the AIK-RA6M3 utilizes the R7FA6M3AH3CFC MCU, has six Pmod ports, and includes Ethernet support. Both the boards support full-speed USB and CAN bus. Renesas AIK-RA4E1 and AIK-RA6M3 reference kits specifications (Consolidated): RA4E1 Microcontroller Features: Model: R7FA4E110D2CFM Package: 64-pin LQFP Core: 100 MHz Arm Cortex-M33 SRAM: 128 KB on-chip Code Flash Memory: 512 MB on-chip Data Flash Memory: 8 KB on-chip RA6M3 Microcontroller Features: Model: R7FA6M3AH3CFC Package: 176-pin LQFP Core: 120 MHz Arm Cortex-M4 with FPU SRAM: 640 KB on-chip Code Flash Memory: 2 MB on-chip Data Flash Memory: 64 KB on-chip Connectivity: One USB […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 15 Comments on Rockchip RK3582 is a cost-down version of RK3588S with two Cortex-A76 cores, four Cortex-A55 cores, no GPU

Rockchip RK3582 is a cost-down version of RK3588S with two Cortex-A76 cores, four Cortex-A55 cores, no GPU

Rockchip RK3582

Rockchip RK3582 hexa-core SoC is pin-to-pin compatible with the popular Rockchip RK3588S octa-core Cortex-A76/A55 SoC, but only features two Cortex-A76 cores, a 5 TOPS NPU (instead of 6 TOPS) and does not come with a 3D GPU. I was first made aware of the Rockchip RK3582 in October 2023 when I was sent a photo of a board allegedly for a TV box, but while the RK3582 still features a 4K video decoder, the lack of a 3D GPU could make it problematic with 3D accelerated user interface. We now have more details with Radxa having released the datasheet and a few more interesting details. Rockchip RK3582 specifications: Hexa-core CPU – 2x Cortex-A76 and 4x Cortex-A55 cores in dynamIQ configuration (frequencies are still shown as TBD in the datasheet) GPU No 3D GPU 2D graphics engine up to 8192×8192 source, 4096×4096 destination AI Accelerator – 5 TOPS NPU 3.0 (Neural […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 7 Comments on Smartcam T1205 – An IP65-rated AI camera with NVIDIA Jetson Orin Nano 40 TOPS system-on-module

Smartcam T1205 – An IP65-rated AI camera with NVIDIA Jetson Orin Nano 40 TOPS system-on-module

NVIDIA Jetson Orin AI camera

SmartCow’s SmartCam T1025 is a powerful AI camera based on the NVIDIA Jetson Orin Nano 8GB system-on-module with 40 TOPS of AI performance. The camera features M12 connectors for gigabit Ethernet, power, and serial interface, and has been certified with an IP65 ingress protection rating for outdoor operation. The camera also comes with 256GB NVMe SSD for the OS (Jetpack 6.0) and data storage and supports 4G LTE and GPS connectivity through an M.2 module. The company also introduced the SmartCam T1023 model compatible with NVIDIA Jetson Nano and Jetson TX2 NX for applications that do not require as much processing power and/or memory as provided by the Jetson Orin Nano AI camera. SmartCam T1025 specifications: System-on-module – NVIDIA Jetson Orin Nano 8GB CPU – 6-core Arm Cortex-A78AE v8.2 64-bit CPU @ 1.5 GHz with 1.5 MB L2 + 4 MB L3 GPU – 1024-core NVIDIA Ampere GPU @ 625 […]

Posted on by Kumpee Teeravech - 10 Comments on Review of Purple Pi OH – A Rockchip RK3566 SBC tested in 2GB/16GB and 4GB/32GB configurations

Review of Purple Pi OH – A Rockchip RK3566 SBC tested in 2GB/16GB and 4GB/32GB configurations

Review of Purple Pi OH and Purple Pi OH Pro

Hello, I am going to review the Purple Pi OH boards from Wireless-Tag. The Purple Pi OH is a single-board computer (SBC) mechanically compatible with the Raspberry Pi. They are designed for personal mobile Internet devices and AIoT devices, which can be used in various applications, such as tablets, speakers with screens, and lightweight AI applications. The manufacturer sent me two models. The first model is the Purple Pi OH, which is equipped with 2GB of memory and 16GB of storage space and supports 2.4GHz Wi-Fi. The second model is the Purple Pi OH Pro, equipped with 4GB of memory and 32GB of storage space. This board supports both 2.4GHz and 5GHz Wi-Fi. The other components of both devices are almost the same. They are powered by the Rockchip RK3566 chip, which integrates a quad-core Cortex-A55 processor up to 1.8 GHz, a Mali-G52 GPU from Arm for 3D graphics acceleration, […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on Edge Impulse machine learning platform adds support for NVIDIA TAO Toolkit and Omniverse

Edge Impulse machine learning platform adds support for NVIDIA TAO Toolkit and Omniverse

Edge Impulse NVIDIA TAO Models

Edge Impulse machine learning platform for edge devices has released a new suite of tools developed on NVIDIA TAO Toolkit and Omniverse that brings new AI models to entry-level hardware based on Arm Cortex-A processors, Arm Cortex-M microcontrollers, or Arm Ethos-U NPUs. By combining Edge Impulse and NVIDIA TAO Toolkit, engineers can create computer vision models that can be deployed to edge-optimized hardware such as NXP I.MX RT1170, Alif E3, STMicro STM32H747AI, and Renesas CK-RA8D1. The Edge Impulse platform allows users to provide their own custom data with GPU-trained NVIDIA TAO models such as YOLO and RetinaNet, and optimize them for deployment on edge devices with or without AI accelerators. NVIDIA and Edge Impulse claim this new solution enables the deployment of large-scale NVIDIA models to Arm-based devices, and right now the following object detection and image classification tasks are available: RetinaNet, YOLOv3, YOLOv4, SSD, and image classification. You can […]

Posted on by Jean-Luc Aufranc (CNXSoft) - 1 Comment on Sipeed MaixBox M4N AI Box with 43.2 TOPS AXera AX650N SoC can decode/encode up to 32 videos

Sipeed MaixBox M4N AI Box with 43.2 TOPS AXera AX650N SoC can decode/encode up to 32 videos

Sipeed MaixBox M4N AI box

Sipeed MaixBox M4N is an AI box for video analytics and computer vision equipped with an AXera-Pi Pro (AX650N) octa-core Cortex-A55 SoC with a 43.2 TOPS (INT4) or 10.8 TOPS (INT8) AI accelerator and an H.265/H2.64 video encoder/decoder supporting up to 32 1080p30 videos. The AI box is based on the Sipeed Maix-IV motherboard, an upgrade to the Maix-III devkit with an AX620A quad-core Cortex-A7 SoC with a 14.4 TOPS AI accelerator (INT4). It comes with 8GB RAM shared for Linux and the AI accelerator, 32GB eMMC flash and an M.2 SATA socket for storage, two HDMI outputs, two gigabit Ethernet ports, optional WiFi or 4G LTE mini PCIe module, a few USB ports, and RS232 and RS485 interfaces. Sipeed MaixBox M4N specifications: SoC – AXera AX650N CPU – Octa-core Arm Cortex-A55 @ 1.7 GHz with NEON support NPU – 43.2 TOPS @ INT4, 10.8 TOPS @ INT8 with support […]

Posted on by Debashis Das - 2 Comments on Waveshare Jetson Nano powered mini-computer features a sturdy metal case

Waveshare Jetson Nano powered mini-computer features a sturdy metal case

Waveshare Launches Jetson Nano Mini Computer

Waveshare has launched the Jetson Nano Mini Kit A, a mini-computer kit powered by Jetson Nano. This kit features the Jetson Nano Module, a cooling fan, and a WiFi module, all inside a sturdy metal case. The mini-computer is built around Nvidia’s Jetson platform housing the Jetson Nano module and features multiple interfaces, including USB connectors, an Ethernet port, an HDMI port, CSI, GPIO, I2C, and RS485 interfaces. It also has an onboard M.2 B KEY slot for installing either a WiFi or 4G module and is compatible with TensorFlow, and PyTorch which makes it well-suited for various AI applications. Waveshare Mini-Computer Specification: GPU – NVIDIA Maxwell  architecture with 128 NVIDIA CUDA cores CPU – Quad-core ARM Cortex-A57 processor @ 1.43 GHz Memory – 4 GB 64-bit LPDDR4 1600 MHz; 25.6 GB/s bandwidth Storage – 16 GB eMMC 5.1 Flash Storage, microSD Card Slot Display Output – HDMI interface with […]

Posted on by Jean-Luc Aufranc (CNXSoft) - No Comments on Arducam KingKong – A Raspberry Pi CM4-based Edge AI camera with global shutter sensor, Myriad X AI accelerator

Arducam KingKong – A Raspberry Pi CM4-based Edge AI camera with global shutter sensor, Myriad X AI accelerator

Arducam KingKong

ArduCam KingKong is a Smart Edge AI camera based on the Raspberry Pi CM4 and system-on-module based on Intel Myriad X AI accelerator that follows the Raspberry Pi 5-powered Arducam PiINSIGHT camera introduced at the beginning of the year. The new product launch aims to provide a complete Raspberry Pi-based camera rather than an accessory for the Raspberry Pi 4/5. Smart cameras built around the Raspberry Pi CM4 are not new as we previously covered the EDATEC ED-AIC2020 IP67-rated industrial AI Edge camera and the StereoPi v2 stereoscopic camera used to create 3D video and 3D depth maps. The ArduCam KingKong adds another option suitable for computer vision applications with an AR0234 global shutter module, PoE support, and a CNC metal enclosure. ArduCam KingKong specifications: SoM – Raspberry Pi Compute Module 4 (CM4) by default CM4104000 Wireless 4GB RAM Lite (0GB eMMC). AI accelerator – Luxonis OAK SOM BW1099 based on Intel […]