tensorflow News - Page 4 of 13 - CNX Software

July 27, 2022 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

mini PCIe module features Rockchip RK1808K SoC with 3.0 TOPS NPU

Toybrick RK1808 mPCIe AI accelerator card

Rockchip RK1808 SoC with a built-in 3.0 TOPS AI accelerator has been around since 2019, and we’ve seen it in USB compute sticks, SBCs, and even in Pine64 SoEdge-RK1808 SO-DIMM module, but somehow never in the more widely used M.2 or mPCIe form factors. Toybrick TB-RK1808M0 changes that and offers Rockchip RK1808K SoC coupled with 1GB RAM and an 8GB eMMC flash in a mini PCIe module that exposes USB 3.0, USB 2.0, UART, and GPIO signals. Toybrick TB-RK1808M0 specifications: SoC – Rockchip RK1808K CPU – Dual-core Cortex-A35 processor @ up to 1.4 GHz AI Accelerator – 3.0 TOPS NPU for INT8 inference (300 GOPS for INT16, 100 GFLOPS for FP16) VPU – 1080p60 H.264 decode, 1080p30 H.264 encode System Memory – 1GB DDR Storage – 8GB eMMC flash Host interface – Mini PCIe edge connector with USB 3.0, USB 2.0, UART, and GPIO Misc – Heatsink for cooling Supply […]

May 6, 2022 by Jean-Luc Aufranc (CNXSoft) - 7 Comments

Allwinner V853 Arm Cortex-A7 + RISC-V SoC comes with 1 TOPS NPU for AI Vision applications

Allwinner V853 SoC combines an Arm Cortex-A7 core with a Xuantie E907 RISC-V core, and a 1 TOPS NPU for cost-sensitive AI Vision applications such as smart door locks, smart access control, AI webcams, tachographs, and smart desk lamps. Manufactured with a 22nm process, the SoC comes with an ISP image processor and Allwinner Smart video engine capable of up to 5M @ 30fps H.265/H.264 encoding and 5M @ 25fps H.264 decoding, offers parallel CSI and MIPI CSI camera interfaces, and well as MIPI DSI and RGB display interfaces. Allwinner V853 specifications: CPU Arm Cortex-A7 CPU core @ 1 GHz with 32 KB I-cache, 32 KB D-cache, and 128 KB L2 cache Alibaba Xuantie E907 RISC-V core with 16 KB I-cache and 16 KB D-cache NPU (Neural network Processing Unit) – Up to 1 TOPS for V853 and 0.8 TOPS for V853S, embedded 128KB internal buffer, support for TensorFlow, Caffe, […]

April 22, 2022April 28, 2022 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

reServer Jetson-50-1-H4 is an AI Edge server powered by NVIDIA Jetson AGX Orin 64GB

Jetson AGX Orin 64GB AI inference server

reServer Jetson-50-1-H4 is an AI inference edge server powered by Jetson AGX Orin 64GB with up to 275 TOPS of AI performance, and based on the same form factor as Seeed Studio’s reServer 2-bay multimedia NAS introduced last year with an Intel Core Tiger Lake single board computer. The 12-core Arm server comes with 32GB LPDDR5, a 256GB NVMe SSD pre-loaded with the Jetpack SDK and the open-source Triton Inference server, two SATA bays for 2.5-inch and 3.5-inch drives, up to 10 Gbps Ethernet, dual 8K video output via HDMI and DisplayPort, USB 3.2 ports, and more. reServer Jetson-50-1-H4 (preliminary) specifications: SoM – Jetson AGX Orin module with CPU – 12-core Arm Cortex-A78AE v8.2 64-bit processor with 3MB L2 + 6MB L3 cache GPU / AI accelerators NVIDIA Ampere architecture with 2048 NVIDIA CUDA cores and 64 Tensor Cores @ 1.3 GHz DL Accelerator – 2x NVDLA v2.0 Vision Accelerator […]

February 26, 2022February 26, 2022 by Jean-Luc Aufranc (CNXSoft) - 2 Comments

Codasip L31 and L11 RISC-V cores for AI/ML support TFLite Micro, customizations

Codasip has announced the L31 and L11 low-power embedded RISC-V processor cores optimized for customization of AI/ML IoT edge applications with power and size constraints. The company further explains the new L31/L11 RISC-V cores can run Google’s TensorFlow Lite for Microcontrollers (TFLite Micro) and can be optimized for specific applications through Codasip Studio RISC-V design tools. As I understand it, this can be done by the customers themselves thanks to a full architecture license as stated by Codasip CTO, Zdeněk Přikryl: Licensing the CodAL description of a RISC-V core gives Codasip customers a full architecture license enabling both the ISA and microarchitecture to be customized. The new L11/31 cores make it even easier to add features our customers were asking for, such as edge AI, into the smallest, lowest power embedded processor designs. The ability to customize the cores is important for AI and ML applications since the data types, […]

January 21, 2022February 25, 2024 by Jean-Luc Aufranc (CNXSoft) - No Comments

$499 BrainChip AKD1000 PCIe board enables AI inference and training at the edge

BrainChip has announced the availability of the Akida AKD1000 (mini) PCIe boards based on the company’s neuromorphic processor of the same name and relying on spiking neural networks (SNN) which to deliver real-time inference in a way that is much more efficient than “traditional” AI chips based on CNN (convolutional neural network) technology. The mini PCIe card was previously found in development kits based on Raspberry Pi or an Intel (x86) mini PC to let partners, large enterprises, and OEMs evaluate the Akida AKD1000 chip. The news is today is simply that the card can easily be purchased in single units or quantities for integration into third-party products. BrainChip AKD1000 PCIe card specifications: AI accelerator – Akida AKD1000 with Arm Cortex-M4 real-time core @ 300MHz System Memory – 256Mbit x 16 bytes LPDDR4 SDRAM @ 2400MT/s Storage – Quad SPI 128Mb NOR flash @ 12.5MHz Host interface – 5GT/s PCI […]

January 7, 2022January 25, 2022 by Jean-Luc Aufranc (CNXSoft) - 6 Comments

Horizon X3 AI development board is powered by Sunrise 3 AI Edge Arm processor

Horizon X3 AI development board is powered by Horizon Robotics Sunrise 3 (aka X3) quad-core Cortex-A53 processor with a 5 TOPS NPU, and multiple camera support with the chip apparently designed for the automotive industry. [Update January 25, 2022: A third-party company, Finsbury Glover Hering, claiming to represent Horizon Robotics informed CNX Software the chip is not designed for the automotive market, and that Horizon’s AIoT business is actually limited to the domestic China market and not overseas.] The devkit is comprised of a Sunrise 3 system-on-module with 1GB LPDDR4 & 16GB EMMC memory, as well as a baseboard with Gigabit Ethernet and WiFi, HDMI up to 1080p60 and MIPI DSI interface, a camera interface, and a 40-pin header for expansion. Horizon X3 AI development board specifications: SoC – Horizon Robotics Sunrise 3 quad-core Cortex-A53 processor @ 1.2 GHz, one Cortex-R5 core, a 5 TOPS NPU (2x “Bernoulli” BPU) System […]

December 2, 2021 by Jean-Luc Aufranc (CNXSoft) - 5 Comments

Seeed XIAO BLE – A tiny nRF52840 Bluetooth 5.0 board with (optional) IMU sensor and microphone

Seeed Studio has just introduced two new members to their XIAO board family with the Seeed XIAO BLE and XIAO BLE Sense boards equipped with Nordic Semi nRF52840 Bluetooth 5.0 microcontroller, as well as an IMU sensor and microphone on the “Sense” model. Just like the earlier XIAO RP2040 board, the tiny Seed XIAO BLE board can be programmed with Arduino, MicroPython, and CircuityPython, and offers two headers with 7-pin each for GPIOs. What’s really new is the wireless connectivity, the sensors, and a battery charging circuitry. Seeed XIAO BLE specifications: Wireless MCU – Nordic nRF52840 Arm Cortex-M4F microcontroller @ up to 64 MHz with 1 MB flash, 256 KB SRAM, Bluetooth 5.0, NFC, Zigbee connectivity Storage – 2 MB QSPI flash Expansion I/Os 2x 7-pin headers with 1x UART, 1x I2C, 1x SPI, 1x NFC, 1x SWD, 11x GPIO (PWM), 6x ADC 3.3V I/O voltage (not 5V tolerant) Sensors […]

November 30, 2021June 8, 2022 by Sponsored Post - No Comments

Download a free trial of the SoftNeuro Deep Learning SDK for Intel and Arm targets (Sponsored)

Jetson Xavier Tensorflow Lite vs SoftNeuro

Morpho, a global research & development company established in Japan in 2004 and specialized in imaging technology, is now offering a free trial for the SoftNeuro deep learning SDK working on Intel processors with AVX2 SIMD extensions, 64-bit Arm targets, while also leveraging OpenCL and/or CUDA. Some of the advantages of SoftNeuro are that the framework is easy to use even for those without any knowledge about deep learning, it’s fast thanks to the separation of the layers and their execution patterns, and it can run on several different hardware and OS being cross-platform. SoftNeuro relies on its own storage format (DNN format) to deliver the above advantages. But you can still use models trained with any mainstream deep learning framework. TensorFlow and Keras models can be directly converted to the DNN format, while models from other frameworks can be converted first to the ONNX format and then to the […]