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 […]

NVIDIA Introduces Jetson Xavier Devkit and Isaac Robotics Software

NVIDIA Jetson Xavier

NVIDIA Xavier was first unveiled in September 2016 as an artificial intelligence SoC with eight NVIDIA Custom 64-bit Arm cores, a 512-core Volta GPU,  8K video encoding and decoding, and a computer vision accelerator (CVA) now called NVDLA (NVIDIA Deep Learning Accelerator). Earlier this year, the company announced Xavier was sampling,  and DRIVE IX & DRIVE AR SDKs for the automotive market. On the eve of Computer 2018, NVIDIA has introduced Jetson Xavier development kit, as well as Isaac robotics software for autonomous machines. Jetson Xavier key specifications: SoC – NVIDIA Xavier with 8-core ARMv8.2 64-bit CPU, 8MB L2 + 4MB L3 512-core Volta GPU with Tensor Cores 2x NVDLA engines for deep learning 7-way VLIW Processor for vision acceleration VPU with dual 4Kp60 video decoding and encoding System Memory – 16GB 256-bit LPDDR4x | 137 GB/s Storage – 32GB eMMC 5.1 flash Display – 3x eDP/DP/HDMI at 4Kp60 | […]

FFmpeg 3.1 adds support for OpenMAX encoding on Raspberry Pi, VA-API H.264 & H.265 Encoding, and more

FFmpeg is an open source multimedia framework used by many open source, as well as closed source, projects to handle audio and video containers parsing, hardware or software video decoding / encoding, and more. I also used it a few months ago to test H.265 hardware encoding with an Nvidia GPU using the development branch, but the developers have now released FFmpeg 3.1 “Laplace”, so it’s possible to use a stable release to perform H.265 hardware encoding. Some of the most noticeable features of the new version include: Generic OpenMAX IL H.264 & MPEG4 encoders for Raspberry Pi VA-API accelerated H.264/HEVC/MJPEG encoding VAAPI-accelerated format conversion and scaling Native Android MediaCodec API H.264 decoding CUDA (CUVID) HEVC & H.264 decoders CUDA accelerated format conversion and scaling DXVA2 accelerated HEVC Main10 decoding on Windows Many new muxers/demuxers A variety of new filters The complete list of changes for FFmpeg 3.1 can be […]

Autonomous Deep Learning Robot Features Nvidia Jetson TK1 Board, a 3D Camera, and More

Autonomous, a US company that makes smart products such as smart desks, virtual reality kits and autonomous robots, has recently introduced a deep learning robot that comes with a 3D camera, speaker and microphone, Jetson TK1 board, and a mobile base. The robot appears to be mostly made of the shelves parts: 3D Depth camera – Asus Xtion Pro 3D Depth Camera Speaker & Microphone Nvidia Jetson TK1 PM375 board – Nvidia Terra K1 quad-core Cortex A15 processor @ 2.3 GHz with a 192-core Kepler GPU, 2GB RAM, 16 GB flash Kobuki Mobile Base –  Kobuki is the best mobile base designed for education and research on state of the art robotics. Kobuki provides power supplies for external computer power as well as additional sensors and actuators. Its highly accurate odometry, amended by calibrated gyroscope, enables precise navigation. The robot is designed for research in deep learning and mobile robotics, […]

Nvidia to Give Away 50 Jetson TK1 Development Boards

Nvidia Jetson TK1 is a development board powered by Tegra K1 quad core Cortex A15 SoC including a 192-core Kepler GPU. This is one the the best, if not the best, ARM platform when it comes to GPU performance, GPGPU capabilities, and the only one I know of that supports OpenGL 4.4 “Desktop”, as well as Nvidia’s CUDA 6.0. You can buy the board for $192, but if you are a developer and have a project that could leverage and showcase Tegra K1 capabilities for computer vision solutions for robotics, medical devices, military, and automotive applications, you may well get one board for free via Nvidia’s Tegra K1 CUDA Vision Challenge. To apply, you need to submit your proposal via Nvidia’s TK1 vision challenge page by April 30, 2014. Please note, the contest is only open to US residents. The company will then consider the various proposals based on innovativeness, […]

$192 Nvidia Jetson TK1 Development Board with Tegra K1 Quad Core Cortex A15 SoC

Nvidia has just unveiled Jetson TK1 development kit powered by their 32-bit Tegra K1 quad core Cortex A15 processor with a 192-core Kepler GPU. This board targets computer-vision applications for robotics, medical, avionics, and automotive industries that can leverage the compute capabilities of the Kepler GPU. Jetson TK1 devkit specifications: SoC – Nvidia Tegra K1 SoC with 4-Plus-1 quad-core ARM Cortex A15 CPU, and Kepler GPU with 192 CUDA cores (Model T124) System Memory – 2 GB x16 memory with 64 bit width Storage – 16 GB 4.51 eMMC memory, SATA data + power ports, full size SD/MMC slot, and 4MB SPI boot flash. Video Output – HDMI port Audio – ALC5639 Realtek Audio codec with Mic in and Line out Connectivity – RTL8111GS Realtek GigE LAN USB – 1x USB 2.0 OTG port, micro AB, 1x USB 3.0 port, A Debugging – RS232 serial port, JTAG Expansion 1x Half […]

SECO mITX GPU DevKit Features Nvidia Tegra 3, Supports CUDA 5

SECO mITX GPU DEVKIT is a GPU computing development kit that provides a Mini-ITX Qseven 2.0 carrier board (SECO mITX Carrier Board) with a Nvidia Tegra 3 powered Qseven SoM (QuadMo747-X/T30). The carrier board provides a PCI-e x16 connector (PCI Express x4) intended to allow the connection of CUDA 5 enabled desktop graphics boards. Embedded Control Europe reports that the platform will support Nvidia Kayla platform. The main specifications of the platform are as follows: CPU – Nvidia Tegra 3 Quad-Core ARM Cortex A9 GPU – TBD. But you should be able to insert Nvidia graphics card via the PCI-e x16 connector (PCI Express x4) on the mini-ITX board Memory – 2 GB Storage – 4 GB eMMC + 1x SATA 2.0 Connector Network – 1x Gigabit Ethernet USB – 3x USB 2.0 + 1 OTG port Display – HDMI The platform will support Linux Ubuntu , as well as […]

Nvidia Updates its Tegra Roadmap with Parker 64-Bit ARM SoC, Unveils Kayla CUDA Development Platform

Nvidia has given an update about the roadmap for its Tegra processor at the GPU Technology Conference in San Jose, California. Tegra 4 will still be followed by Logan (Tegra 5) as planned with a Kepler GPU and support for CUDA and OpenGL 4.3, but “Stark” has been replaced by “Parker” (Tegra 6) which will be the first 64-Bit Tegra processor based on Denver CPU, Maxwell GPU and make use of Finfet transistors. Logan will be available in 2014, and Parker should be available in 2015 with 100 times more performance than Tegra 2. With this kind of performance, the separation line between desktop and mobile processors will be gone. Nvidia also unveiled Kayla (“Logan’s girlfriend”), a development platform for CUDA and OpenGL based on Tegra 3 quad-core ARM processor and a Kepler GPU connected via a PCI express slot. Jen-Hsun Huang (above) showcased Kayla performance by running real-time ray […]

Memfault IoT and embedded debugging platform