Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 151 for “"Jetson"”.

  1. Umělá inteligence na platrofmě nVIDIA Jetson

    … neuronové sítě ve vestavném zařízení NVIDIA Jetson Nano. V první části práce je popsán současný stav implementace umělé inteligence ve vestavných zařízeních. Následující část popisuje nástroje pro vývoj umělých neuronových sítí a možnosti jejich implementace v zařízení. Tyto nástroje jsou …

    brno-tech Repository record for Umělá inteligence na platrofmě nVIDIA Jetson (opens in a new tab)

  2. Propojení procesoru AURIX s platformou NVIDIA Jetson

    … pojednává o základech používání platforem NVIDIA Jetson Nano a AURIX Application Kit, konkrétně typů TC277 TFT a TC224 TFT. Rovněž jsou v ní teoreticky rozebrány některé periferie platforem. Tyto základy jsou nezbytné pro navazující část, která je zaměřena na realizaci sériového komunikačního …

    brno-tech Repository record for Propojení procesoru AURIX s platformou NVIDIA Jetson (opens in a new tab)

  3. Preparing NVIDIA Jetson for Space Applications: Mitigating Radiation Effects

    … καταλληλότητα του εμπορικού υποσυστήματος NVIDIA Jetson Nano για επεξεργασία επί του δορυφόρου σε χαμηλή τροχιά γύρω από τη Γη. Τα φάσματα ροής σωματιδίων για πέντε κυκλικά ύψη από 500 km έως 2000 km υπολογίστηκαν με το λογισμικό OMERE, αποδίδοντας ολικές δόσεις πέντε ετών κάτω από 25 krad …

    athens Repository record for Preparing NVIDIA Jetson for Space Applications: Mitigating Radiation Effects (opens in a new tab)

  4. Performance Bottleneck Evaluation of llama.cpp on Jetson and H100

    … datacenter-class H100 GPU and the edge-oriented Jetson AGX Orin. The study uses Llama 3.1 8B models in BF16, Q8_0, and Q4_K_M formats, and separates inference into prefill and decode phases using controlled single-sequence workloads and concurrent serving experiments. The evaluation first …

    chalmers Repository record for Performance Bottleneck Evaluation of llama.cpp on Jetson and H100 (opens in a new tab)

  5. Astro – A Low-Cost, Low-Power Cluster for CPU-GPU Hybrid Computing Using the Jetson TK1

    … our Astro cluster, which consists of 46 NVIDIA Jetson TK1 nodes each equipped with an ARM Cortex A15 CPU, 192 core Kepler GPU, 2 GB of RAM, and 16 GB of flash storage. The cluster has a number of advantages when compared to conventional clusters including lower power usage, ambient cooling, …

    calpoly Repository record for Astro – A Low-Cost, Low-Power Cluster for CPU-GPU Hybrid Computing Using the Jetson TK1 (opens in a new tab)

  6. ONBOARD SHIP CLASSIFICATION FOR MARITIME SURVEILLANCE: BENCHMARKING CONVOLUTIONAL NEURAL NETWORK-BASED TRANSFER LEARNING ON THE NVIDIA JETSON ORIN NANO 8GB

    … ship classification pipeline on the NVIDIA Jetson Orin Nano 8GB onboard computing module of the Naval Postgraduate School (NPS) Space Program’s forthcoming satellite. Two pretrained convolutional neural network architectures, ResNet-50 and EfficientNet-B0, are fine-tuned on the …

    nps Repository record for ONBOARD SHIP CLASSIFICATION FOR MARITIME SURVEILLANCE: BENCHMARKING CONVOLUTIONAL NEURAL NETWORK-BASED TRANSFER LEARNING ON THE NVIDIA JETSON ORIN NANO 8GB (opens in a new tab)

  7. Generování kódu pro zpracování surového obrazu na grafickém zařízení

    … Matlab GPU Coder na grafické zařízení Nvidia Jetson Nano a zpracování hloubkových obrazových dat z Intel RealSence kamery takto vygenerovanými funkcemi. Teoretická část je věnována seznámení s CUDA code, Intel RealSence D415, Jetson Nano a Matlab GPU Coder. Praktická část práce je zaměřena na …

    brno-tech Repository record for Generování kódu pro zpracování surového obrazu na grafickém zařízení (opens in a new tab)

  8. Improved Navigation for Social Robots Through OS and Sensor Augmentation

    … Kameli 2022). However, the Pepper robot and the Jetson Nano were unable to communicate gracefully due to issues with time synchronization and inaccurate navigation. As such we looked into two solutions to solve this issue. An early solution explored removing the Nvidia Jetson Nano, but due to …

    umn Repository record for Improved Navigation for Social Robots Through OS and Sensor Augmentation (opens in a new tab)

  9. Dissecting the Performance of AI Applications Using NVIDIA GPUs at the Edge

    … an object detection AI application on two NVIDIA Jetson edge computing devices. Specifically, both AI training and inference phases are evaluated against different settings that can impact application performance. The main contribution of this thesis is to provide experimental evidence on …

    athens Repository record for Dissecting the Performance of AI Applications Using NVIDIA GPUs at the Edge (opens in a new tab)

  10. Implementace algoritmu hlubokého učení na embedded platformě

    … jsou podle výsledků vybrány pro implementaci Jetson Nano a Raspberry Pi. Dále je vytvořen vlastní dataset s třídami pro detekci bonbonů Maoam a na jeho základě potom vytrénován pomocí transfer learning inferenční model. Ten je potom použit při sestavení vlastní aplikace na detekci objektů, …

    brno-tech Repository record for Implementace algoritmu hlubokého učení na embedded platformě (opens in a new tab)

  11. Towards variability-aware frequency scaling on heterogeneous edge platforms

    … heterogeneous Edge platforms (e.g., NVIDIA Jetson platform) incorporate several architectural innovations. One that stands out is the wide frequency configuration space (more than a dozen frequency levels per processing unit spanning a 10x max-min ratio). We postulate that this can be …

    ubc Repository record for Towards variability-aware frequency scaling on heterogeneous edge platforms (opens in a new tab) Download PDF for Towards variability-aware frequency scaling on heterogeneous edge platforms (opens in a new tab)

  12. Cyber Security Related to Agricultural Data Encryption Using Edge Computing Devices

    … lengths of 128 bits was implemented on NVIDIA Jetson Nano and Jetson Xavier NX devices using high-resolution soybean field imagery. The system was evaluated across multiple frame rates using statistical, differential, and performance metrics, including mean squared error, peak signal-to-noise …

    sdstate Repository record for Cyber Security Related to Agricultural Data Encryption Using Edge Computing Devices (opens in a new tab)

  13. Desarrollo de un análisis comparativo de desempeño computacional entre Nvidia Jetson Nano y el Raspberry Pi CM4, en el contexto de clasificación de frutas mediante algoritmos basados en Máquinas de Soporte Vectorial (SVM) y Redes Neuronales Convolucionales (CNN)

    … de dos Single Board Computers (SBCs), el Nvidia Jetson Nano y el Raspberry Pi CM4, en el contexto de clasificación de frutas mediante algoritmos basados en SVM y CNN. Dada la creciente demanda de sistemas de clasificación en el sector agroindustrial, se implementaron estos algoritmos de …

    upc-peru Repository record for Desarrollo de un análisis comparativo de desempeño computacional entre Nvidia Jetson Nano y el Raspberry Pi CM4, en el contexto de clasificación de frutas mediante algoritmos basados en Máquinas de Soporte Vectorial (SVM) y Redes Neuronales Convolucionales (CNN) (opens in a new tab)

  14. Implementation of a Scale Semi-autonomous Platoon to Test Control Theory Attacks

    … Our 1/10 scale car leverages an Nvidia Jetson, embedded microcontroller, and sensors. The Jetson manages the computer vision, networking, control logic, and overall system control; the embedded microcontroller directly controls the car. A lidar module is responsible for recording …

    calpoly Repository record for Implementation of a Scale Semi-autonomous Platoon to Test Control Theory Attacks (opens in a new tab)

  15. Deep learning in edge: evaluation of models and frameworks in ARM architecture

    … development in boards such as NVIDIA TK1, NVIDIA Jetson TX1, and NVIDIA TX2, perhaps it finally be came feasible to study and perform more challenging parallel and distributed workloads directly on a RISC-based architecture. On the other hand, the novelty of this technology poses a fundamental …

    brazil-ufrgs Repository record for Deep learning in edge: evaluation of models and frameworks in ARM architecture (opens in a new tab)

  16. Study of Implementation of CNN on Low-power Platform for Smart Traffic Optimization

    … real-time CNN implementation on ARM platform and Jetson TX1 embedded system, which reveals the shortage of computational resource on ARM platform and the potential of Jetson series to become the low-power platform for CNN implementation.

    waterloo Repository record for Study of Implementation of CNN on Low-power Platform for Smart Traffic Optimization (opens in a new tab)

  17. A Joint Model Provisioning and Request Dispatch Solution for Mobile Inference Serving at the Edge

    … on a cluster of edge nodes, including Nvidia Jetson Nano and Jetson Xavier. We further demonstrate the proposed solution’s effectiveness in reducing the overall inference latency under various system parameters and practical system settings through simulation and testbed experiments, …

    washington Repository record for A Joint Model Provisioning and Request Dispatch Solution for Mobile Inference Serving at the Edge (opens in a new tab)

  18. Hybrid Compression: Exploiting Model and Data Compression for Deep Neural Network Workloads

    … of compressed model on two edge devices, Nvidia Jetson Nano and Nvidia Jetson Xavier NX. We find that the gains of hybrid compression are hardware related and NX shows more impressive strengths than Nano. At last, we give users recommendations about how to apply the hybrid compression from …

    chalmers Repository record for Hybrid Compression: Exploiting Model and Data Compression for Deep Neural Network Workloads (opens in a new tab)

  19. Detekce dopravních značek v reálném čase

    … byla testována na jednodeskovém počítači Nvidia Jetson Nano.

    brno-tech Repository record for Detekce dopravních značek v reálném čase (opens in a new tab)

  20. Detekce a klasifikace objektů zájmu zalévacího robotu zpracováním obrazu

    … robotu s využitím embedded počítače NVIDIA Jetson Nano. Vybrána a aplikována byla metoda pro detekci objektů YOLOv5, která sloužila k detekci květin a květináčů. Pomocí metody pro monokulární predikci MiDaS byla predikována relativní hloubková mapa. Vytvořen byl algoritmus, který pomocí dat …

    brno-tech Repository record for Detekce a klasifikace objektů zájmu zalévacího robotu zpracováním obrazu (opens in a new tab)

Page 1 of 8