Sökning: "Constrained optimization"

Visar resultat 1 - 5 av 77 uppsatser innehållade orden Constrained optimization.

  1. 1. Exploring the Depth-Performance Trade-Off : Applying Torch Pruning to YOLOv8 Models for Semantic Segmentation Tasks

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Xinchen Wang; [2024]
    Nyckelord :Deep Learning; Semantic segmentation; Network optimization; Network pruning; Torch Pruning; YOLOv8; Network Depth; Djup lärning; Semantisk segmentering; Nätverksoptimering; Nätverksbeskärning; Fackelbeskärning; YOLOv8; Nätverksdjup;

    Sammanfattning : In order to comprehend the environments from different aspects, a large variety of computer vision methods are developed to detect objects, classify objects or even segment them semantically. Semantic segmentation is growing in significance due to its broad applications in fields such as robotics, environmental understanding for virtual or augmented reality, and autonomous driving. LÄS MER

  3. 2. LP_MQTT - A Low-Power IoT Messaging Protocol Based on MQTT Standard

    Master-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Anchu Antony; Deepthi Myladi Kelambath; [2024]
    Nyckelord :;

    Sammanfattning : In the Internet of Things (IoT) era, the MQTT Protocol played a bigpart in increasing the flow of uninterrupted communication betweenconnected devices. With its functioning being on the publish/subscribe messaging system and having a central broker framework, MQTTconsidering its lightweight functionality, played a very vital role inIoT connectivity. LÄS MER

  4. 3. The Impact of Deep Neural Network Pruning on the Hyperparameter Performance Space: An Empirical Study

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Jonna Matthiesen; [2023-10-24]
    Nyckelord :Compression; Deep Learning; DNN; Hyperparameters; Optimization; Pruning; Hyperparameter Optimisation; Hyperparameter Tuning;

    Sammanfattning : With the continued growth of deep learning models in terms of size and computational requirements, the need for efficient models for deployment on resource-constrained devices becomes crucial. Structured pruning has emerged as a proven method to speed up models and reduce computational requirements. LÄS MER

  5. 4. Construction and evaluation of a lossless image format, Carbonara

    Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Viktor Rösler; [2023]
    Nyckelord :Data Compression; Image Compression; Image Format; Software Development;

    Sammanfattning : High-speed laser triangulation 3D cameras, such as the Ranger3 from SICK, transmit image data to a PC for processing. The camera’s operational speed is constrained by the capabilities of the transmission link. By compressing the data, the bandwidth requirements of the camera is reduced. LÄS MER

  7. 5. Optimizing Realistic 3D Facial Models for VR Avatars through Mesh Simplification

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Beiqian Liu; [2023]
    Nyckelord :Mesh Simplification; Virtual Reality; Realistic Avatars; 3D Face Reconstruction;

    Sammanfattning : The use of realistic 3D avatars in Virtual Reality (VR) has gained significant traction in applications such as telecommunication and gaming, offering immersive experiences and face-to-face interactions. However, standalone VR devices often face limitations in computational resources and real-time rendering requirements, necessitating the optimization of 3D models through mesh simplification to enhance performance and ensure a smooth user experience. LÄS MER