Sökning: "Model Compression"

Visar resultat 1 - 5 av 213 uppsatser innehållade orden Model Compression.

1. 1. Test Equipment for the LUCAS Chest Compression System: Incorporating Biomechanical Insights for Future Design Enhancements

   Master-uppsats, Lunds universitet/Avdelningen för Biomedicinsk teknik

   Författare :Ester Pörtfors; Malin Svärdling; [2024]
   Nyckelord :Mechanical CPR; Cardiopulmonary Resuscitation; LUCAS Chest Compression System; Test Equipment; Chest Biomechanics; Chest Stiffness; Technology and Engineering;

   Sammanfattning : The LUCAS Chest Compression System is a market leading mechanical cardiopulmonary resuscitation device, assisting medical professionals worldwide when treating patients with sudden cardiac arrest. The objective of this master thesis project was to develop a new, adjustable test equipment for the LUCAS device, allowing for tests on varying chest heights and stiffness levels. LÄS MER

3. 2. 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

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. Interactive Visualization of Network Models in JavaScript/TypeScript for Web-based Applications

   Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

   Författare :Morrow Erik; [2023]
   Nyckelord :Networks; Information visualization; Information Theory; Interactive visualization; Nätverk; Informationsvisualisering; Informationsteori; Interaktiv visualisering;

   Sammanfattning : Networks of nodes and links are powerful tools to model complex systems, however, when the number of nodes and links grows to the thousands then even the network becomes too complex to comprehend unless we can simplify and highlight the networks underlying structure. The map equation is a method developed by the researchers at IntegratedScience Lab that uses an information theoretic approach to reveal community structure using the flow of information on the network modeled with random walks. LÄS MER

7. 5. Methods for Developing TinyConvolutional Neural Networksfor Deployment on EmbeddedSystems

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Egemen Yiğit Kömürcü; [2023]
   Nyckelord :;

   Sammanfattning : With the recent development in the Deep Learning area, computationally heavy tasks like object detection in images have become easier to compute and take less time to execute with powerful GPUs. Also, when employing sufficiently larger models, these daily tasks are predicted with greater accuracy. LÄS MER