Sökning: "map inference"

Visar resultat 11 - 15 av 36 uppsatser innehållade orden map inference.

  1. 11. Real-time video Bokeh

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Jerker Kanon; [2022]
    Nyckelord :Convolutional neural network; bokeh; video segmentation; image processing;

    Sammanfattning : Bokeh is defined as a soft out of focus blur. An image with bokeh has a subject in focus and an artistically blurry background. To capture images with real bokeh, specific camera parameter choices need to be made. One essential choice is to use a big lens with a wide aperture. LÄS MER

  2. 12. Mapping quantized convolutional layers on the SiLago platform

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

    Författare :Yue Zhang; [2022]
    Nyckelord :SiLago; algorithm mapping; quantized neural networks; convolution; SiLago; algoritmkartläggning; kvantiserade neurala nätverk; faltning;

    Sammanfattning : Convolutional neural networks (CNNs) have been utilized in various applications, such as image classification, computer vision, etc. With development, the complexity and computation of CNNs also increase, which requires more memory and resources when deployed on devices, especially embedded systems. LÄS MER

  3. 13. Techniques for Multilingual Document Retrieval for Open-Domain Question Answering : Using hard negatives filtering, binary retrieval and data augmentation

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

    Författare :Carlos Lago Solas; [2022]
    Nyckelord :OpenQA; Multilingual Transformers; Document retrieval; Data augmentation.; OpenQA; Flerspråkiga Transformatorer; Dokumenthämtning; Dataförstärkning.;

    Sammanfattning : Open Domain Question Answering (OpenQA) systems find an answer to a question from a large collection of unstructured documents. In this information era, we have an immense amount of data at our disposal. However, filtering all the content and trying to find the answers to our questions can be too time-consuming and ffdiicult. LÄS MER

  4. 14. 3D Instance Segmentation of Cluttered Scenes : A Comparative Study of 3D Data Representations

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Albin Konradsson; Gustav Bohman; [2021]
    Nyckelord :Deep Learning; Computer Vision; Point Cloud; Depth Map; 3D; Instance Segmentation; Cluttered Scenes;

    Sammanfattning : This thesis provides a comparison between instance segmentation methods using point clouds and depth images. Specifically, their performance on cluttered scenes of irregular objects in an industrial environment is investigated. Recent work by Wang et al. LÄS MER

  5. 15. Automatic Annotation of Models for Object Classification in Real Time Object Detection

    Uppsats för yrkesexamina på avancerad nivå, Luleå tekniska universitet/Institutionen för system- och rymdteknik

    Författare :Tom Hammarkvist; [2021]
    Nyckelord :;

    Sammanfattning : The times of manual labour are changing as automation grows larger and larger by the day. Self-driving vehicles being one of the more well known examples of automation (the vehicles in this thesis being those found in the construction industry), relies on a machine learning network to recognize its surroundings. LÄS MER