Sökning: "tensorflow"

Visar resultat 1 - 5 av 54 uppsatser innehållade ordet tensorflow.

  1. 1. Region Proposal Based Object Detectors Integrated With an Extended Kalman Filter for a Robust Detect-Tracking Algorithm

    Master-uppsats, Karlstads universitet/Fakulteten för hälsa, natur- och teknikvetenskap (from 2013)

    Författare :Gabriel Khajo; [2019]
    Nyckelord :Object Detection; Extended Kalman Filter; Tracking;

    Sammanfattning : In this thesis we present a detect-tracking algorithm (see figure 3.1) that combines the detection robustness of static region proposal based object detectors, like the faster region convolutional neural network (R-CNN) and the region-based fully convolutional networks (R-FCN) model, with the tracking prediction strength of extended Kalman filters, by using, what we have called, a translating and non-rigid user input region of interest (RoI-) mapping. LÄS MER

  2. 2. Identifiera löv i skogar – Att lära en dator känna igen löv med ImageAI

    Kandidat-uppsats, Mittuniversitetet/Institutionen för informationssystem och –teknologi

    Författare :My Nordqvist; [2019]
    Nyckelord :SCA; Machine learning; Neural networks; Deep learning; Forest classification; Leaf; Orthophoto; Python; TensorFlow; ImageAI; SCA; Maskininlärning; Neurala nätverk; Djuplärning; Klassificering av skog; Löv; Ortofoton; Python; TensorFlow; ImageAI;

    Sammanfattning : A current field of research today is machine learning because it can simplify everyday life for human beings. A functioning system that has learned specific tasks can make it easier for companies in both cost and time. A company who want to use machine learning is SCA, who owns and manages forests to produce products. LÄS MER

  3. 3. Machine visual feedback through CNN detectors : Mobile object detection for industrial application

    Uppsats för yrkesexamina på avancerad nivå, Mittuniversitetet/Institutionen för elektronikkonstruktion

    Författare :Kastriot Rexhaj; [2019]
    Nyckelord :Object detection; CNN; SSD; Faster R-CNN; YOLO; TensorFlow; ARM; Android; Deep learning; Machine vision.;

    Sammanfattning : This paper concerns itself with object detection as a possible solution to Valmet’s quest for a visual-feedback system that can help operators and other personnel to more easily interact with their machines and equipment. New advancements in deep learning, specifically CNN models, have been exploring neural networks with detection-capabilities. LÄS MER

  4. 4. Ablation Programming for Machine Learning

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

    Författare :Sina Sheikholeslami; [2019]
    Nyckelord :Distributed Machine Learning; Distributed Systems; Ablation Studies; Apache Spark; Keras; Hopsworks;

    Sammanfattning : As machine learning systems are being used in an increasing number of applications from analysis of satellite sensory data and health-care analytics to smart virtual assistants and self-driving cars they are also becoming more and more complex. This means that more time and computing resources are needed in order to train the models and the number of design choices and hyperparameters will increase as well. LÄS MER

  5. 5. Memory Efficient Semantic Segmentation for Embedded Systems

    Master-uppsats, Lunds universitet/Institutionen för datavetenskap

    Författare :Haochen Liu; Erik Olsson; [2019]
    Nyckelord :Neural networks; Semantic segmentation; Pruning; Quantization; Tiling; Memory allocation; DeepLab; MobileNet; Technology and Engineering;

    Sammanfattning : Convolutional neural networks (CNNs) have made rapid progress in the last years and in fields, such as computer vision, they are considered state-of-the-art. However, CNNs are very computationally intensive. This makes them challenging to use in embedded devices such as smartphones, security cameras and cars. LÄS MER