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 11 of 11 for “"Tensor flow"”.
-
A Strict Physicality-Preserving Scheme for a 2D Q-Tensor Flow with a Singular Potential
… behavior, mathematical frameworks such as the Q-tensor model are used to describe the orientation and degree of molecular order. In this work, we introduce a numerical scheme for a two-dimensional (2D) dynamic Q-tensor model, which is formulated as an L2-gradient flow driven by the liquid crystal …
-
Incorporation of directionally dependent diffusion with polymer composite flow theory
… is presented, and the fiber orientation tensor flow equations are developed based upon the directional diffusion model. The model satisfies the desired characteristics, both to decrease fiber alignment rates and steady state orientation results at the cost of requiring orientation tensors …
-
Real-Time Finger Spelling American Sign Language Recognition Using Deep Convolutional Neural Networks
… and other supporting libraries like OpenCV, Tensor flow and Dlib to perform various image processing and machine learning tasks. This entire application can be deployed as a web application using Flask to make it operating system independent.
-
Global Ensemble Streamflow and Flood Modeling with Application of Large Data Analytics, Deep learning and GIS
… flood management and decision making. Streamflow and flood forecasting can provide important information for various applications including optimization of water resource allocations, water quality assessment, cost analysis, sustainable design of hydrological infrastructures, improvement in …
-
Cloud-based machine learning architecture for big data analysis
… and special software environments (e.g. tensor flow) have been developed. In addition, for specific applications, special optimisations are often developed based on the requirements of the particular application. This thesis also addresses the challenge of efficiency of machine learning …
-
Improved Deep Learning Model Based on Integrated Convolutional Neural Networks and Transfer Learning for Shoeprint Image Classification
… results. In CNN and CNN-TL methods, python's tensor-flow library was used. Finally, the shoeprint classifications were performed using a pre-trained and fine-tuned version of the Inception model, including comparing different pre-trained Inception V3, VGG16, and ResNet50 models. The results …
-
Simulation of stress dependent fluid flow in naturally fractured reservoirs
… fractures are important contributors to fluid flow. Thus, modeling and simulation of discrete fracture network is essential to assess responses of the reservoirs under stimulation pressure, develop the best hydraulic fracture treatments, carry out feasibility studies, design optimum production …
-
Transparent spatial sharing of multiple and heterogeneous accelerators
… high-level Machine Learning (ML) frameworks like Tensor Flow, PyTorch, and Caffe presents notable challenges across four key aspects: (a) sharing heterogeneous accelerators, (b) al-locating available resources elastically during application execution, (c) providing the required performance for …
-
Blind Image Denoising using Supervised and Unsupervised Learning
Image denoising is an important problem in image processing and computer vision. In real-world applications, denoising is often a pre-processing step (so-called low-level vision task) before image segmentation, object detection, and recognition at higher levels. Traditional image denoising …
-
Detekce významných událostí v systémech využívajících princip fázových OTDR
Diplomová práce se zabývá návrhem, implementací a testováním systému klasifikujícího události snímané optickým vláknem podél perimetru střežených objektů. V teoretické části jsou objasněny fyzikální principy, základní struktury měřících systémů, metody měření, formát dat, způsoby předzpracování a …
-
Rozpoznání květin v obraze
Tato práce se zabývá rozpoznáváním květin v obraze a klasifikaci do tříd. Teoretická část je zaměřena na problematiku hlubokých konvolučních neuronových sítí. Praktická část se zabývá popisem mnou vytvořené databáze květin, se kterou je dále pracováno. Databáze obsahuje celkem 13000 fotek rostlin …