|
|
Web Application for Intuitive Composition of Text Filters
Sadílek, Jakub ; Kolář, Martin (referee) ; Herout, Adam (advisor)
The aim of this thesis is to provide intuitive and easy to use tool for advanced text filtration with the option of easy prototyping and tuning, without the necessity to know programming techniques. The basic principle is the choice of text tools and their inserting into the sequence, so called pipeline, which is typical for shell, from which the application draws inspiration. Tools can be also additionally edited or swapped. The application is aimed primarily at users unfamiliar with this principle or at programmers, for whom it is time-efficient to have their text modified this way and afterwards generate equivalent shell expression. Another way of tuning is realized using so called breakpoints, through which it is easy to quickly focus on chosen lines of the text. This way, the application offers functionality in two separated modes, between which the users can switch anytime according to their needs.
|
|
|
Algorithmic Music Composition
Pankuch, Adam ; Beran, Vítězslav (referee) ; Kolář, Martin (advisor)
Cieľom tejto práce je tvorba systému schopného generovať gitarové stopy. Tento problém pozostáva z dvoch hlavných častí: získanie trénovacieho datasetu a trénovanie vhodného deep learning modelu. Prvá časť tohto problému bola vyriešená sériou skriptov, ktoré vyfiltrovali a transformovali sadu skladieb s viacerými hudobnými nástrojmi z Guitar Pro formátu na sadu gitarových stôp vo formáte pianoroll. Druhá časť problému bola vyriešená natrénovaním niekoľkých konvolučných a rekurentných neurónových sietí na vytvorenom datasete gitarových stôp. Gitarové stopy generované týmito sieťami boli navzájom porovnané a ohodnotené. Hoci vygenerované stopy nie sú veľmi harmonické a príjemné na vypočutie, ukázujú, že konvolučné siete sú vhodnejšie na generovanie polyfónnej hudby v porovnaní s inými typmi neurónových sietí.
|
|
|
Mobile App for Making Challenges and Taking Part in Them
Plachý, Tomáš ; Kolář, Martin (referee) ; Herout, Adam (advisor)
This thesis deals with the problematics of designing, implementing and testing of mobile application for operationg systems iOS and Android. The main work of this thesis is development of an application, which allows its users to create challenges and invite their friends to participate in them. Users can also watch the progress of other participants in a challenge, which can give themselve more motivation to complete the challenge. The application was designed and developed with focus on opinions of its users. I have started by developing a prototype in order to find out, which functions do the users find the most crucial. Thereafter I created the first official version, which was subsequently iteratively improved with regard to feedback from testers.
|
|
|
Video Montage on Android
Janska, Miroslav ; Herout, Adam (referee) ; Kolář, Martin (advisor)
The main goal of this thesis is to implement an application enabling video editing on the Android platform. The FFmpeg framework was used in the implementation. It enables manipulation with multimedia content. The application was iteratively improved and adapted to user requirements during implementation. The resulting application allows video cutting, merging several videos, and applying effects. Thanks to the application a potential user can edit recorded videos in a few minutes.
|
|
|
Generating Faces with Generative Adversarial Networks
Konečný, Daniel ; Herout, Adam (referee) ; Kolář, Martin (advisor)
Cílem této práce je generování barevných obrázků obličejů z náhodně určených vysokodimenzionálních vektorů pomocí generativních neuronových sítí. Dále se zabývá analýzou vstupních vektorů na základě příznaků obličejů z nich vygenerovaných. Je provedena implementace generativní neuronové sítě pro generování obrázků ručně psaných číslic, poté dalších dvou sítí pro generování obrázků obličejů. Vygenerované obrázky zobrazují věrohodně vypadající obličeje, lidské oko je však dokáže odlišit od fotek reálných osob. Analýza jednotlivých dimenzí vektorů je provedena pomocí Studentova t-testu. Dále jsou vstupní vektory promítnuty do podprostorů pomocí lineární diskriminační analýzy a jsou nalezeny rozdělovací hranice mezi třídami příznaků. Analýza generovaných dat dokazuje, že ovlivněním vstupního vektoru je možné docílit generování obrázku obličeje s požadovanými příznaky s pravděpodobností až 80 %. Hlavním výsledkem této práce je model generativní neuronové sítě určené pro generování obrázků obličejů. Dalším přínosem je nástroj pro generování obrázků obličejů na základě vybraných příznaků.
|
|
|
Generating training data with neural networks
Ševčík, Pavel ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis was to prepare a training data set for traffic sign detection using generative neural networks. The solution uses a modified U-Net architecture and several experiments with the application of styles using AdaIN layers as in the StyleGAN model have been conducted. By extending the real GTSDB data set with the generated images, mean average precision of 80.36 % has been achieved, which yields an improvement of 19.27 % compared to the mean average precision of the detection model trained on real data only.
|
|
|
Active Learning with Neural Networks
Bureš, Tomáš ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The topic of this thesis in active learning in conjunction with neural networks. First, it deals with theory of active learning and strategies used in real life scenarios. Followed by practical part, experimenting with active learning strategie and evaluating those experiments.
|
|
|
Virtual Waiting Room Data Base Storage
Sadloň, Matej ; Brejcha, Jan (referee) ; Kolář, Martin (advisor)
This thesis is part of project called Virtual Waiting Room. It is a cross-platform application which allows users to book a term with a provider without the need to personally wait in a waiting room. The thesis describes the design and implementation of database, library for work with this database, and a client for the administration of providers and waiting rooms. For this purpose, was used technologies such as MySQL, PHP and HTML.
|
|
|
Deep Neural Networks for Reinforcement Learning in Real-Time Strategy
Barilla, Marco ; Dobeš, Petr (referee) ; Kolář, Martin (advisor)
Machine learning is one of the fastest growing branches of modern science. It is a subfield of artificial intelligence research that is interested the problem of making computers help us solve complex modern problems. Games play an important role in this field because they represent the perfect environment for testing of new approaches and benchmarking against human performance. Starcraft 2 is currently in the spotlight, thanks to its broad playerbase and its complexity. The practical goal of this paper is to create an advantage actor critic agent that is able to operate in the environment of this game.
|
|
|
Convolutional Networks for Historic Text Recognition
Vešelíny, Peter ; Kolář, Martin (referee) ; Kišš, Martin (advisor)
This thesis deals with text line recognition of historical documents. Historical texts dating back to the 17th - 19th centuries are written in fraktur typeface. The character recognition problem is solved using neural network architecture called sequence-to-sequence . This architecture is based on encoder-decoder model and contains attention mechanism. In this thesis a dataset, from texts originated from German archiv called Deutsches Textarchiv , was created. This archive contains 3 897 different German books that have available transcripts and corresponding images of pages. The created dataset was used to train and experiment with the proposed neural network. During the experiments, several convolutional models, hyperparameters and the effects of positional embedding were investigated. The final tool can recognize characters with accuracy 99,63 %. The contribution of this work is the~mentioned dataset and neural network, which can be used to recognize historical documents.
|
guest ::
RSS feed.