|
|
Deep Neural Networks: Embedded System Implementation
Matěj, Aleš ; Šimek, Václav (referee) ; Mrázek, Vojtěch (advisor)
The goal of this thesis is to firstly design and implement an application for embeddedsystems which will classify MNIST numbers and secondly optimize energy and memoryrequirements of this network. The basics of neural networks, Cortex-M processor cores andembedded devices are described in the theoretical part. Followed by implementation details.Networks learning is done with Python and Theano library on a PC. The network is thenconverted to C for a board STM32F429 Discovery. Last part consist of network optimization,which focuses on convolution, dot product and number representation of weights and biasesof the network.
|
|
|
Sketchup Woodworking Plugin
Matěj, Aleš ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
Main goals of this work are to understand the SketchUp application, learn the basic tasks of fiberboard furniture design and the design and implementation of tools, which should increase efficacy of these tasks. Tools are created as plug-ins for SketchUp using its Ruby API. The text it self is focused on fundamentals of 3D computer graphics and use of them in SkechtUp, fiberboard furniture design processes and the woodworking plug-in it self. Described tools are used for creation of board models, their management through user interface and generation of edging for boards.
|
|
|
Deep Neural Networks: Embedded System Implementation
Matěj, Aleš ; Šimek, Václav (referee) ; Mrázek, Vojtěch (advisor)
The goal of this thesis is to firstly design and implement an application for embeddedsystems which will classify MNIST numbers and secondly optimize energy and memoryrequirements of this network. The basics of neural networks, Cortex-M processor cores andembedded devices are described in the theoretical part. Followed by implementation details.Networks learning is done with Python and Theano library on a PC. The network is thenconverted to C for a board STM32F429 Discovery. Last part consist of network optimization,which focuses on convolution, dot product and number representation of weights and biasesof the network.
|
|
|
Sketchup Woodworking Plugin
Matěj, Aleš ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
Main goals of this work are to understand the SketchUp application, learn the basic tasks of fiberboard furniture design and the design and implementation of tools, which should increase efficacy of these tasks. Tools are created as plug-ins for SketchUp using its Ruby API. The text it self is focused on fundamentals of 3D computer graphics and use of them in SkechtUp, fiberboard furniture design processes and the woodworking plug-in it self. Described tools are used for creation of board models, their management through user interface and generation of edging for boards.
|
guest ::
