DAT096-NN1

Repository for the DAT096 group project

Table of Contents

1. About The Project
   • Built With
2. Contributors
3. Getting Started
   • Prerequisites
   • Installation
4. Usage
5. Contributing
6. License
7. Acknowledgements

About The Project

This project was developed as part of Chalmers University's DAT096 course during the spring of 2021. It aims to implement a pre-trained image recognition neural network into an FPGA.

Check our sister project at DAT096-NN1_matlab for the neural network implementation in Matlab.

Built With

• Vivado 2019.2

Contributors

Sebastian Bengtsson

Johan Nilsson

Rafael Romón

Chi Zhong

Getting Started

To get a local copy up and running follow these simple steps.

Prerequisites

Vivado version 2019.2 is advised for synthesis and implementation as some of the IP blocks used in this project may change in newer versions of Vivado.

Project Installation

1. Clone the repo

   git clone https://github.com/rafaelromon/DAT096-NN1.git

2. Open Vivado and move into project directory

   cd DAT096-NN1/

3. Generate the project using the .tcl script

   source ./git_project.tcl

Usage

This project is meant to be implemented into a AC701 Evaluation Kit but other boards may be supported as long as they have the same interfaces.

Contributing

This project was developed as part of Chalmers University's DAT096 course during the spring of 2021, as such, there are no plans of further developing this project. Nonetheless, you are more than free to fork this project.

License

Distributed under the MIT License. See LICENSE for more information.

Acknowledgements

• Synective Labs for formulating the project.
• Chalmers University - DAT096 course for supervising the project.