This repository contains a collection of projects focused on implementing various deep learning models and algorithms on FPGA. These projects leverage the power of FPGA for efficient and high-performance execution of machine learning tasks. Below is a brief overview of each project included in this repository.
In this project, a Convolutional Neural Network (CNN) is implemented on FPGA for image classification tasks using the CIFAR-10 dataset. The project explores the design and optimization of CNNs to achieve high accuracy and performance on FPGA hardware.
This project demonstrates the implementation of the ResNet-18 architecture on both GPU and FPGA. The goal is to compare the performance and efficiency of the two hardware platforms when classifying images from the ImageNet dataset.
A distributed neural network implementation leveraging systolic arrays on FPGA is presented in this project. The use of systolic arrays aims to enhance the parallel processing capabilities and improve the throughput of neural network computations on FPGA.
This project focuses on real-time motion detection by utilizing deep learning algorithms implemented on FPGA. The project aims to achieve low-latency and high-accuracy motion detection suitable for various real-time applications.
In this project, a neural genetic algorithm is implemented on FPGA for scheduling tasks. The project explores the combination of neural networks and genetic algorithms to create an efficient and adaptive scheduler on FPGA hardware.
This repository is licensed under the Apache License 2.0. See the LICENSE file for more details.
- VHDL/Verilog knowledge
- Basic understanding of FPGA design and implementation
- Familiarity with deep learning concepts and frameworks
-
Clone the repository:
git clone https://github.com/Awrsha/FPGA-Programming.git cd FPGA-Programming
-
Follow the instructions in each project directory for specific setup and implementation details.
Contributions are welcome! Please read the CONTRIBUTING file for guidelines on how to contribute to this project.
- Thanks to all the contributors who have worked on these projects.
- Special thanks to the open-source community for providing valuable tools and resources.
For any questions or inquiries, please contact the repository owner at [official.parvizi@gmail.com].