PYNQ FPGA Development with Python Programming & VIVADO
- 3 hours on-demand video
- 4 articles
- 12 downloadable resources
- Full lifetime access
- Access on mobile and TV
- Certificate of Completion
Get your team access to 4,000+ top Udemy courses anytime, anywhere.
Try Udemy for Business- PYNQ Development Flow
- Implementing Face Recognition with PYNQ FPGA
- Image and Video Processing with PYNQ FPGA and Python Library
- Creating Custom Overlay for PYNQ on VIVADO
- Machine Learning Algorithm Implementation on PYNQ
- Installing Tensorflow on PYNQ and Implementing Neural Network on PYNQ
- Python Programming with Jupyter Interface on Internet Browser
- FPGA Design Basics
- Basic of Python Programming
- PYNQ FPGA Board
- Eager to Learn Pynq Development with Python and VIVADO
PYNQ (Python+Zynq), An FPGA development platform from Xilinx is an Open Source FPGA development platform. This Course covers from the Architecture of PYNQ (Zynq 7000), PYNQ Development Flow, Basic GPIO interfacing with PYNQ FPGA, Image Processing with PYNQ, using PYNQ libraries as sci_pi, OpenCV, Installing Tensorflow on PYNQ,Machine Learning with Pynq, Neural Network Implementation on PYNQ, Creating Custom PYNQ Overlay on Xilinx VIVADO .
After completing this course you will also know about the Acceleration methodology on the PYNQ Development Platform. Another important section of this course is Implementation of Machine Learning Algorithms on Python for Image Processing and other projects. We will implement Artificial Neural Networks (ANN) algorithms as CNN, BNN and other Neural Networks for real time projects as Number Plate Recognition, Face Recognition etc.
At the another section we will have sessions on "How to design Overlay system with VIVADO for PYNQ FPGA". This session is based on the VIVADO HLS & IP integrator for creating custom Overlay.
- Electrical Engineering
- Computer Science
- Hardware Design Enthusiast
This first Lecture is on "Introduction to PYNQ FPGA Architecture". PYNQ is an Zynq 7000 FPGA device from Xilinx. The main goal of PYNQ, Python Productivity for Zynq, is to make it easier for designers of embedded systems to exploit the unique benefits of APSoCs in their applications. PYNQ has specifically XC7Z020-1CLG400C FPGA Device which is Zynq 7000 device, this Zynq 7000 consists of two main block which are Programmable Logic (PL) and Processing System (PS). PL is an 7 series FPGA core (Logical Units, FF, MUX) and PS is dual core ARM Cortex A9.
This introductory session on PYNQ architecture has been included in this first Lecture.
This Lecture 2 of Section 1st is on Python Programming Interface, we have here a basics of Python, how it works on PYNQ and a small example of Python program. This session just widen the Python programming use with PYNQ, while we have complete Python programming session on Section 3.
This session is on Python Programming with PYNQ FPGA, we have included the conditional statements and loops with the GPIO based example of PYNQ FPGA. And we also have included the SciPy, MatPlotLib, NumPy and other Python Library with examples in this session.
This session includes the basics of OpenCV Library, image processing functions on OpenCV as transformation, smoothing, blurring functions. We also have included the Jupyter Notebook based LAB example on this session and those LAB project files (.ipnyb) files are attached with this lecture.
This session covers from OpenCV functions as: Image Gradient, Edge Detection, Feature Detection functions (Harris & Fast Corner), Haar Cascade algorithm, Face Detection with Haar, Face and Eye Detection with Haar Cascade algorith. All the LAB sources are attached with this video lecture , so you can download those and explore on your own Jupyter+ PYNQ environment.
This Lab session is on showing the example project of PYNQ on Streaming the HDMI input to HDMI output and Processing the HDMI input with Grayscale function on Software Level and Hardware Level. The Software Level gives 3 Frame/Sec and Software+Hardware Level gives 8 frames/sec.
This session is on Creating the custom Overlay using the VIVADO HLS, VIVADO IP integrator and the Jupyter interface. This session focus on the design flow of creating the custom overlay, so that you can accelerate other application on the HLS and create custom overlay.