Sign Language Recognition: Hand Object detection using R-CNN and YOLO
For our introduction to neural networks on FPGAs, we used a variation on the MNIST dataset made for sign language recognition. It keeps the same 28x28 greyscale image style used…
Getting started with Computer Vision for Vitis 2020.1 on Zynq: Part 3 Productive and Efficient Vitis Development Flow
Welcome to the 2020.1 version of getting started with computer vision on Vitis on Zynq. The release of 2020.1 saw significant changes from the old 2019.2 version and we thought…
Improving Convolutional Neural Networks: The weaknesses of the MNIST based datasets and tips for improving poor datasets
Introduction In our previous tutorial series, we looked at sign language recognition using the sign language MNIST dataset based off the original 1999 MNIST dataset, which is considered the “Hello…
Getting started with Computer Vision for Vitis 2020.1 on Zynq: Part 2 Automation and Scripts
Welcome to the 2020.1 version of getting started with computer vision on Vitis on Zynq. The release of 2020.1 saw significant changes from the old 2019.2 version and we thought…
Getting started with Computer Vision for Vitis 2020.1 on Zynq: Part 1 Quick Start
Welcome to the 2020.1 version of getting started with computer vision on Vitis on Zynq. The release of 2020.1 saw significant changes from the old 2019.2 version and we thought…
Vitis AI using Tensorflow and Keras Tutorial Part 8
Part 8: Compiling our CNN We now have our complete model and must make it ready to be run on the FPGA. To do this, we must compile our model…