2 days agoTransformers more than meets the eye!Transformer networks is the novel and fastest sequence models in use. Let us dive in a bit and learn why it is faster than the other sequence models and why it is commonly used. The following information is got from MIT 6.S191 class and a video on youtube named: Illustrated…Deep Learning9 min readDeep Learning9 min read
Nov 26YUV colour spaceIn some machine learning applications images are converted from RGB to YUV format. The conversion is done by a very basic matrix multiplication but what is YUV format of an image or a video and why do we use this format in some applications? …Computer Vision3 min readComputer Vision3 min read
Feb 15, 2020ZED camera calibration and 3D stereo depth estimationThis post describes how to make 3D stereo camera calibration with a ZED camera. A ZED camera is used for this project but any DIY , or industrial stereo cameras could be used as the code only acquires Left and Right images from the stereo camera and do not use…Zed Camera4 min readZed Camera4 min read
Jan 5, 2020Working with OpenCV 4.2.0 on MacOS Mojave version 10.14.4 (18E226), VSCode and C++I have been working with OpenCV and Python for a while for my PhD studies, as I am not happy with the performance of Python I did try to move to C++ on VSCode but it was not an easy move as I expected. I did try to use OpenCV…Visual Studio Code2 min readVisual Studio Code2 min read
