[email protected]

Author: Strahinja Zivkovic

#016 PyTorch – Three hacks for improving the performance of Deep Neural Networks: Transfer Learning, Data Augmentation, and Scheduling the Learning rate in PyTorch

08.11.2021

Highlights: Hi and welcome to our new post. In this post, we are going to talk about very popular deep learning techniques that we can apply to speed up training and improve the performance of our deep learning model. You will learn how you can use transfer learning and some other popular methods like data augmentation and scheduling the learning rate. So, let’s begin. Tutorial Overview: What is Transfer learning? Transfer learning in PyTorch Scheduling…
Read more

#015 PyTorch – Building A Smile Detector with PyTorch

18.10.2021

Highlights: People spend a lifetime in the pursuit of happiness. Fortunately, intelligent machines can, today, detect happiness or smiles within seconds using Smile Detection Models. In this tutorial post, we will learn how to build a Deep Learning-based Smile Detection model in PyTorch. We will utilize the LeNet-5 architecture and work on the CelebA dataset which is a large dataset of images containing faces of people smiling and not smiling, respectively. So let’s begin! Tutorial…
Read more

#010 Linear Algebra – Linear least squares

12.07.2021

Highlight: Linear least squares is a very powerful algorithm to find the approximate solutions of overdetermined linear systems of linear equations. Those are systems of linear equations that have more equations than unknowns. The solution to this idea is to minimize the sum of squares of errors in the equation. This method was discovered independently by the mathematicians, Carl Friedrich Gauss, and Adrien-Marie Legendre, around the beginning of the 19th century. So, let’s begin with…
Read more

#011 Linear Algebra – Nonlinear Least Squares

11.07.2021

Highlights: In the real-world scenario, models don’t produce linear graphs that often. Most of the time the equation of the model involves higher-order and higher-degree functions. In this post, we will learn how to solve the harder nonlinear equations using a heuristic algorithm of finding the least-squares approximate solution. So let’s begin. Tutorial Overview: Nonlinear Equations Introduction Difficulty Of Solving nonlinear equations Nonlinear Least Squares Optimality condition Gauss-Newton Algorithm Basic Gauss-Newton Algorithm Shortcomings Of The Gauss-Newton Algorithm…
Read more

#001 Advanced Computer Vision – Introduction to Direct Visual Tracking

17.06.2021

Highlights: In this post, we will review some simple tracking methods. First, we will introduce several types of visual tracking methods. Then, we will explain how we can classify them. We will also talk about the fundamental aspects of direct visual tracking, with a special focus on region-based methods and gradient-based methods. In future post series, we will provide a detailed mathematical derivation of the Lucas Kanade framework with a focus on image alignment. Finally,…
Read more

The hundred-page Computer Vision book
What are morphological transformations?
Learn how to align Faces in OpenCV in Python

©  2024 Master Data Science. Built using WordPress and the Mesmerize Theme