Data science is a rapidly growing field that combines statistics, mathematics, and computer science to extract insights and knowledge from data. As a data scientist, you need to be proficient in a variety of tools, techniques, and concepts to effectively analyze and visualize data. To help streamline your work, we have created the ultimate data science cheat sheet. The cheat sheet covers all the essential topics in data science, from the basics of statistics and probability to advanced machine learning algorithms and deep learning techniques. It is designed to be a quick reference guide for data scientists, providing a comprehensive overview of the key concepts and tools used in the field.

#001 PyTorch – How to Install PyTorch with Anaconda? A brief step by step tutorial on how to install PyTorch with Anaconda #002 PyTorch – What are Tensors in PyTorch 1.3? Learn what are tensors – the main data structure of PyTorch #003 PyTorch – How to implement Linear Regression in PyTorch Learn what Linear regression is and how to create a linear regression model in Python using PyTorch #004 PyTorch – Computational graph and… Read more

In this post we will see how we can classify handwritten digits using shallow neural network implemented with tf.keras. First, let us import all necessary libraries. After imports, we can use imported module to load digits data. The load_digits() function will just download data and we need to split it into train and test sets. We can also plot some digits to see how they look.

Highlights: In this post we will learn about fundamental matrix and we will continue our series about stereo vision. In the last post we concluded that if we have enough points we should be able to figure out the constraints for the epipolar line. So for this, we will need to calculate a fundamental matrix. In previous posts we have developed the relationship between two images obtained with two calibrated cameras where we have actually known the rotation and translation parameters between them. In particular we defined the essential matrix which related between world points of two calibrated cameras.

Highlights: In this post, we will explain the main idea behind Camera Calibration. We will do this by going through code, which will be explained in details. In a last few posts, we have talked about modeling a projection, perspective projection, camera translation and rotation and all of this stuff will be of a great importance for you in order to understand this post. So, if you missed that, jump back and prepare for programming. Basically the main idea of camera calibration is to find parameters that would help us to solve some problems, which we will be doing here.

We will first import libraries as NumPy, matplotlib, pyplot and derivative function. Then with a NumPy function – linspace() we define our variable \(w \) domain between 1.0 and 5.0 and 100 points. Also we define alpha which will represent learning rate. Next, we will define our \(y \) ( in our case \(J(w) \)) and plot to see a convex function, we will use \((w-3) 2 \). So we can see that we plotted our convex function as an example.

Highlights: In this post we are going to continue our story about vectors. We will talk more about basis vectors, linear combination of vectors and what is the span of vectors. We provide a code examples to demonstrate how to work with vectors in Python. Let's talk about vectors in more details. Vectors are related to pairs of numbers that we call coordinates.

Highlights: In this post we're going to talk about perspective imaging. First, there is a little bit of math that is needed for the explanations of the geometry and the configuration of the camera. Second, we will use a simplified pinhole camera model. Hence, we will not talk about focus and other "non-pinhole effects" when the rays are not in focus. When we take a photo, our 3D world is mapped into a 2D image.

In 1996 Italians entered the game. Professor Alberto Broggi and his team at the University of Parma initiated the ARGO project to pick up where the "Prometheus" left off. They came up with, a Lancia Thema, prototype equipped with two simple black-and-white video cameras and a navigational system based on stereoscopic vision algorithms. The car managed to cover a route of more than 1,200 miles at an average speed of 56 mph.

In the following image we can see an alternative basis for one coordinate system and those are basis vectors \(\vec{b}_{1} \) and \(\vec{b}_{2} \). On the other hand, in this different alternative coordinate system it is represented with coordinates \(-1 \) because that's how much we have to scale vector \(\vec{b}_{1} \) and it's scaled with \(2 \) along \(\vec{b}_{2} \), cause that's how we much we have to scale our \(\vec{b}_{2} \) vector.