In this tutorial, we'll be testing our trained Transformer model from scratch for Spanish to English translation. We'll use the onnx model that was exported after training.

In this tutorial, I'll walk through a practical example of Transformer Training for Language Translation tasks from Spanish to the English language

Preparing Data for Effective Transformer Training: From Raw Text Selection and Download to Crafting Custom Tokenizers and Establishing Efficient Data Pipelines

In this tutorial, we continue implementing the complete Transformer model in TensorFlow. To achieve this, we implement Encoder and Decoder step-by-step

In this tutorial, we'll walk through the attention mechanism and the core components of the transformer to build encoder-decoder architecture

Introduction to Transformers Architecture covering main components, advantages, disadvantages, limitations, etc. In this part, we'll cover the PositionalEmbedding layer

We'll cover more advanced Generative Adversarial Network technique WGAN-GP. We'll train it on a popular celebA human portrait dataset

In this tutorial, we'll cover the basics of GANs (Generative Adversarial Networks) step-by-step in TensorFlow. As an example, we'll use a basic MNIST dataset

Construct an accurate handwriting recognition model with PyTorch! Understand how to use MLTU package, to simplify the PyTorch models training pipeline, and discover methods to enhance your model's accuracy

I will introduce the PyTorch Wrapper in this tutorial, saving us time when developing the PyTorch models training pipeline. We'll be able to do this in blocks!

In this tutorial, I'll cover the basics of PyTorch, how to prepare a dataset, construct the network, define training and validation loops, save the model and finally test the saved model

Master the basics of speech recognition with TensorFlow: Learn how to build and train models, implement real-time audio recognition, and develop practical applications

Unlock the power of handwritten sentence recognition with TensorFlow and CTC loss. From digitizing notes to transcribing historical documents and automating exam grading

Construct an accurate handwriting recognition model with TensorFlow! Understand how to utilize the IAM Dataset to extract text from handwritten images, and discover methods to enhance your model's accuracy

Training a Custom OCR for Captcha Image Text Extraction with TensorFlow and CTC Loss Function: A Step-by-Step Guide. Using the mltu Library to Simplify the Process

In this tutorial, we will explore how to recognize text from images using TensorFlow and CTC loss with the Neural Networks model

I'll show you how you can easily apply the AnimeGAN effect on your media to get beautiful animated pictures, videos, or real-time camera streams

I'll introduce a simple way to build and use any custom face recognition model with my custom framework

In this tutorial, I'll show you how we can create a "pencil" sketch image using Python with just a few lines of code

This tutorial will teach us to detect the faces and face landmarks in the image, video, or webcam stream using the MediaPipe library and display it!

We'll learn how to blur or change our selfie background just like Zoom, MS Teams, Google Meet, or Skype using Python

This tutorial will teach us how to deploy a Django application with Nginx, Gunicorn, PostgreSQL, and Let's Encrypt SSL on an Ubuntu server

In this tutorial, we will cover, investigate and explore social (Google) OAuth 2.0 authentication integration with Django

In this part, we'll focus on remote PostgreSQL database creation and migrating it to from the default Django SQLite database

We'll create a module for users to subscribe to a newsletter. We'll extend this module, so we can send emails to our subscribers

In this part, we'll cover how to implement Django image management so we can upload them from a local computer or clipboard

We'll continue to cover how to complete email functionality in the Django webserver to allow users to change and restore their passwords

In this part, we'll cover how to send an email confirmation using Django when someone registers on our website

We'll learn how we can implement buttons to update, delete and create articles and series just in the front end if we have the right authorization for that

We'll cover how to upload and manage images for our series and articles. Also, we'll enable users to add their profile image so that others can recognize him

In this article, we'll crack on our user profile so that our users can edit their description, name, surname, or other details you want to include

We will cover Google reCAPTCHA - a top-rated solution to protect your application or website against bots or spam that it's reasonably effortless to implement when we are using the right tools

We'll get familiar with decorators and implement some changes to allow users to log in not only with a username but also with an email

In this part, we will continue working on our user handling; we'll bring some dynamics to the page and some ability for users to log in and log out on our page.

This part will cover the Django messaging tool that will throw a pop-up for a user about what's going on with their operations on the website!

This tutorial will cover creating user registration, login, and logout functionality on a site built using the Django Web Framework and a little CSS

We'll spend time on our website's front-end styling and design, together with some pagination views

This tutorial will cover how to easily create and manage basic Django admin functionality in our Django database

In this tutorial, we will check out the admin functionality of Django and cover its benefits

In this tutorial part, we're going to introduce the concept of Models. This is where the majority of the value of Django comes from

This tutorial shows how you can create a "skeleton" website, which you can then populate with site-specific settings models, paths, views, and templates (we discuss these in later tutorials)

In this tutorial, we'll get a basic understanding of what is Django, why people use it, how it's different from other frameworks, and how to run your first basic page

In this tutorial, we will continue developing a Bitcoin trading bot. We'll integrate more technical indicators, implement normalization techniques, and of course, test everything up!

We'll learn the simplest way to download historical cryptocurrency OHCL market data via exchange APIs. We'll use this data to train our RL Bitcoin trading agent that could finally beat the market!

We'll integrate a few most popular technical indicators into our Bitcoin trading bot to make it learn even better decisions while making automated trades

Let’s improve our deep RL Bitcoin trading agent code to make even more money with a better reward strategy and test different model structures

In this tutorial, we will continue developing a Bitcoin trading bot, but this time instead of making trades randomly, we'll use the power of reinforcement learning

In this part, we are going to extend the code written in my previous tutorial to render a visualization of the RL Bitcoin trading bot using Matplotlib and Python

In this tutorial, we will write a step-by-step foundation for our custom Bitcoin trading environment where we could do further development, tests and experiments

In this tutorial, we'll solve the BipedalWalker-v3 environment, which is a very hard environment in the Gym. Our agent should run very fast, should not trip himself off, should use as little energy as possible...

In this step-by-step reinforcement learning tutorial with gym and TensorFlow 2. I’ll show you how to implement a PPO for teaching an AI agent how to land a rocket (Lunarlander-v2)

After giving you a lot of explanations about YOLO, I decided to create something fun and exciting, which would be a Counter-Strike Global Offensive game aimbot

In many cases, when we want to train a neural network to detect our custom object, it's hard to find that labeled data to download, so in this case, we must do this manually. In this tutorial, I'll show how to speed up this process.

This tutorial is a brief introduction to multiprocessing in Python. At the end of this tutorial, I will show how I use it to make TensorFlow and YOLO object detection work faster

In this part, I will show you how we can optimize our deep learning model and speed it up with TensorRT while running it on NVIDIA GPUs

In this part, we will continue bag-of-specials (BoS) and we’ll cover bag-of-freebies (BoF). Will show you how to train a custom YOLOv4 model

In this article, we'll try to understand YOLOv4 theory and why the release of a new object detection method spread through the internet in just a few days

This tutorial will provide step-by-step instructions for how to set up TensorFlow 2.* and run YOLOv3 on the Raspberry Pi

In this tutorial, you will figure out how to use the mAP (mean Average Precision) metric to evaluate the performance of an object detection model

In this tutorial, I will explain to you what is object tracking, where we use it, what are the differences between object detection, and will give you my own working example code

In this tutorial, you will learn how to utilize YOLOv3-Tiny the same as we did for YOLOv3 for near real-time object detection

In this tutorial, I will demonstrate how to use Google Colab (Google's free cloud service for AI developers) to train the Yolo v3 custom object detector with free GPU

In this tutorial, I’m going to explain to you an easy way to train YOLO v3 on TensorFlow 2 to detect a custom object even if you’re a beginner or if you have no experience with coding

In this step-by-step tutorial, I will show how to train a 7-class object detector (could use this method to get a dataset for every detector you may use)

In this tutorial, I’ll cover the Yolo v3 loss function and model training. We’ll train a custom object detector on Mnist dataset

I will make Yolo v3 easy and reusable without over-complicating things. With this tutorial, you will be able to implement object detection in TensorFlow 2 simply

In this tutorial, we'll dive into the understanding of the PPO architecture and we'll implement a Proximal Policy Optimization (PPO) agent that learns to play Pong-v0

In this tutorial, I will provide an implementation of the Asynchronous Advantage Actor-Critic (A3C) algorithm in Tensorflow and Keras. We will use it to solve a simple challenge in the Pong environmens

Today, we'll study a Reinforcement Learning method that we can call a 'hybrid method': Actor-Critic. This algorithm combines the value optimization and policy optimization approaches

To wrap up deep reinforcement learning, I’ll introduce the types of agents beyond DQN’s (Value, Model, Policy optimization, and Imitation Learning). We'll implement Policy Gradient!

In this tutorial, I'll implement a Deep Neural Network for Reinforcement Learning (Deep Q Network), and we will see it learns and finally becomes good enough to beat the computer in Pong!

Now I will show you how to implement DQN with CNN. After this tutorial, you'll be able to create an agent that successfully plays almost ‘any’ game using only pixel inputs

Now we will try to change the sampling distribution by using a criterion to define the priority of each tuple of experience.

In this part, we'll cover the Epsilon Greedy method used in Deep Q Learning and we'll fix/prepare our source code for PER method

In this short tutorial, I will show you how to set up YOLO v3 real-time object detection on your webcam capture

In this post, we’ll be covering Dueling DQN networks for reinforcement learning. This architecture is an improvement from our previous DDQN tutorial.

This is the second reinforcement tutorial part, where we'll make our environment use two (Double) neural networks to train our main model

This is an introduction tutorial to Reinforcement Learning. To understand everything from basics I will start with a simple game called - CartPole

This is my last tutorial with object detection in CS:GO, check out what results I got with the custom YOLO v3 object detection model in this unusual aimbot

Continuing from my previous tutorial, where I showed how to prepare custom data for YOLO v3 object detection training, finally, I will show you how to train that model

In this step-by-step tutorial, I will show you how to prepare data for your own custom YOLO v3 object detector

In this tutorial, I will try to explain how TensorFlow YOLO v3 object detection works. If you only want to try or use it without getting deeper details, go to my GitHub repository

In this tutorial, I will explain to you what is YOLO v3 object detection model, and how it works behind the math

Now we will learn how to build extremely deep Convolutional Neural Networks using Residual Networks (ResNets)

We'll learn to use Keras(programming framework), written in Python and capable of running on top of several lower-level frameworks

In this tutorial part, we will Implement helper functions that we will use when implementing a TensorFlow model and a fully functioning ConvNet

In this tutorial part, we will build a deep neural network using TensorFlow. You'll see that the training model on Tensorflow is significantly faster

Welcome to the second tutorial. Now I will step you through a deep learning framework that will allow you to build neural networks more easily

Convolutional Neural Network (CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery, this tutorial is about them

Training neural network requires specifying an initial value of the weights. You'll see that a well-chosen initialization method could improve learning and accuracy

In this tutorial, we will use the functions we had implemented in the previous parts to build a deep network and apply it to cat vs dog classification

In this part, we will implement the backward function for the whole network and we will also update the parameters of the model, using gradient descent

Just like with the forward propagation, we'll implement helper functions for backpropagation and calculate the gradient of the loss function with respect to the parameters

Now when we have initialized our parameters, we will do the forward propagation module by implementing functions that we'll use when implementing the model.

In the last tutorial series, we wrote 2 layers neural networks model, now it's time to build a deep neural network, where we could have whatever count of layers we want

So we came to the last tutorial part where we'll build our final neural network model. To do that we'll use previous functions in the right order

In this tutorial part, we'll write backward propagation and parameters update function using cache computed during the forward propagation

In the previous tutorial, we initialized our model parameters. In this part we'll for this we'll use cache computed during the forward propagation

It's time to build a neural network, with one hidden layer. You will see that there is no big difference between this model and logistic regression

In order for Gradient Descent to work, we must choose the learning rate wisely. In this part, you will see how the learning rate determines how rapidly we update the parameters

In this tutorial, you will see how the overall model is structured by putting together all the building blocks together in the right order

In this tutorial, we will implement the predict() function and we will be able to use w and b to predict the labels for our dataset X

In this tutorial, we will learn how to update learning parameters (gradient descent). We'll use parameters from the forward and backward propagation

In this part, we'll build a Logistic Regression using a Neural Network mindset. We'll see that it is actually a straightforward Neural Network model

Logistic regression is a binary classification method. In this full tutorial, we will start writing an algorithm that could predict the correct animal in a given picture

When we are writing machine learning functions, we must be sure that our code is computationally efficient so we always use vectorization

In this tutorial, we'll learn how to reshape arrays, normalize rows, what is broadcasting, and softmax. All of this is extremely useful in machine learning

Introduction to sigmoid logistic regression function that gives an ‘S’ shaped curve that can take any real-valued number and map it into a value between 0 and 1

In this part we'll finish this tutorial, we'll write a code that we could start script from CMD line and our script could process a batch of images in multiprocessing mode

In this tutorial part, I will show you how to read a single image or folder full of images with the same function, and we will process this image as in the previous tutorial part

In this tutorial, I will show you what task I received when I was applying for a new python programmer job. This task is related to OpenCV image-stitching and multiprocessing

In this tutorial you will learn how to make panorama and image stitching using Python and OpenCV. I'll demonstrate step by step how image stitching can be performed

In this tutorial, you will learn how to make panorama and image stitching using Python and OpenCV. I'll demonstrate step by step how image stitching can be performed

In this tutorial, I will write a custom function that will be used to wait since the HTML object is loaded on-page for a certain time

In this tutorial part, I will create a virtual click function, which we'll use that no one could track our click, in simple words, we'll be clicking as humans

In this tutorial part, I will show you how to find HTML objects and interact with them in different ways. As an example, I'll use Gmail log-in page

In this part, I will show you how to use SELENIUM to start automating commonly used and custom browsers, how to open and close new browsing tabs

Selenium is one of the most popular tools for Web User Interface Automation. In this tutorial, I will introduce you to this amazing tool and simple example.

In this tutorial, we will grab all CAPTCHA symbols, check the order of them, detection accuracy, and overlapping, and use these components to write the final out-of-the-box CAPTCHA solver.

TensorFlow CAPTCHA detection tutorial, in this part, we will extract our model from training data, and we'll write a short code to use that model actually to detect CAPTCHA symbols

TensorFlow CAPTCHA detection tutorial, in this part, we will extract our model from training data, and we'll write a short code to use that model actually to detect CAPTCHA symbols

In this tutorial, we will grab all symbols from CAPTCHA, checking the order of them, detection accuracy, and overlapping, and use these components to write the final out-of-the-box CAPTCHA solver.

In this tutorial, I will merge multiprocessing code with TensorFlow object detection code to maximize FPS performance

In this tutorial, I will show you how to faster grab your computer screen with python multiprocessing on the MSS library

In this tutorial, I will show you how to export a faster newly trained model and we’ll test it out

In this part, we're going to change our code, that we could detect enemies, move our mouse and shoot them.

In this part, we're going to export inference graph and detect our own custom objects

In this part and a few in the future, we're going to cover how we can track and detect our own custom objects

In this tutorial, we'll make our code from tutorial part 3 work much faster by modifying our while loop

In this tutorial, we'll merge Object detection API exported code with our grab screen code, and we will try to detect objects on our screen

In this tutorial, we'll review three methods of grabbing our computer screen, and we will choose the best one to use for our further development

The first part of the TensorFlow Object detection tutorial begins with installing drivers, packages, preparing files, and starting our first example.

In this tutorial we are going to cover the very basics of classes in Python. We will learn to understand, read and write basic classes.

In this tutorial you will learn writing and reading files with python. We will cover basic methods provided how to manipulate files with python.

In this tutorial we will learn how to use Python modules. A module can define functions, classes and variables which include runnable code.

This tutorial is about Python variables, you will learn how to use global and local variables. This helps to keep code clean and easy to read

This tutorial is about Python functions, you will learn about keyword, default, variable-length argument and anonymous functions

This tutorial is about Python break, continue and pass control statements, using them we can leave loop, go back or skip certain code.

This tutorial is about Python for loop, short basic introduction with for loop syntax and how to use range loop.

This tutorial is about one of the most basic forms of logic that can be introduced using if, elif, else logical expression.

This tutorial is about Python while loop, short basic introduction with while loop syntax and what is infinite loop.

This tutorial is about python differences between tuples and lists, short introduction with python dictionaries.

This tutorial is about python variables and strings. Short introduction with numbers, strings, lists, tuples and dictionaries.

This tutorial is about python variables and strings. Short introduction with numbers, strings, lists, tuples and dictionaries.

This tutorial is for beginners to learn how to use Python interpreters as a simple calculator using basic math syntax.

This tutorial is for beginners to learn using Python print statement, a great tool to find, remove and fix errors made within code.

This tutorial is for beginners and will show you, how to install Python and Sublime text editor on windows 10.

Introduction with python programming language. Popularity, features, benefits, who use it and what are the possibilities with it.