In a previous tutorial, we explored using the k-means clustering algorithm as an unsupervised machine learning technique that seeks to group similar data into distinct clusters to uncover patterns in the data. So far, we have seen how to apply the k-means clustering algorithm to a simple two-dimensional dataset containing distinct clusters and the problem […]
Digital videos are close relatives of digital images because they are made up of many digital images sequentially displayed in rapid succession to create the effect of moving visual data. The OpenCV library provides several methods to work with videos, such as reading video data from different sources and accessing several of their properties. In […]
When working with images, some of the most basic operations that are essential to get a grip on include reading the images from disk, displaying them, accessing their pixel values, and converting them from one color space to another. This tutorial explains these basic operations, starting first with a description of how a digital image […]
If you are interested in working with images and video and would like to introduce machine learning into your computer vision applications, then OpenCV is a library you will need to get hold of. OpenCV is a huge open source library that can interface with various programming languages, including Python, and is extensively used by […]
We have seen how to train the Transformer model on a dataset of English and German sentence pairs and how to plot the training and validation loss curves to diagnose the model’s learning performance and decide at which epoch to run inference on the trained model. We are now ready to run inference on the […]
We have previously seen how to train the Transformer model for neural machine translation. Before moving on to inferencing the trained model, let us first explore how to modify the training code slightly to be able to plot the training and validation loss curves that can be generated during the learning process. The training and […]
We have put together the complete Transformer model, and now we are ready to train it for neural machine translation. We shall use a training dataset for this purpose, which contains short English and German sentence pairs. We will also revisit the role of masking in computing the accuracy and loss metrics during the training […]
We have arrived at a point where we have implemented and tested the Transformer encoder and decoder separately, and we may now join the two together into a complete model. We will also see how to create padding and look-ahead masks by which we will suppress the input values that will not be considered in […]
There are many similarities between the Transformer encoder and decoder, such as their implementation of multi-head attention, layer normalization, and a fully connected feed-forward network as their final sub-layer. Having implemented the Transformer encoder, we will now go ahead and apply our knowledge in implementing the Transformer decoder as a further step toward implementing the […]
Having seen how to implement the scaled dot-product attention and integrate it within the multi-head attention of the Transformer model, let’s progress one step further toward implementing a complete Transformer model by applying its encoder. Our end goal remains to apply the complete model to Natural Language Processing (NLP). In this tutorial, you will discover how […]
