Deep Learning, Machine Learning, and Learning
Model serving can be achieved using different approaches, let's see how the Publish-Subscribe Pattern can be used to create an infrastructure to serve Deep Learning models along with Spot Instances to reduce the costs of this infrastructure
Thin-Plate Splines is a technique for data interpolation and smoothing. We can use this technique to transform or augment data like images to increase the number of training images or change the image content without impacting its style.
Let's see how we can implement the BlazeFace architecture for face detection that works in low-end hardware using TensorFlow 2.0
The BlazeFace architecture is truly suitable for mobile devices, let's see how we can implement the face detection task in iOS using this architecture along with TensorFlow Lite
The BlazeFace architecture is truly suitable for mobile devices, let's see how we can implement the face detection task in iOS, this time using CoreML
TensorFlow.js is a great tool to deploy models to the web. We can combine this tool along with Electron to build desktop apps for several operative systems and show our models to the users in an easy way.
Deep Learning is a powerful tool that can be used to create and automatize tasks. Here, we will look at a paper that introduces an architecture to colorize line art images from reference color images. We will also implement it using TensorFlow.
In recent years, Magnetic resonance imaging pictures have been used to build deep learning approaches to solve several tasks like disease detection, image quality improvement, or reconstruction. Here, we will explore how MRI works and why the reconstruction task is important not only for radiologists but also for patients.