Are you sure you need image classification instead of Siamese networks? — Siamese neural networks Learning a similarity between 2 data points can be extremely useful. Imagine a face identification system where there is a camera that captures your face and then the face recognition system is supposed to identify whether you are allowed to enter a building or not, based on a database of…

A summary of my journey of doing this in the last 3 years — Introduction In machine learning projects, there are several ways to deploy your final model. It could be cloud deployment, deployment on mobile devices, deployment on embedded systems, etc. For this, you can leverage several programming languages depending on the tech stack you’re using in your day job or project. In some…

AI that can paint images — Image style transfer

How we tested PointNet with data coming from an industrial 3D sensor — 3D Computer Vision 3D computer vision is a fascinating field! Instead of representing scenes in 2D as a set of pixel values, we can represent them in 3D in multiple forms. Some famous forms: Depth images, also referred to as RGBD where D stands for depth. 3D point clouds where there is a…

A deep learning model that combines NLP with Computer Vision — What is CLIP? Self-supervised learning in computer vision has shown great potential in learning different representations about images. This is one approach where a neural network can learn representations that can later be used for different tasks such as image classification and object detection. Another approach for learning representations from a dataset is…

Research and industry trends by an AI engineer — Backstory when I was doing an internship back in 2018, I started looking into object detection techniques, because I needed to solve a visual inspection problem. This problem required the detection of many different objects in a stream of images coming from an industrial camera. To tackle this challenge, I first…

Introduction to training deep learning models on Google Cloud AI Platform Backstory Around a year ago I was working on a personal project where I needed to be able to train deep learning models on the cloud. …

Is one of them really better than the other? An explanation from a ML engineer who uses both frameworks. — Backstory I surf the internet everyday looking for machine learning and computer vision content. I like to stay up-to-date with what’s happening in the field of ML because this is a field that can surprise you almost everyday! One question that I came across a few times is : Which is…

What is it? Why use it? And how to create your custom learning rate schedulers in Tensorflow 2 Learning rate schedule is simply the process of making your learning rate change during the training of your neural networks. Some publications show that by changing the learning rate during the training…