-
# Machine Learning Building a zero-shot Sign Pose Embedding model
At Xmartlabs, our machine learning team set out to develop an innovative ML product last year. After careful consideration and collaboration with our Design team, we decided to focus on building a sign language practice assist...
-
# Machine Learning When and why should you go for AI on the edge?
AI on the Edge, or Edge AI, is a concept that people often disregard in their projects without an idea of how powerful it can be. In this blog, I’ll explain what edge AI is, its advantages and weaknesses (and...
-
# Machine Learning Image Completion
In this blog, we will present the topic of image completion. With it, we’ll show its use cases, the relevance of this topic, and how to solve it using deep learning models. There is also a link to a repository...
-
# Machine Learning Precision Agriculture And The Future of Farming with Machine Learning
Maintaining a plantation, whether it’s for forestry or crops, has never been more expensive (costs per acre in the US have risen 170% since the 70s). And this is partly due to the increasing costs of maintaining weed-free fields....
-
# Machine Learning From Low to High-Quality Image — Practical Application of Super-Resolution Algorithms
Nowadays, everyone is exposed to artificial intelligence (AI) in one way or another. Computer vision is a popular application of AI through cellphones, video conference platforms, and video vigilance cameras, among other use cases. One fascinating problem to solve within the...
-
# Machine Learning How To Get The Most Out Of A Recommendation Engine
Recommendation engines can rapidly increase online business revenue and boost customer loyalty, both crucial for sustainable growth. In this blog post, we’ll go through the main challenges, and pros and cons we faced implementing and deploying such solutions for a...
-
# Machine Learning Occupancy Analytics powered by Edge-AI & Object Detection models
In a previous post, we covered computer vision and its application to body detection. Today, we’ll go a little bit deeper into the object detection problem showing an actual use case scenario: Lanthorn. What’s Lanthorn? Lanthorn is an Occupancy...
-
# Machine Learning Our Solution for the NFL Helmet Assignment Kaggle Competition
Kaggle competitions attract thousands of data science and machine learning enthusiasts by providing access to various datasets and infrastructure with GPU availability and discussion forums to share ideas; this is very important for practitioners looking for a starting point. Here...
-
# Machine Learning Body Detection using Computer Vision
Being able to infer human bodies in images automatically has opened avenues for an array of real-life applications. Everyone, in one way or another, has used these technologies. If you’ve used Zoom (and almost everyone has in the past two...
-
# Machine Learning CoreML not fast enough? Use Bender!
Have you ever wanted to run a neural network model on iOS and found out that it runs too slow for your use case? We faced this problem and have gone through several options to reduce model inference time. We...
-
# Machine Learning Find your missing pet with deep learning
Losing a pet can be a dramatic situation some families might go through. Immediately, social media posts with pictures of the pet emerge from both the owner and the finder. What happens then depends on multiple factors, such as their...
-
# Machine Learning 5 Practical Ways to Speed Up your Deep Learning Model
Did you obtain good accuracy with your deep learning model only to find out that inference time isn’t enough to deploy on production? Are you lost on how to optimize your model’s inference speed? Then this post is for you....
-
# Machine Learning How to convert a NN model from TensorFlow Lite to CoreML
It’s been over a year since Apple has introduced Create ML, a framework that allows you to build neural network models in Swift and use them on iPhones and iPads with Core ML. However, the most common way of...
-
# Machine Learning ML Kit on iOS and how it performs against Core ML
At Xmartlabs we have been closely involved in the nascent field of on-device Machine Learning. Our main focus has been Machine Learning on iOS and we have been exploring different use cases including style-transfer, human body pose detection and medical...
ML Model Monitoring: Boosting Performance & Reliability
ML Model Monitoring: Boosting Performance & Reliability In the dynamic realm of recommendation systems, the spotlight often shines on the development and deployment of models. Yet, the vital importance of ongoing model monitoring can...