Ciro Greco has built ML systems at many named-brand retailers. In this episode, he gives us tips on getting value out of ML at “reasonable scale” companies with NLP and information retrieval. The concept of “reasonable scale” was one he returned to. and he clearly has a nuanced understanding of how that segment differs from the hyper scale tech giants. He also brings advanced ideas like embeddings from NLP towards e-commerce personalization.
Building Things with Machine Learning is Masterful AI's podcast covering interesting applications of machine learning. We started this podcast to focus less on innovative research, and more on the innovative ways ML is being applied to building products.
Building Things with Machine Learning is Masterful AI's podcast covering interesting applications of machine learning. We started this podcast to focus less on innovative research... and more on innovative ways ML is being applied to building products.
We've released Masterful 0.5.2, the platform that automates model development for computer vision. This release adds support for object detection, allowing developers to build detection models faster than ever before.
You can download it right now with a `pip install -U masterful`.
Deep learning has opened the door to tackling many real-world computer vision problems. But building and deploying Deep Learning models has always been a tedious task of labeling the entire dataset, finding the right hyperparameters, determining a data augmentation policy, and then deploying the model.
Masterful makes building and deploying Deep Learning models orders of magnitude easier. All you need to get started is to label a small fraction of your image data. Masterful’s meta-learner finds the optimal hyperparameters, augmentation policy, and trains the model both on labeled and unlabeled data.
In this post, we’ll show how easy it is to solve a real-world computer vision problem using Masterful.
Semi-supervised learning (SSL) unlocks value in your unlabeled data, but it can be difficult to implement. Masterful can fully automate model training and apply SSL, but it also allows users to easily use SSL with their existing training code. We call this Simple SSL, and the benefits are less labeling and a more accurate model. In this post we'll show you how to try it.
Today we’re making a big leap forward in enabling new applications and insights for every enterprise that uses visual data. We’re releasing the next version of Masterful, the platform that automates model development for computer vision. Masterful now includes a low-code interface that enables developers to build models faster than ever before. Using a simple command-line interface (CLI), any developer can build production-grade models without needing to write code in TensorFlow or PyTorch. Our low-code interface also opens up CV development to an even wider universe of developers!
It’s no secret that just about any deep learning computer vision task can be improved with transfer learning. Transfer learning is a method where a model developed for one task is reused as the starting point for a model for another task. It leads to the question: how can we best reuse weights gathered from existing models trained on very large datasets to improve the performance and cut down development time on a new model for a smaller target dataset? In this post we’ll compare several approaches, provide experimental results, and show you how to easily incorporate transfer learning into your model development.
In a previous post we compared Masterful AI’s computer vision training platform to Google’s Vertex AI AutoML platform. We observed significant improvements across the board from Masterful. But that comparison only considered the use of labeled data, whereas Masterful—unlike Vertex—can also leverage your unlabeled data to improve performance, using semi-supervised learning (SSL).