Datature Tutorials

In this video, Wei Loon walks you through the steps to train an image classification model on Datature’s Nexus platform using YOLOv8. This tutorial is designed for machine learning engineers interested in classifying images into distinct categories with state-of-the-art deep learning models. Learn how to process and label datasets, train image classification models with YOLOv8, and apply them to a variety of applications—from recognizing objects in photos to enhancing visual search engines or improving quality control in manufacturing.

In this video, Leonard walks you through the steps to train an object detection model on Datature’s Nexus platform using YOLOv8. This tutorial is designed for machine learning engineers interested in detecting and classifying objects in images or videos with state-of-the-art deep learning models. Learn how to process and label datasets, train object detection models with YOLOv8, and apply them to a wide range of applications—from enhancing surveillance systems to improving quality control in manufacturing or advancing medical diagnostics.

In this video, Leonard walks you through the steps to train a video classification model on Datature’s Nexus platform using MoViNet. This tutorial is tailored for machine learning engineers looking to categorize visual content into distinct categories using state-of-the-art models. Learn how to process and label datasets, train video classification models with MoViNet, and apply them to various applications, from analyzing sports footage to advancing autonomous vehicle systems or improving medical imaging.

In this video, Leonard walks you through the steps to train a keypoint detection model on Datature’s Nexus platform using YOLOv8 - in this case, a golf swing. This tutorial is ideal for machine learning engineers looking to understand pose detection and its applications, such as tracking joints or objects in images. Learn how to process datasets, label keypoints, and train a model to enhance precision in sports mechanics, robotics, and more.

In this video, Leonard walks you through the process of building a semantic segmentation model in just 8 minutes using DeepLab V3. This tutorial is designed for machine learning engineers and computer vision enthusiasts who are eager to dive into pixel-wise segmentation tasks with state-of-the-art deep learning models. Learn how to prepare your dataset, train a semantic segmentation model with DeepLab V3, and apply it to a variety of real-world scenarios—from enhancing autonomous vehicles to improving environmental analysis and medical image segmentation.