Blog

Check out a novel approach for multiple object tracking in video sequences, which decouples object classification & localization for improved performance.

We're thrilled to announce Video Labelling is now available for early access! The asset onboarding and annotation process have been bolstered with new tools.

We support asset upload to Nexus via Amazon S3 for greater convenience and a smoother workflow while keeping your assets secure.

Model Assisted Labelling streamlines your MLOps pipeline by iterating upon previously trained models to assist in data annotation for model retraining.

Datature is proud to support CentrovisioN’s mission to improve the efficiency and accuracy of building facade inspections through aerial surveillance!

Asset Group Management provides control over dataset usage throughout the whole computer vision pipeline, from asset upload to training dataset versioning.

We are excited to showcase how students from SMU used Datature's Nexus platform to create innovative computer vision projects without coding.

Streamlit empowers users to visualise inference results using custom trained computer vision models while staying within the ease of a Python environment.

We are excited to introduce Datature Edge, a simple way for users to deploy their trained deep learning model on edge devices like the Raspberry Pi.

Our TFLite model export option gives users access to an on-device mobile model that is extensively supported across many devices and platforms.

We continue to strive for democratization of low code implementations for computer vision with Node-RED and TensorFlow.js.

Gain greater insight into your dataset's quality with Aggregation Statistics which will help you improve your dataset for more effective ML model training.

Learn how you can train a YOLOX model to recognize your custom data (without code) for your next computer vision project.

Our Intelligent AI Mask Refinement gives users the option to correct imprecise masks with just a click of the button for new or pre-existing annotations.

An in-depth guide in understanding the uses & importance of image augmentation and how to perform it using Keras and the Datature platform

We are excited to introduce REST API deployment - a new way for users to access their trained machine learning model with low code requirements.

Discover the different approaches to Zero-Shot / K-Shot learning: One-Shot Object Detection, Decoupled Faster R-CNN, Few-Shot Object Detection, and more.

Datature is proud to support Brainscanology’s missions to revolutionize shape analysis and shape the future of image-based diagnostics!

The complete guide to compare the performance of multiple object tracking algorithms and build your object tracker project on Datature's platform. Read more!

Announcing our US$2.7M Series Seed funding round, led by Openspace Ventures, with participation from January Capital and new strategic investors.

Build your very own ASL alphabet detection model on the Datature platform to accelerate your learning of ASL in building a more accessible community.

The new Datature Metadata Query is an in-built search engine on the Nexus platform to allow teams to better understand and curate their datasets.

Learn how to label images, create augmentation sequences, and train a Face Mask Detection Model without coding. Validate it with our open-source tool - Portal.

IntelliBrush is the fastest way to annotate complex images in a few clicks. No prior training and installation are required. Read more to find out.

Portal is the fastest way to load and visualize your computer vision model performance. Read more to find out how to test your models on images and videos now!

Learn how to train an instance segmentation model in 5 easy steps. Try out new network architectures and augmentation techniques quickly and easily. Read more!

We streamline the pipeline and tasks required to build computer vision models. Create object detection and segmentation models - without code!