Digitize and Automate Projects Faster
By simplifying labor-intensive data upload, labeling, training, model optimization and retraining tasks, teams quickly build vision models for a wide range of processes, including detecting defective parts in a production line, reducing downtime on the factory floor, automating inventory management, or other digitization and automation projects. The Intel® Geti™ software platform makes it intuitive and shortens the time-to-value of AI model development dramatically.
Core Capabilities Behind the Next-Generation Computer Vision AI Software
Interactive Model Training
Get started annotating data with as little as 20-30 images; then let active learning help you teach the model as it learns.
Multiple Computer Vision Tasks
Create models for AI tasks including classification, object detection, semantic segmentation or anomaly detection.
Train your model into a multistep, smart application by chaining two or more tasks, without the need to write additional code.
Expedite data annotation and easily segment images with professional drawing features like a pencil, polygon tool and OpenCV GrabCut.
Output deep learning models in TensorFlow or PyTorch formats
(where available) or as an optimized model for OpenVINO™ toolkit to run on Intel® architecture CPUs, GPUs and VPUs.
Refining hyperparameters is critical to the model’s learning process. With built-in optimization, the Intel Geti platform makes a data scientist’s job easier.
Rotated Bounding Boxes
Support for rotated bounding boxes extends the training simplicity and accuracy to datasets with images that are not axis-aligned.
Comprehensive statistics to assess your model’s performance
Flexible Deployment Options to Get You Started
Whether you want to take advantage of the cloud virtual machine without having to manage infrastructure or utilize your system infrastructure within your network, just configure your infrastructure and environment and get ready to install the Intel® Geti™ platform.
- On Premise
- Virtual Machine
Enabling Collaboration that Adds Value
Cross-functional AI teams collaborate in a single instance to analyze results in real time. The graphical interface allows team members with little or no AI experience to help train computer vision models. Enabling functionalities such as annotation assistants, drawing features, and object detection assistants make model training drag-and-drop simple.