Skip to content

Robovision AI 5.0 release notes

Release date: March 4, 2023

What's new

Set up your Robovision AI instance

Platform setup options allow you to control various settings, such as managing platform users, selecting a color theme, or configuring a platform layout.

Learn more

Configure projects

Tackle the main computer vision problems with the EfficientNet, YOLOv5, and SOLOv2 project types.

Learn more

Import data of various formats

Import your annotated or unannotated data in one of the supported formats.

Learn more

Label and create datasets with the new 2D labeling center

Manually label your data or automate your labeling with the prediction tool. Select samples and create custom datasets for training and testing your models.

Learn more

Get a better overview of your models and trainings

Use metrics to compare training performance, view project details, and get overviews of the training settings and data.

Learn more

Test your models with the advanced setup in the test center

Use the new test center to test your models against train and validation data splits, custom datasets created in the labeling center, or prediction sets.

Learn more

Known limitations

General

  • The Robovision AI UI has been optimized for the browser size of 1920x1080.

Browser support

  • The Robovision AI platform has been designed and validated for Google Chrome 85 and Mozilla Firefox 77 or later.
  • In Google Chrome, training metrics and a final validation score might not be displayed if an ad blocker is used. To prevent this, mark the Robovision AI URL as trusted in the Google Chrome settings.

Backward compatibility

  • Backward compatibility with Robovision AI versions 3.x and 4.x is not foreseen. But upon request, Robovision will provide the needed assistance and conversion scripts.

Images

  • Types supported: In general and with respect to the model testing functionality, the following image types are supported: JPEG, JPG, PNG, TIFF, BMP, GIF, including a 4th transparency channel. EXIF orientation metadata is supported.
  • File names must contain only Latin (ASCII) characters. There are known rendering, packing, and backup/restore issues with file names/object keys that contain non-Latin characters.

Labeling

2D labeler performance (in particular the Magnetic lasso and Grab cut tools) may degrade for high-resolution images.