Robovision AI 5.1 release notes¶

Release date: June 23, 2023

What's new¶

YOLOv5 and SOLOv2 project types now support empty annotations. In the label center, you can assign an empty annotation to a sample that does not contain the classes existing in the project. For more information, see Work with empty annotations.

When creating datasets in the label center, you can now choose the Annotation by member option to create a dataset with annotations by a certain user.
In the thumbnails and list views of the label center, you can now sort your samples by name and import date.
Now, in the Status section of the label center, if your sample is displayed in blue, it means the sample has been labeled by the other user.

When your Robovision AI license expires, you will not able to create projects or perform other actions in the platform. The respective buttons will be disabled and the hint on hover will now display the reason why.

We have substantially improved the performance in the label center. Now, when working with large datasets of (annotated and unannotated) samples, the following works faster:
- Saving and loading mask annotations.
- Data loading in the thumbnails view.
- Switching views.
In the label center, you can now update the color of your classes.
In the label center, we have improved the filtering behavior as follows:
- The Clear button next to filters or chart setup now clears the setup for the respective section.
- If the chart filtering is applied to the already filtered data, you will get notified about that.
- If you change your annotations while keeping a chart open, you will be prompted to refresh the chart.

We have fixed the issue with project naming. Now, you cannot create projects with the same name but different capitalization.

We have improved the training statuses and their indicators. For more information, see Train models.
On the model details page, you can now view the data used for training organized into separate sections—training and validation data.
The training score, as one of the most important characteristics of a model, has been made to stand out both on the project and model details pages.
You can now start a training if your project contains no imports, but has datasets created in the label center. The training can be started on the project details page, using the Train tab in the upper-right corner of the platform, or in the label center.
To speed up the training process of SOLOv2 and YOLOv5 models, we have introduced dataloaders and caching.

When testing models, the datasets used for testing used to get cloned. This issue has been fixed.
The test progress is now displayed in stages. For more information, see Test models.

The Robovision AI UI has been optimized for the browser size of 1920x1080.
You will be logged out of the platform if your data import has been in the Uploading stage for more than an hour.

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.
In Google Chrome, the thumbnail view can load slowly if you have password managers like Lastpass activated. To prevent this, disable the extension or work in a guest profile window.

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.

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 4^th 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.

2D labeler performance (in particular the Magnetic lasso and Grab cut tools) may degrade for high-resolution images.
You may face the following issues when using the Prediction tool in the label center:
- The prediction process gets hidden if you leave the label center. To view it again, click the Prediction tool.
- The predicted labels are not added to the samples as the prediction process is running.
- The Status section is not updated as the prediction process is running.

You cannot edit or delete tags in the test center, although these options are available.