Skip to content

Robovision AI 5.8 release notes

Robovision AI 5.8.2

Release date: February 10, 2025

Bug fixes

  • The GPU usage issue for YOLOv8 and PIDNet algorithms has been resolved.

Known limitations

General

  • The Robovision AI UI has been optimized for the browser size of 1920x1200.
  • If the storage is full, some functions may become unavailable, for example, saving annotation or training a model.
  • When upgrading to a new version, new algorithm versions are installed, while preserving the existing ones. Existing projects will be updated to utilize the new algorithms.
  • If the terms and conditions change, you will not be prompted to read and accept them again.

  • Notifications may be missing in specific cases, such as:

    • When copying of annotations fails because the storage is almost full.
    • When the connection between two Robovision AI platforms is lost during an ongoing data transfer.
    • When an inference setup import fails due to nearly full storage.

  • The Show all datasets button on the project details page redirects to the label center instead of the dedicated Datasets page.

Browser support

  • The Robovision AI platform has been designed and validated for Google Chrome 85 or later.
  • You can transfer data between Robovision AI platforms only in Chromium-based browsers (Google Chrome, Microsoft Edge, and more).
  • 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.
  • When using Google Chrome, you might experience issues in the label center. As a quick fix, reset your browser 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.

Project management

  • You can't delete a project if it has running processes.
  • If you try to delete a project that contains a model or dataset used in another project, the deletion process stops once it encounters the shared elements. This results in an incomplete deletion when some elements still remain in the project.

Data upload

  • In general and with respect to the model testing functionality, the following image types are supported: JPG, JPEG, PNG, 8-bit TIF and 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.
  • You will be logged out of the platform if your data import has been in the Uploading stage for more than an hour.
  • If you leave the project details page during an ongoing data import, the import process disappears from the page.
  • Limited functionality projects: You can still import data if the label center is empty.

Branding and brand assets

  • Upon upgrading to a newer version, Robovision AI may include new UI text that has not been customized. To ensure alignment, export the template containing the UI text and review for any necessary updates (see step 3 in Change brand assets).

Labeling

  • 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.
    • When you delete annotations from samples after testing a model, and then filter by unannotated samples and run a prediction, the Prediction tool does not add annotations to those samples.

  • If you select more than 100 samples in the label center, the Selected annotations panel on the right includes no information about individual samples. As a result, you will not be able to copy or delete individual annotations.

  • When copying or replacing annotations for multiple samples, the same source should be selected for each sample (for example, annotations from one particular member or one prediction job).
  • EfficientNet: When you re-annotate already annotated samples in bulk, you will not be notified that existing annotations will be overwritten.
  • YOLOv8+ instance segmentation: When you select a few predictions on a sample and remove them in the right panel with the delete button, all predictions for that sample get deleted instead of only the selected ones.

Datasets

  • If you haven't added any annotations to the selected samples, you won't be able to create a dataset, even though you can select your name under Labels by.

Pagination

  • In all views except the single view, a maximum of 100 samples is displayed per page. If you select samples and then go to another page, these samples will no longer be selected.
  • In the test center, you can't select samples beyond the current page (more than 100 samples). The same applies when you view samples in a dataset.

Classes

  • In the label center, it is possible to create a class with a name that is just a space.
  • The class name is not saved if you collapse the Classes section without pressing Enter.
  • After annotated data is imported, system classes from that import do not appear on the Classes page until the label center of that project is opened.
  • On the Classes page, clicking the Color column to sort classes may not correctly reorder them by color.

Charts

  • Class distribution:

    • Label and test centers: If you apply a filter when the chart is already open, the filter isn't considered. To refresh the chart, click Clear in the upper-right corner of the Chart setup panel, and then set up the chart again.

  • Confusion matrix:

    • In both the UI and exported CSV files, percentages are rounded to whole numbers.
    • When setting up the confusion matrix, you can select the same user for both "Labels by (x-axis)" and "Labels by (y-axis)".

    • Label center:

      • If you apply a filter when the chart is already open, the filter isn't considered. To refresh the chart, click Clear in the upper-right corner of the Chart setup panel, and then set up the chart again.
      • When you generate the chart for filtered data, some information in the chart might be inaccurate.

    • Test center:

      • YOLOv8+: For some samples, no model annotations are displayed in the chart, even though the annotations exist.
      • The chart doesn't consider the filters you have applied—the number and percentage of samples labeled with a certain class is incorrect. To view the actual number of samples, you'll need to click the needed cell.
      • SOLOv2, YOLOv5: When a test compares two models or different parameters of the same model, more than one matrix may be generated.

  • Wafer map:

    • The wafer map chart is optimized for the browser size of 1920x1080 in full-screen mode. To enter full-screen mode, press F11.
    • When the wafer map contains more than 100,000 samples, selection and filtering within the chart may affect performance and increase the loading time.
    • Classes displayed on the wafer map may differ from those shown in the thumbnails view for the same samples. This difference occurs because the wafer map currently applies filtering constraints differently than the thumbnails view.

Model training

  • PIDNet: When labeling a consistent area with the ignore class, the model might predict every class in those areas. To avoid this, ensure there is some variation in the areas labeled as ignore.
  • PIDNet: If the entered batch size is too large, no validation message is displayed, and the training cannot be started.
  • YOLOv8+: Subtle differences in score calculations during model validation and in the test center may result in discrepancies between the scores, even when using the same settings and data.
  • During training setup, the Add model button is enabled even if there are no models available for transfer learning.
  • When you stop and delete a training that had a custom name, the next training you set up will have the same custom name instead of the default one.

Model testing

  • If you test a model on tagged data without comparison, the test data in the test center may disappear after you unassign that tag. However, the training center will still display the correct number of samples used in the test.
  • Filter by class returns no results if the class exists in the ground truth but is absent in the predictions.
  • YOLOv5: If a test is set up with a confidence threshold of 0, it will automatically run with a threshold of 0.001 instead. This temporary workaround prevents the test from failing.
  • The test process will not start if the test name contains exactly 255 characters.
  • Tests fail if the dataset includes samples that have been deleted.

Inferences

  • You can run only one camera inference at a time.
  • You can't rename a running inference. Wait for the inference to stop or stop it manually before renaming.
  • If you stop an inference within the first minute of this first run, inference logs will not be available.
  • SOLOv2: During inference setup, you can set the inference parameters that are outside of the available range. Despite this, the inference will run with the parameters within the range.
  • It is possible to delete a stopping inference from the project details page.
  • You cannot restart inferences in the Failed status. To proceed, stop the inference and start it again.
  • In an inference setup, repeatedly switching between imported models and then saving the setup may cause the platform to crash.
  • If your license expires, you cannot access the inference center to view details of inferences started while the license was active. Renew the license to regain access.

Import and export of data

  • If the import or export process is interrupted, it will restart from the beginning instead of resuming, potentially resulting in multiple notifications about the process start.

  • Data transfer from Robovision Edge or connected Robovision AI platform:

    • On the target Robovision AI platform, you won't receive notifications about data upload.
    • On the project details page of the target Robovision AI platform, you can't stop the data upload.
    • Exporting large numbers of samples to the connected platform may fail. To avoid this, export no more than 200,000 samples at a time.
    • If you delete an import while it's still in progress, some imported samples may not be deleted. These samples will appear in the label center, but they won't be associated with any import.
    • EfficientNet: During samples export, some samples may incorrectly show empty annotations. Once the data transfer is complete, the annotations will be updated, and the issue will no longer appear.
    • When data upload is in progress, the number of samples displayed above the sample preview in the label center may be out of sync with the number shown in the Imports group of the Filter panel.

  • Inference setups:

    • Imported models aren't displayed on the training details page and the Training center section of the project details page because trainings—not models—are shown there. However, you will still be able to select imported models for transfer learning, to set up a test, and more.
    • YOLOv8+ instance segmentation: Import of inference setups with YOLOv11 models may fail, especially if the network is interrupted. In most cases, the issue resolves itself once the network stabilizes.
    • You can import several models with the same name.

  • Samples:

    • If you don't change the default name, all exports in your project will share the same name.
    • Sample export or import, especially for more than 100 samples, may become stuck. To resolve this, manually resume the process.

Robovision AI 5.8.1

Release date: January 31, 2025

What's new

YOLOv8+

  • Robovision AI now supports the YOLOv8 and YOLOv11 algorithms:

    • YOLO Instance Segmentation v8+: Enhances instance segmentation by resolving performance issues and known limitations in SOLOv2.
    • YOLO Object Detection v8+: Improves object detection performance compared to YOLOv5.

  • You can choose between the YOLOv8 or YOLOv11 architecture as a training parameter.

  • To migrate from YOLOv5 or SOLOv2 to YOLOv8+, export the training data from an old project, import it in a new project, and train a new model.

Upcoming API changes

  • Starting with Robovision AI 5.9, ExampleStream models will require a project_id to be specified. This update will affect the following endpoints:

    • Creating example streams
    • Listing example streams
    • Listing job dependencies
    • Listing job artifacts
    • Listing deployment dependencies

Bug fixes

Model training

  • Disk usage limits no longer cause trainings with larger models to fail.

Model testing

  • PIDNet: Performance of comparison jobs in tests has been optimized for faster execution.
  • PIDNet: Previously, PIDNet masks had a slight positional shift during testing compared to training, especially when using larger images or reduced rescale factors. This issue has been resolved: predicted masks now align accurately, ensuring consistent performance across different image sizes and configurations.

WebRTC streams

  • WebRTC streams have been optimized to eliminate latency and dropped frames, resolving issues with freezing and interruptions in Google Chrome.

Known limitations

General

  • The Robovision AI UI has been optimized for the browser size of 1920x1200.
  • If the storage is full, some functions may become unavailable, for example, saving annotation or training a model.
  • When upgrading to a new version, new algorithm versions are installed, while preserving the existing ones. Existing projects will be updated to utilize the new algorithms.
  • If the terms and conditions change, you will not be prompted to read and accept them again.

  • Notifications may be missing in specific cases, such as:

    • When copying of annotations fails because the storage is almost full.
    • When the connection between two Robovision AI platforms is lost during an ongoing data transfer.
    • When an inference setup import fails due to nearly full storage.

  • The Show all datasets button on the project details page redirects to the label center instead of the dedicated Datasets page.

Browser support

  • The Robovision AI platform has been designed and validated for Google Chrome 85 or later.
  • You can transfer data between Robovision AI platforms only in Chromium-based browsers (Google Chrome, Microsoft Edge, and more).
  • 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.
  • When using Google Chrome, you might experience issues in the label center. As a quick fix, reset your browser 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.

Project management

  • You can't delete a project if it has running processes.
  • If you try to delete a project that contains a model or dataset used in another project, the deletion process stops once it encounters the shared elements. This results in an incomplete deletion when some elements still remain in the project.

Data upload

  • In general and with respect to the model testing functionality, the following image types are supported: JPG, JPEG, PNG, 8-bit TIF and 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.
  • You will be logged out of the platform if your data import has been in the Uploading stage for more than an hour.
  • If you leave the project details page during an ongoing data import, the import process disappears from the page.
  • Limited functionality projects: You can still import data if the label center is empty.

Branding and brand assets

  • Upon upgrading to a newer version, Robovision AI may include new UI text that has not been customized. To ensure alignment, export the template containing the UI text and review for any necessary updates (see step 3 in Change brand assets).

Labeling

  • 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.
    • When you delete annotations from samples after testing a model, and then filter by unannotated samples and run a prediction, the Prediction tool does not add annotations to those samples.

  • If you select more than 100 samples in the label center, the Selected annotations panel on the right includes no information about individual samples. As a result, you will not be able to copy or delete individual annotations.

  • When copying or replacing annotations for multiple samples, the same source should be selected for each sample (for example, annotations from one particular member or one prediction job).
  • EfficientNet: When you re-annotate already annotated samples in bulk, you will not be notified that existing annotations will be overwritten.
  • YOLOv8+ instance segmentation: When you select a few predictions on a sample and remove them in the right panel with the delete button, all predictions for that sample get deleted instead of only the selected ones.

Datasets

  • If you haven't added any annotations to the selected samples, you won't be able to create a dataset, even though you can select your name under Labels by.

Pagination

  • In all views except the single view, a maximum of 100 samples is displayed per page. If you select samples and then go to another page, these samples will no longer be selected.
  • In the test center, you can't select samples beyond the current page (more than 100 samples). The same applies when you view samples in a dataset.

Classes

  • In the label center, it is possible to create a class with a name that is just a space.
  • The class name is not saved if you collapse the Classes section without pressing Enter.
  • After annotated data is imported, system classes from that import do not appear on the Classes page until the label center of that project is opened.
  • On the Classes page, clicking the Color column to sort classes may not correctly reorder them by color.

Charts

  • Class distribution:

    • Label and test centers: If you apply a filter when the chart is already open, the filter isn't considered. To refresh the chart, click Clear in the upper-right corner of the Chart setup panel, and then set up the chart again.

  • Confusion matrix:

    • In both the UI and exported CSV files, percentages are rounded to whole numbers.
    • When setting up the confusion matrix, you can select the same user for both "Labels by (x-axis)" and "Labels by (y-axis)".

    • Label center:

      • If you apply a filter when the chart is already open, the filter isn't considered. To refresh the chart, click Clear in the upper-right corner of the Chart setup panel, and then set up the chart again.
      • When you generate the chart for filtered data, some information in the chart might be inaccurate.

    • Test center:

      • YOLOv8+: For some samples, no model annotations are displayed in the chart, even though the annotations exist.
      • The chart doesn't consider the filters you have applied—the number and percentage of samples labeled with a certain class is incorrect. To view the actual number of samples, you'll need to click the needed cell.
      • SOLOv2, YOLOv5: When a test compares two models or different parameters of the same model, more than one matrix may be generated.

  • Wafer map:

    • The wafer map chart is optimized for the browser size of 1920x1080 in full-screen mode. To enter full-screen mode, press F11.
    • When the wafer map contains more than 100,000 samples, selection and filtering within the chart may affect performance and increase the loading time.
    • Classes displayed on the wafer map may differ from those shown in the thumbnails view for the same samples. This difference occurs because the wafer map currently applies filtering constraints differently than the thumbnails view.

Model training

  • PIDNet: When labeling a consistent area with the ignore class, the model might predict every class in those areas. To avoid this, ensure there is some variation in the areas labeled as ignore.
  • PIDNet: If the entered batch size is too large, no validation message is displayed, and the training cannot be started.
  • YOLOv8+: Subtle differences in score calculations during model validation and in the test center may result in discrepancies between the scores, even when using the same settings and data.
  • During training setup, the Add model button is enabled even if there are no models available for transfer learning.
  • When you stop and delete a training that had a custom name, the next training you set up will have the same custom name instead of the default one.

Model testing

  • If you test a model on tagged data without comparison, the test data in the test center may disappear after you unassign that tag. However, the training center will still display the correct number of samples used in the test.
  • Filter by class returns no results if the class exists in the ground truth but is absent in the predictions.
  • YOLOv5: If a test is set up with a confidence threshold of 0, it will automatically run with a threshold of 0.001 instead. This temporary workaround prevents the test from failing.
  • The test process will not start if the test name contains exactly 255 characters.
  • Tests fail if the dataset includes samples that have been deleted.

Inferences

  • You can run only one camera inference at a time.
  • You can't rename a running inference. Wait for the inference to stop or stop it manually before renaming.
  • If you stop an inference within the first minute of this first run, inference logs will not be available.
  • SOLOv2: During inference setup, you can set the inference parameters that are outside of the available range. Despite this, the inference will run with the parameters within the range.
  • It is possible to delete a stopping inference from the project details page.
  • You cannot restart inferences in the Failed status. To proceed, stop the inference and start it again.
  • In an inference setup, repeatedly switching between imported models and then saving the setup may cause the platform to crash.
  • If your license expires, you cannot access the inference center to view details of inferences started while the license was active. Renew the license to regain access.

Import and export of data

  • If the import or export process is interrupted, it will restart from the beginning instead of resuming, potentially resulting in multiple notifications about the process start.

  • Data transfer from Robovision Edge or connected Robovision AI platform:

    • On the target Robovision AI platform, you won't receive notifications about data upload.
    • On the project details page of the target Robovision AI platform, you can't stop the data upload.
    • Exporting large numbers of samples to the connected platform may fail. To avoid this, export no more than 200,000 samples at a time.
    • If you delete an import while it's still in progress, some imported samples may not be deleted. These samples will appear in the label center, but they won't be associated with any import.
    • EfficientNet: During samples export, some samples may incorrectly show empty annotations. Once the data transfer is complete, the annotations will be updated, and the issue will no longer appear.
    • When data upload is in progress, the number of samples displayed above the sample preview in the label center may be out of sync with the number shown in the Imports group of the Filter panel.

  • Inference setups:

    • Imported models aren't displayed on the training details page and the Training center section of the project details page because trainings—not models—are shown there. However, you will still be able to select imported models for transfer learning, to set up a test, and more.
    • YOLOv8+ instance segmentation: Import of inference setups with YOLOv11 models may fail, especially if the network is interrupted. In most cases, the issue resolves itself once the network stabilizes.
    • You can import several models with the same name.

  • Samples:

    • If you don't change the default name, all exports in your project will share the same name.
    • Sample export or import, especially for more than 100 samples, may become stuck. To resolve this, manually resume the process.

Robovision AI 5.8

Release date: December 17, 2024

What's new

Data capture

  • You can now set up and manage cameras for data recording directly within the Robovision AI platform. This new feature allows you to seamlessly integrate camera feeds into your projects, enhancing your ability to monitor and record data effectively. See Camera management.

    Cameras

  • You can now record real-time data directly from a camera. Data can be captured:

    • At intervals configured on the camera.
    • In response to an API signal.

    Recording

  • You can also define metadata in key-value pairs for your recorded data, such as Location: factory floor 1. This metadata will be associated with each sample from your recording session.

    Recorded sample metadata

  • Recording logs are available for download, allowing you to verify data integrity or troubleshoot issues if a recording session fails.

  • A video stream preview from your cameras is now supported. See Build a WebRTC stream viewer.
  • GStreamer usage: This release includes the use of modified GStreamer plugins for video processing. In accordance with license requirements, the corresponding source code is available upon request.

Inference

  • You can now download the logs of a running, finished, or stopped inference.

  • Camera inference:

    • A new inference type—direct camera inference—is now available for on-premises installations. Depending on your installation type, you can use either API or camera inference.

      Camera inference center

    • During inference setup, you can specify a webhook URL to which Robovision AI will send predictions and images. This URL is the address of a custom application or a third-party service that will receive and process the data. For more details, see Use webhooks with camera inference.

Other improvements

  • Browser tab titles now display the corresponding page names.
  • Logs now include platform and SDK version details.

Bug fixes

Label center

  • Previously, it was possible to save a tag with an existing name by pressing Enter in the Edit tags sidebar. This issue is now fixed.
  • Issues with annotations visibility in the single view have been resolved.
  • Sorting in the Classes section is now case-insensitive, ensuring classes are displayed in the correct order.
  • Previously, pressing the arrow keys while editing an import name would navigate to another page in the label center. This issue has been resolved.
  • In the single view, when you delete a tag from a filtered sample, you will not be redirected to the first sample.
  • When an import is deleted in the label center, it is no longer listed on the project details page.
  • Label center setup: Previously, changes to the label opacity, sample brightness, or contrast were saved even if you clicked Cancel. This issue has been resolved.

Training center

  • PIDNet: Training sessions no longer stop prematurely when early stopping is turned off.

Test center

  • Assigning a newly created tag in the test center now applies it only to the selected test data, instead of to all samples in the project.
  • Test results exported in the CSV format now also include empty annotations.
  • SOLOv2, YOLOv5: When you adjust the slider to view a confusion matrix for a different confidence threshold, the current filter is now cleared automatically.
  • PIDNet: Custom metrics are now properly visualized in the test center.

Inference

  • Inferences are no longer stuck in the Stopping status.

Data exchange between Robovision AI platforms

  • If a user connected to the platform is deleted, the list of projects or inferences during data exchange no longer appears empty. Instead, an error message now indicates that the connection to the platform failed.
  • Stopping the import of an inference setup now works as expected.
  • Exports and imports now automatically resume once the connection is restored.

Resources

  • On the All resources page, the date and time of the last inference activity are now displayed accurately.
  • KRF export processes now appear on the All resources page.

Other bug fixes

  • Spaces are no longer removed from the project name when you type quickly.
  • Notifications about full disk storage have been improved.
  • When a page is not found, the correct error message is now displayed.
  • Deleted algorithm extensions are no longer displayed on the UI.

Known limitations

General

  • The Robovision AI UI has been optimized for the browser size of 1920x1200.
  • You will be logged out of the platform if your data import has been in the Uploading stage for more than an hour.
  • If the storage is full, some functions may become unavailable, for example, saving annotation or training a model.
  • When upgrading to a new version, new algorithm versions are installed, while preserving the existing ones. Existing projects will be updated to utilize the new algorithms.
  • If the terms and conditions change, you will not be prompted to read and accept them again.
  • You can't delete a project if it has running processes.

  • Notifications may be missing in specific cases, such as:

    • When copying of annotations fails because the storage is almost full.
    • When the connection between two Robovision AI platforms is lost during an ongoing data transfer.
    • When an inference setup import fails due to nearly full storage.

  • The Show all datasets button on the project details page redirects to the label center instead of the dedicated Datasets page.

Browser support

  • The Robovision AI platform has been designed and validated for Google Chrome 85 or later.
  • You can transfer data between Robovision AI platforms only in Chromium-based browsers (Google Chrome, Microsoft Edge, and more).
  • 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.
  • When using Google Chrome, you might experience issues in the label center. As a quick fix, reset your browser 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: JPG, JPEG, PNG, 8-bit TIF and 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.

Branding and brand assets

  • Upon upgrading to a newer version, Robovision AI may include new UI text that has not been customized. To ensure alignment, export the template containing the UI text and review for any necessary updates (see step 3 in Change brand assets).

Label center

  • 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.

  • If you select more than 100 samples in the label center, the Selected annotations panel on the right includes no information about individual samples. As a result, you will not be able to copy or delete individual annotations.

  • When copying or replacing annotations for multiple samples, the same source should be selected for each sample (for example, annotations from one particular member or one prediction job).
  • EfficientNet: When you re-annotate already annotated samples in bulk, you will not be notified that existing annotations will be overwritten.
  • If you haven't added any annotations to the selected samples, you won't be able to create a dataset, even though you can select your name under Labels by.
  • Limited functionality projects: You can still import data if the label center is empty.

Pagination

  • In all views except the single view, a maximum of 100 samples is displayed per page. If you select 1–100 samples within a page and then go to another page, these samples will no longer be selected.
  • In the test center, you can't select samples beyond the current page (more than 100 samples). The same applies when you view samples in a dataset.

Classes

  • In the label center, it is possible to create a class with a name that is just a space.
  • The class name is not saved if you collapse the Classes section without pressing Enter.
  • After annotated data is imported, system classes from that import do not appear on the Classes page until the label center of that project is opened.

Charts

  • Class distribution:

    • Label and test centers: If you apply a filter when the chart is already open, the filter isn't considered. To refresh the chart, click Clear in the upper-right corner of the Chart setup panel, and then set up the chart again.

  • Confusion matrix:

    • In both the UI and exported CSV files, percentages are rounded to whole numbers.
    • When setting up the confusion matrix, you can select the same user for both "Labels by (x-axis)" and "Labels by (y-axis)".

    • Label center:

      • If you apply a filter when the chart is already open, the filter isn't considered. To refresh the chart, click Clear in the upper-right corner of the Chart setup panel, and then set up the chart again.
      • When you generate the chart for filtered data, some information in the chart might be inaccurate.

    • Test center:

      • The chart doesn't consider the filters you have applied—the number and percentage of samples labeled with a certain class is incorrect. To view the actual number of samples, you'll need to click the needed cell.
      • SOLOv2, YOLOv5: When a test compares two models or different parameters of the same model, more than one matrix may be generated.

  • Wafer map:

    • The wafer map chart is optimized for the browser size of 1920x1080 in full-screen mode. To enter full-screen mode, press F11.
    • When the wafer map contains more than 100,000 samples, selection and filtering within the chart may affect performance and increase the loading time.

Training center

  • PIDNet: An area labeled with the ignore class isn't ignored by the model training.
  • PIDNet: If the entered batch size is too large, no validation message is displayed, and the training cannot be started.
  • During training setup, the Add model button is enabled even if there are no models available for transfer learning.
  • When you stop and delete a training that had a custom name, the next training you set up will have the same custom name instead of the default one.

Test center

  • If you test a model on tagged data without comparison, the test data in the test center may disappear after you unassign that tag. However, the training center will still display the correct number of samples used in the test.
  • Filter by class returns no results if the class exists in the ground truth but is absent in the predictions.
  • YOLOv5: If a test is set up with a confidence threshold of 0, it will automatically run with a threshold of 0.001 instead. This temporary workaround prevents the test from failing.
  • The test process will not start if the test name contains exactly 255 characters.
  • Tests fail if the dataset includes samples that have been deleted.

Inference

  • You can run only one camera inference at a time.
  • A running inference gets interrupted when renamed. To avoid this, wait for the inference to stop or stop it manually before renaming.
  • If you stop an inference within the first minute of this first run, inference logs will not be available.
  • SOLOv2: During inference setup, you can set the inference parameters that are outside of the available range. Despite this, the inference will run with the parameters within the range.
  • It is possible to delete a stopping inference from the project details page.
  • You cannot restart inferences in the Failed status. To proceed, stop the inference and start it again.
  • In an inference setup, repeatedly switching between imported models and then saving the setup may cause the platform to crash.
  • If your license expires, you cannot access the inference center to view details of inferences started while the license was active. Renew the license to regain access.

Import and export of data

  • If the import or export process is interrupted, it will restart from the beginning instead of resuming, potentially resulting in multiple notifications about the process start.

  • Data transfer from Robovision Edge or connected Robovision AI platform:

    • On the target Robovision AI platform, you won't receive notifications about data upload.
    • On the project details page, you can't stop the data upload.
    • Exporting large numbers of samples to the connected platform may fail. To avoid this, export no more than 200,000 samples at a time.
    • If you delete an import while it's still in progress, some imported samples may not be deleted. These samples will appear in the label center, but they won't be associated with any import.
    • EfficientNet: During samples export, some samples may incorrectly show empty annotations. Once the data transfer is complete, the annotations will be updated, and the issue will no longer appear.
    • When data upload is in progress, the number of samples displayed above the sample preview in the label center may be out of sync with the number shown in the Imports group of the Filter panel.

  • Inference setups:

    • Imported models aren't displayed on the training details page and the Training center section of the project details page because trainings—not models—are shown there. However, you will still be able to select imported models for transfer learning, to set up a test, and more.
    • You can import several models with the same name.

  • Samples:

    • If you don't change the default name, all exports in your project will share the same name.
    • Sample export or import, especially for more than 100 samples, may become stuck. To resolve this, manually resume the process.