#
Dashboard
The dashboard is the main screen of the application. It contains information about recently added datasets, trainings and manipulations, presented in the form of easy-to-read tables.
#
Recently used datasets
Information on recently processed datasets:
- dataset name,
- date of creation,
- date of last update,
- number of images in the dataset,
- list of categories assigned to the dataset.
#
Recent manipulations
Information on new datasets recently generated by the manipulator:
- dataset name,
- date of creation,
- start time,
- working time,
- number of images generated.
#
Recent trainings
Information on recently trained neural network models:
- training name,
- date of creation,
- start time,
- working time,
- type of training (i.e. detection or classification),
- framework used,
- pretrained model.
#
Recent conversions
Information on recent conversions:
- model name,
- creation time,
- start time,
- working time,
- hardware name.
#
Recent predictions
Information on recent predictions:
- dataset name - the dataset on which you made the prediction,
- model name - the model you used for prediction,
- creation time - the queue time,
- start time - the task start time,
- working time - the time elapsed from the start to finish,
- total images - the total number of images from the dataset to be analyzed,
- predictions over minimum confidence - selected predictions that exceeded the minimum confidence threshold of all predictions,
- total predictions - all predictions obtained on the analyzed images,
- images with errors - images that for some reason could not be processed by the predictor.
#
Recent notifications
Collection of notifications about successfully completed tasks:
- notification type,
- task completion time,
- task name,
- full message
- details.
#
Recent errors
Collection of notifications about tasks that have failed to be completed:
- error type,
- task failure time,
- task name,
- message describing the error,
- details.
#
Working with table records
Each table consists of five most recently processed records. Clicking on a record will redirect you to a detailed record view.
When processing a dataset, training or manipulation, a progress bar will appear in the Status
column of each table. Below the progress bar, you can track the current stage of the process, as shown in the figure below.
The records cannot be accessed (neither edited nor viewed) while the process is running.
When the process is complete, a notification will appear and the record will be unlocked.