Model Dashboard

Model dashboard user interface overview

Dashboard Information:

• Split name
• Experiment name
• Number of iterations
• Runtime
• Best Loss (Train & Validation)
• Problem - This is the type of model you want to use for the model building phase. It includes: Attribute prediction, Label class prediction, Object detection, Image tag prediction, Instance segmentation, Semantic segmentation.
• Creation date
• Created by - This helps to track which user is experimenting with a particular model.
• Images - This value gives an idea of the number of images (Total, Train, Test, Validation) that were used for a particular set of experiments/model types.
• Experiments - Total number of experiments a user has carried out for a model type.
• Under Manage Experiments, you can check the number of experiments tested by the user using a particular model type.
• Experiment status

Actions that can be performed after creating an experiment

• Deploy and export - This will link the user to the Deploy and export page of Model Playground
• See parameters - This will take the user inside the experiment section where the user can review the parameters used. (Read-only)
• Change color - Allows users to change colors used in different widgets for a particular experiment.
• Copy Experiment - Allows users to make a new experiment with all the same parameters from the experiment from which it is copied. Then, the user has the freedom to change some indivdual parameters in the new experiment.
• Delete experiment