The basic unit on which you are working is a project. Each project corresponds to a given set of images, a given set of concepts that you want to recognize and a given task among: classification, tagging or detection.
The home page for your organization is the listing of all the projects that have been created for this organization.
You can either select one of the projects that have already been created or create a new one.
To create a new project, you need to click on Add a new project and choose a name for it.
Now you can select the type of the project you want to create:
Classification: each image is labelled with exactly one concept and all concepts are then exclusive.
Tagging: each image is labelled positively or negatively for all concepts. A single image can then validate several concepts (or none).
Detection: concepts are localised in the image with bounding boxes. The information is then much richer as you can get several instances of a same concept in the image.
To design your image recognition system, you need to specify the concepts that you want to recognize. You can do so by clicking on New concept. You need to give a name to your new concept. You can also use existing concepts: the project is created and you can then import a JSON file in which the concepts and images are defined.
When selecting a given project, you arrive on its Home Page.
Here are the different elements that you will find on this page:
A navigation bar on the left hand side to navigate through all main functionalities.
On the central panel, you can see the number of images and the image distribution for each of your concepts.
Finally, you have the validation split function, which enables you to randomly select a portion of your images and put them in your validation set.
After changing your validation set, it is no longer possible to compare two models.