Training Models

Models Library Tab

To train models and to see trained models history, click on the Library tab in Models section of the navigation bar. You will see a listing of all the models, the different versions that you have trained, their status, a first indicator on their performances and a few useful links.

Models and Model Versions

When working on a project, a model corresponds to a specific set of concepts. Adding or deleting a concept changes the model that you are building because it implies that you are modeling the problem differently. Nevertheless, adding new images to the project only adds data but does not alter the model.

This means that as long as the set of concepts is unchanged, you can train new neural networks that will be new model versions of the same model. All model versions for a given model are grouped under the same tab and the number of concepts associated is displayed on the tab. It makes it easy to confront the performances across the networks that are comparable, namely the model versions.

Train a model

To train a new model, click on Train a new model version, give a name to your model version, and decide on your parameters in the training options panel. By clicking on Create, you launch the training job.

The number of iterations is the number of passes (forward and backward) through the neural network, each pass using a batch size number of examples. The batch size is the number of training examples in one pass and can be found in the page Available architectures.

In the same way as the Add images, you will get a progress bar with the different steps required and a status on their advancement.

For more information on the advanced options panel, see our Guidebook on how to build your custom AI. For information on all the available models, click on the link below.

Once the training is launched, you can click on the model version to get more information on the training information and evaluate the performance of your model.