The lab notebooks will take you through:
Generating synthetic data of user interactions.
Preprocessing sequential data with NVTabular on GPU.
Using the NVTabular dataloader with PyTorch.
Training a session-based recommendation model with a Transformer architecture (XLNET).
Open JupyterLab by clicking on the Training Jupyter Notebooks link in the left-hand navigation pane.
The JupyterLab file navigation pane will contain two notebooks like the image below. Double-click on a notebook to open it in another tab. Complete each notebook in the series sequentially, beginning with the notebook numbered “01” and finishing with the notebook numbered “02”. Text in each notebook will guide you through the exercises.
If you want to edit a notebook to experiment with code changes, use the File -> Make a Copy menu item to create a new notebook and edit the copy. This will preserve the original notebook for reference.