Name		Name	Last commit message	Last commit date
parent directory ..
01-ETL-with-NVTabular.ipynb		01-ETL-with-NVTabular.ipynb
02-End-to-end-session-based-with-Yoochoose-PyT.ipynb		02-End-to-end-session-based-with-Yoochoose-PyT.ipynb
03-Session-based-Yoochoose-multigpu-training-PyT.ipynb		03-Session-based-Yoochoose-multigpu-training-PyT.ipynb
README.md		README.md

README.md

End-to-end session-based recommendation

These end-to-end example notebooks focus on the following:

Preprocessing the Yoochoose e-commerce dataset.
Generating session features with on GPU.
Using the NVTabular dataloader with PyTorch.
Training a session-based recommendation model with a Transformer architecture (XLNET).
Exporting the preprocessing workflow and trained model to Triton Inference Server (TIS).
Sending request to TIS and generating next-item predictions for each session.

Refer to the following notebooks:

ETL with NVTabular
End-to-end session-based recommendation: PyTorch