Getting Started with Movielens
The MovieLens25M is a popular dataset for recommender systems and is used in academic publications. Most users are familiar with the dataset and the example notebooks teach the basic concepts of NVTabular:
Learning NVTabular for using GPU-accelerated ETL (Preprocess and Feature Engineering).
Getting familiar with NVTabular’s high-level API.
Using single-hot/multi-hot categorical input features with NVTabular.
Using NVTabular dataloader with TensorFlow Keras model.
Using NVTabular dataloader with PyTorch.
Refer to the following notebooks:
Training a model: HugeCTR | TensorFlow | PyTorch
Serving with Triton Inference Server: HugeCTR | TensorFlow