Training on original Criterio Dataset.

[Karoljv]

Hey, I have a question about training DeepFM on originial dataset Criterio dataset. Is this possible with the code provided in the repository? Dataset presented in demo version has 19 colummns. I mean train_sample.csv, test_sample.csv etc. Are these columns from Criterio dataset? How can I use original Criterio dataset when the data from this dataset is numerical and the caterogical columns are hashed. How to handle no labels in test set?

[zhujiem]

Please follow the benchmark steps in BARS: say https://github.com/reczoo/BARS/tree/main/ctr_prediction/benchmarks/DeepFM/DeepFM_criteo_x1

[zhujiem]

If you have test set without labels, you can call model.predict() at https://github.com/reczoo/FuxiCTR/blob/main/fuxictr/pytorch/models/rank_model.py#L244