NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.
![image](https://github.com/NVIDIA-Merlin/Merlin/assets/64394100/34ed91bb-86a6-42ed-a61b-f5b0ddfe67b8)
This InBatchSampler pram is only applicable to TwoTowerModel but not for the DLRM model right? For DLRM I need to feed both positive and negative samples for training and validate, is that correct?
❓ Questions & Help
Details
![image](https://github.com/NVIDIA-Merlin/Merlin/assets/64394100/34ed91bb-86a6-42ed-a61b-f5b0ddfe67b8) This InBatchSampler pram is only applicable to TwoTowerModel but not for the DLRM model right? For DLRM I need to feed both positive and negative samples for training and validate, is that correct?