How to deal with the multiple lables?

GitHub-HongweiZhang / prediction-flow

Deep-Learning based CTR models implemented by PyTorch

MIT License

248 stars 51 forks source link

How to deal with the multiple lables? #33

Open jellchou opened 2 years ago

jellchou commented 2 years ago

I'm frustrated when I realize the ESMM model based on prediction-flow, it has two labels which are click and post-click-conversation lables. It seems like create_dataloader_fn should be rewriten?

GitHub-HongweiZhang commented 2 years ago

@jellchou

Yes, create_dataloader_fn need to be rewriten.