Dongjun Lee comments

Repositories
Issues
Comments

Results 14 comments of


                                            Dongjun Lee

Significant overfit on default hyperparameters on cornell-movie-dialogs config

Seq2Seq model has a problem that there is a gap between training and inference. You can check practical tips for training sequence-to-sequence models with attention in [this blog](https://awni.github.io/train-sequence-models/?utm_campaign=Revue%2520newsletter&utm_medium=Newsletter&utm_source=The%2520Wild%2520Week%2520in%2520AI) I don't...

Here's a suggestion

Sorry for late comment, I was so busy these days Thanks for your suggrestion. I'll check it.

Apple machine learning feed

Hi :) You're right. Thank you for letting me know. I can't find it either.

[Question] Is there anyway to speed up the prediction speed?

Are you run with `predict.py`? It is for 1-example inference. I think you need to use `evaluate` and increase batch_size.