pytorch-ignite/examples

Text Classification using Transformers

Priyansi opened this issue · 6 comments

Priyansi commented

The idea is to make a new beginner-level NLP tutorial combining this transformers example and this Text CNN notebook.

Update:
The idea has now been changed to using this 🤗 tutorial: https://huggingface.co/transformers/training.html for all the base code and then introducing Ignite for training. Ignite concepts are still derived from the TextCNN notebook.

LiviaCavalcanti commented

Hi! Do you guys have any other tutorial that you think would be nice to have here? I would like to help here

  • 👍1
sdesrozis commented

@LiviaCavalcanti Hi, thank you for your interest !

Your contribution would be great, very helpful and appreciated. Can you join our discord channel to discuss further ? See https://github.com/pytorch/ignite#communication

vfdev-5 commented

@LiviaCavalcanti we were also thinking about

@Priyansi can you open issues in this repository for cross-validation tutorial and hyperparameter tuning, please ?

  • 👍1
LiviaCavalcanti commented

@LiviaCavalcanti we were also thinking about

@Priyansi can you open issues in this repository for cross-validation tutorial and hyperparameter tuning, please ?

@vfdev-5 sounds good. I am interested in working on it. I am gonna wait for the issues right?

Priyansi commented

@Priyansi can you open issues in this repository for cross-validation tutorial and hyperparameter tuning, please ?

Cross-validation would work better as a how-to guide IMO #28 and here is the hyperparameter tuning tutorial #29 (no ideas on how to proceed with this right now).

LiviaCavalcanti commented

Thanks @Priyansi. I will think about how we could do it and bring the discussion to the issues. Does it work?

  • 👍1