Matt comments

Repositories
Issues
Comments

Results 3 comments of


                                            Matt

[Feature]: Multiple GPU Training for MultiTask Learning

We are also trying to do this, it would really speed up our training up to 10 fold

Update the protobuf dependency?

it looks like this is holding us back from upgrading to `tensorflow 2.12.0` and using `protobuf 4` for any use case that requires `tensorflow-metadata`, or `tensorflow-datasets` which requires `tensorflow-metadata`

[Question]: How to do what MultiTagger used to do?

I was also wondering the same thing. We are using multitask training to train multiple `SequenceTagger` models, along with `TextClassifier` and `RelationExtractor` models, with shared embeddings. For inference, we would...