Closed ValerianRey closed 1 year ago
@ValerianRey
Thanks for the query. Appreciate your interest in our work.
Your understanding is correct:
feature_extractor
is the pre-trained network.classifier
is just a task head that supports an arbitrary number of labels.We are very busy with a few upcoming deadlines right now. If you wish to make a pull request, very happy to take a look and merge it in :D
Thanks for your answer! I made a PR. Hopefully my explanation is accurate enough!
Hi! First of all, thanks for this high quality and open research!
I ran the usage example shown in the
README.md
:I have trouble understanding exactly what the harnet models are. I understand that they are instances of
sslearning.models.accNet.Resnet
, and my understanding is the following:feature_extractor
part was pre-trained using multi-task SSL on UK-Biobank dataset, as explained in your paperclassifier
part is not trained at all, and we have to train it on any labelled classification dataset (what makes me understand this is that we can select any numberclass_num
).Is my understanding correct? Also, would it be possible to write this information next to the usage example?
Thanks a lot in advance :)