training data

[ss880426]

Have you ever tried to use all deepfake methods of ff++ for training? thanks

[beuve]

Do you mean all methods at once?

[ss880426]

yes

[ss880426]

Excuse me How do you calculate your auc? thanks

[beuve]

Regarding training on all methods at once, we will soon publish a preprint targeting detection of all deepfake at once with the FF++ dataset (This paper will be announced on this repo).

for the AUC, we used the (roc_auc_score)[https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html] function from Sklearn:

roc_auc_score(labels, predict, average='macro'))

[ss880426]

Thank you！！