I want to train a deepfake detection model. The trian set has some attack types but the dev set has others that is not same as the attack in train set at all.
When I choose model by dev set, my model does not work well. How can I reach a better result?
New contributor
Nyoron 9 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.