Inferencing without face detector leads to very low performance

[deepfakeLearnerHi]

Hi, I have my face dataset ready and wish not to perform duplicate face detection during inference as it brings huge time cost. However, when I commented out the face detection code and directly ran the inference on my cropped faces (using FFmpeg and dlib) from FF++, it seems that the performance dropped a lot. I wonder if there is a solution to it.

[githuboflk]

@tianyw23
Can you provide the relevant code? I was in a similar situation.

[Pudge-tao]

me too，I changed the face detector by Centerface and test on FF++ that got a terrible auc

[mapooon]

Hi,
The performance of the classifier strongly relies on the preprocess, e.g., cropping.
We recommend you use the same preprocess as we provide in this repository.

[leobryan]

me too，AUC shows around 0.50 for all cross datasets, wonder why