search

yyk-wew / F3Net

Pytorch implementation of F3Net (ECCV 2020 F3Net: Frequency in Face Forgery Network)
148 stars 17 forks source link

About dataset split! #8

Open Nerdary opened 3 years ago

Nerdary commented 3 years ago

The FaceForensics++ dataset offers an official dataset split here, , but I am confused about the performance of Xception on the official split which is only about 75% ~ 80% on c40. However with the same training code, if I train Xception on my self-splitted dataset(72%-14%-14%, but FaceSwap/000_001.mp4 and NeuralTextural/000_001.mp4 might be splitted into train set and val set respectively for example), the performance is close to the results in all those papers which is about 86% ~ 89%. So could you please help me about which split are you using in this repo?

yyk-wew commented 3 years ago

Hi Nerdary. The result reported in this repo are obtained following the official split (exactly the json you mentioned). I haven't tried the random split as you mentioned, so unfortunately I have no idea why the results you got are hooked with the dataset split.