Wolowolo commited on
Commit
3c854b1
·
verified ·
1 Parent(s): d948683

Create FF++_o-c23_VIT-B/README.md

Browse files
pretrained_models/FF++_o-c23_VIT-B/README.md ADDED
@@ -0,0 +1 @@
 
 
1
+ fsfm-3c_vit_base_patch16 pre-trained on FF++_o (~43W facial image from train and val videos of the original YouTube subset in FaceForensics++ c23/HQ version, extract all frames) for 400 epochs.