finetuned_models/FF++_c23_32frames/README.md

Script for fine-tuning our FSFM-3C model for evaluation of cross-dataset deepfakes detection:

CUDA_VISIBLE_DEVICES=0,1 OMP_NUM_THREADS=1 python -m torch.distributed.launch --node_rank=0 --nproc_per_node=2 main_finetune_DfD.py \
    --accum_iter 1 \
    --apply_simple_augment \
    --batch_size 32 \
    --nb_classes 2 \
    --model vit_base_patch16 \
    --epochs 10 \
    --blr 2.5e-4 \
    --layer_decay 0.65 \
    --weight_decay 0.05 \
    --drop_path 0.1 \
    --reprob 0.25 \
    --mixup 0.8 \
    --cutmix 1.0 \
    --dist_eval \
    --finetune ../../pretrain/checkpoint/pretrained_models/VF2_ViT-B/checkpoint-400.pth \
    --finetune_data_path ../../../datasets/finetune_datasets/deepfakes_detection/FaceForensics/32_frames/DS_FF++_all_cls/c23 \
    --output_dir ./checkpoint/finetuned_models/FF++_c23_32frames