search

davide-coccomini / Combining-EfficientNet-and-Vision-Transformers-for-Video-Deepfake-Detection

Code for Video Deepfake Detection model from "Combining EfficientNet and Vision Transformers for Video Deepfake Detection" presented at ICIAP 2021.
https://dl.acm.org/doi/abs/10.1007/978-3-031-06433-3_19
MIT License
239 stars 60 forks source link

test the model in ff++ #53

Open wzk101 opened 8 months ago

wzk101 commented 8 months ago

ient_vit.pth" --config "configs/architecture.yaml" Namespace(batch_size=32, config='configs/architecture.yaml', dataset='DFDC', efficient_net=0, frames_per_video=30, max_videos=-1, model_path='cross_efficient_vit.pth', workers=10) Loaded pretrained weights for efficientnet-b0 Loaded pretrained weights for efficientnet-b0 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 700/700 [00:01<00:00, 395.95it/s] Predicting | | 1/700Traceback (most recent call last): File "test.py", line 269, in video_pred = video_faces_preds[0] IndexError: list index out of range

it seems the model cannot get preds， and I face this error while testing.