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
237 stars 60 forks source link

extract error #25

Closed shui-tian-ju-shi closed 2 years ago

shui-tian-ju-shi commented 2 years ago

image I used the Celeb dataset, but changed the format of the Celeb dataset to f ++ to be consistent with your code. The folder architecture for storing videos and the folder architecture for storing face pictures are shown in the figure.The photo with the train folder is the folder that holds the face image. image

shui-tian-ju-shi commented 2 years ago

I confirmed that the number of files in the box is equal to the number of my videos by the command you gave, but I encountered the error as shown in the picture. Why did I get this wrong? When I deleted the video he reported the error and ran it again, he suggested another video encountered the same error. I don't think I can delete it one by one according to his hints, so I would like to request your help

shui-tian-ju-shi commented 2 years ago

I just added the absolute path to the folder where the video is stored and the folder where the images are extracted to the extract.py file you gave me,and I didn't make any other changes.

davide-coccomini commented 2 years ago

Hi. Could you please share the exact command you used and the error shown?

shui-tian-ju-shi commented 2 years ago

image This is the error

shui-tian-ju-shi commented 2 years ago

image The red line is the absolute path THAT I added,Corresponding to the folder structure on the left

shui-tian-ju-shi commented 2 years ago

image This is the command to check the number of files in the box

shui-tian-ju-shi commented 2 years ago

the number of my video is also the same 1200.