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
233 stars 60 forks source link

no faces detected when run the detect_faces.py #43

Closed Hezhexi2002 closed 1 year ago

Hezhexi2002 commented 1 year ago

@davide-coccomini Hi,sorry to bother you here,but I meet a problem which shown below in the screenshot: image there is no faces detected in the DFDC dataset even when I set the threshold of MTCNN very low,and here is the structure of my data: image as you can see,I etracted part of the whole DFDC dataset there because I haven't downloaded all of them yet,However,I checked the code in detect_faces.py and found that the script will traverse the directory under dfdc and then read the video from the sub-directory.so I was confused why it can't detected any faces from the video,so is there something wrong with my data_path?hope you can give me some advice!:-)

Hezhexi2002 commented 1 year ago

@davide-coccomini Hi,sorry to bother you here,but I meet a problem which shown below in the screenshot: image there is no faces detected in the DFDC dataset even when I set the threshold of MTCNN very low,and here is the structure of my data: image as you can see,I etracted part of the whole DFDC dataset there because I haven't downloaded all of them yet,However,I checked the code in detect_faces.py and found that the script will traverse the directory under dfdc and then read the video from the sub-directory.so I was confused why it can't detected any faces from the video,so is there something wrong with my data_path?hope you can give me some advice!:-)

Update:I changed the data_path of detect_faces.py into the directory of the dfdc video and try again,it seems like the model detected some faces and generate a jsom file in the box folder but then the process is killed shown in the screenshot below： image so I wonder if it is due to the memory limit I set to my WSL2: image I will change it to 8GB and see if it works,But I would still like to get some advice from you!:-)

Hezhexi2002 commented 1 year ago

@davide-coccomini Hi,I'm very glad to tell you that the detect_faces.py works well after I increase the memory limit up to 8GB: image I will close this issue afterwards