This projects aims in detection of video deepfakes using deep learning techniques like RestNext and LSTM. We have achived deepfake detection by using transfer learning where the pretrained RestNext CNN is used to obtain a feature vector, further the LSTM layer is trained using the features. For more details follow the documentaion.
GNU General Public License v3.0
495
stars
164
forks
source link
About using another trained model with 100 frames #27
Thank you for your contribution!
By the way, I want to use another trained model named model_97_acc_100_frames_FF_data.pt but the application doesn't work. What should I do with the code?
Thank you for your contribution! By the way, I want to use another trained model named model_97_acc_100_frames_FF_data.pt but the application doesn't work. What should I do with the code?