Deepfake detector is a tool capable of detecting facially altered videos using ResNext and LSTM networks.
- The model is trained using over 700 videos and we achieved a prediction accuracy of 90%.
- We also created a user-friendly web application using Django allowing users to upload videos for deepfake detection.
-
CUDA version >= 10.0 for GPU
-
GPU Compute Capability > 3.0
-
Required modules are listed in the requirements.txt
Python >= v3.6
Django >= v3.0
download link: https://developer.nvidia.com/cuda-12-1-0-download-archive
python manage.py runserver