Skip to content
Vanshikaa-SainiPublic

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

3 Commits

Folders and files

Repository files navigation

Deepfake detection (paper re-implementation)

Python 3.10/3.11 recommended.

python -m venv .venv
.venv\Scripts\activate        (Mac/Linux: source .venv/bin/activate)
pip install -r requirements.txt
pip install torch torchvision   (use the exact command from pytorch.org for your GPU/CPU)

python deepfake.py "C:\path\to\dfdc-faces-of-the-train-sample" --smoke    # quick check (20 videos/class)
python deepfake.py "C:\path\to\dfdc-faces-of-the-train-sample"            # full run

The path is the folder that contains train/. Outputs go to ./work (figures, ablation.csv, weights). First run downloads dlib's 68-landmark model (needs internet). Preprocessing is cached after the first run. Everything the paper leaves unspecified is marked # ASSUMED in the CFG block of deepfake.py.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages