DeepFake Detection in Face Images- Final Project Computer Vision (Fall 2023)

Objective: Use Convolutional Neural Networks to detect deepfakes in Face Images

Create Virtual Environment

The following commands can be used to create the conda environment and install all necessary dependencies:

python -m venv df_venv
pip install -r requirements.txt

Dataset

here. To install data on HPC, first generate the API token, then run the following command.

kaggle datasets download -d xhlulu/140k-real-and-fake-faces

Executing Experiments

Change path to data in the code

sbatch slurm_script.batch

Notes

This project was part of the coursework for the Computer Vision (Fall 2023) course at NYU. Contributors:

• Arunima Mitra (am13018@nyu.edu)
• Anoushka Gupta (ag8733@nyu.edu)
• Divyanshi Parashar (dp3635@nyu.edu)