Skip to content

Latest commit

 

History

History
27 lines (23 loc) · 786 Bytes

README.md

File metadata and controls

27 lines (23 loc) · 786 Bytes

DeepFake Detection in Face Images

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

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

Done as part of the Computer Vision course by Prof. Rob Fergus @NYU Courant Fall 23