This project leverages deep learning to detect deepfake videos by training a Convolutional Neural Network (CNN) model. Using TensorFlow and the '1000 Videos Split' dataset from Kaggle, the model aims to distinguish real videos from deepfakes with high accuracy.
With the rise of deepfake technology, distinguishing real from fake media has become crucial. This project uses a CNN-based approach to identify manipulated videos, providing a foundation for detecting deepfakes effectively.
- Name: 1000 Videos Split
- Source: Kaggle
- Description: The dataset contains both real and manipulated videos, which are split into training, validation, and test sets.
data/: Directory for dataset files.models/: Saved models and checkpoints.notebooks/: Jupyter notebooks with exploratory data analysis and model development.scripts/: Scripts for data preprocessing, training, and evaluation.README.md: Project documentation.
- Clone the repository:
git clone https://github.com/yourusername/deepfake-detection