1. Introduction

This projects aims in detection of video and image deepfakes using deep learning technique like EfficientNetB0.

2. Directory Structure:

For ease of understanding the project is structured in below format:

Deepfake_detection_using_deep_learning
    |--- Android app
    |--- Documentation
    |--- project local API
    |--- the model

♦ Documentation:

Here, you can find the documentation of our work beside a presentation which is considered as a summary of what was presented in the Documentation.

♦ The Model:

This directory consists of the step by step process of creating and training a deepfake detection model using our approach (EfficientNetB0).

The order which to run the model is:
    1. preprocessing
    2. deepfake_detection_train
    3. prediction

♦ project local API:

This directory consists of the application made with flask. In this app the user can upload the video or the image and submit it to the model for prediction. After that the prediction result will be displayed.

♦ Android app:

This directory contains a zipped file of the android version of the project. To be able to use it, you need first to download it and unzip it then open it with android studio.

3. Demo:

you can find the demo of the project here: https://youtu.be/M0NTPM9lnxo