Skip to content

BinaryGears/KerasDeepFakeDetection

Repository files navigation

How to use this

Download the latest version of Python 3.11



Run the MakeCSV.py file: python MakeCSV.py

The MakeCSV.py file will make a folder called "images" in the same directory as MakeCSV.py. The "images" folder will have a folder called "test", "train", and "val". Inside the "test" and "val" folders are more folders called "fake_image" and "real_image". Put the real and fake images you have in their proper folders.

Then run MakeCSV.py again: python MakeCSV.py

This will make a .csv file that contains all of the file names and classes of each image, which will be used when you run Main.py later.



TensorFlow recommends upgrading pip before installing TensorFlow.

Use the command: pip install --upgrade pip



This project uses TensorFlow and Keras.

Use the command: pip install tensorflow



You can then run the python file: python TrainReadyFile.py





Other .py Files:

OriginalPaperModel.py is the original CNN model from the paper.

KerasDeepFakeDetection Credits

Paper that this CNN model is in comparison to: https://doi.org/10.1109/ACCESS.2023.3251417

Paper that talks about Separable Convolution Layers: https://arxiv.org/pdf/1610.02357/1000

Paper that talks about PReLU: https://arxiv.org/pdf/1502.01852

Visualkeras citation: @misc{Gavrikov2020VisualKeras,

author = {Gavrikov, Paul},

title = {visualkeras},

year = {2020},

publisher = {GitHub},

journal = {GitHub repository},

howpublished = {\url{https://github.com/paulgavrikov/visualkeras}},

}

Link to original repository: https://github.com/BinaryGears/KerasDeepFakeDetection/

About

Program I made for my CS capstone to detect Deepfakes

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages