GitHub - yaseeng-md/Explicit-Content-Detection: This Project focus on detectin the Explicit Images using ViTs. I have used ViT with Feed Forward Patch extraction techqniqe and Conv based Patch Extraction Technique additionally Swin ViT model. Achived an accuracy of 985 with Swin. Future work is going on this project that uses Autoencoders for feature extraction.

yaseeng-md / Explicit-Content-Detection Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

This Project focus on detectin the Explicit Images using ViTs. I have used ViT with Feed Forward Patch extraction techqniqe and Conv based Patch Extraction Technique additionally Swin ViT model. Achived an accuracy of 985 with Swin. Future work is going on this project that uses Autoencoders for feature extraction.

1 star 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
.ipynb_checkpoints		.ipynb_checkpoints
Helpers		Helpers
History		History
Images		Images
Models		Models
_		_
__pycache__		__pycache__
Autoencoder Training.ipynb		Autoencoder Training.ipynb
CAE + Transformer.ipynb		CAE + Transformer.ipynb
Conv + Transformers.ipynb		Conv + Transformers.ipynb
Dataset_Loader.py		Dataset_Loader.py
Delete Corrupt files.ipynb		Delete Corrupt files.ipynb
FF + Transformer.ipynb		FF + Transformer.ipynb
Swin Transformer.ipynb		Swin Transformer.ipynb