Deit FaceMask Finetuned

🚀 Distilled Data-efficient Image Transformer for Face Mask Detection

A pre - trained and fine - tuned Distilled data - efficient Image Transformer (DeiT) model for face mask detection on the Self Currated Custom Face - Mask18K Dataset.

🚀 Quick Start

This section provides a high - level overview of the model. The Distilled data - efficient Image Transformer (DeiT) model is pre - trained and fine - tuned on the Self Currated Custom Face - Mask18K Dataset, which contains 18k images with 2 classes at a resolution of 224x224. It was first introduced in the paper "Training data - efficient image transformers & distillation through attention" by Touvron et al.

✨ Features

• Distilled Vision Transformer: This model is a distilled Vision Transformer (ViT). It uses a distillation token in addition to the class token to learn effectively from a teacher (CNN) during both pre - training and fine - tuning.
• Patch - based Input: Images are presented to the model as a sequence of fixed - size patches (resolution 16x16), which are linearly embedded.

📚 Documentation

Model description

This model is a distilled Vision Transformer (ViT). It uses a distillation token, besides the class token, to effectively learn from a teacher (CNN) during both pre - training and fine - tuning. The distillation token is learned through backpropagation, by interacting with the class ([CLS]) and patch tokens through the self - attention layers.

Images are presented to the model as a sequence of fixed - size patches (resolution 16x16), which are linearly embedded.

Training Metrics

Evaluation Metrics

📄 License

This project is licensed under the Apache - 2.0 license.