Vit FaceMask Finetuned

🚀 Vision Transformer (ViT) for Face Mask Detection

A Vision Transformer (ViT) model pre - trained and fine - tuned on the Self - Curated Custom Face - Mask18K Dataset for face mask detection.

🚀 Quick Start

This Vision Transformer (ViT) model is pre - trained and fine - tuned on the Self Curated Custom Face - Mask18K Dataset (18k images, 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. and also in the paper "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale" by Dosovitskiy et al.

✨ Features

• Pre - trained and fine - tuned on a custom face mask dataset.
• Can be used for face mask detection tasks.
• The pre - trained pooler can be utilized for downstream tasks.

📚 Documentation

📋 Model description

The Vision Transformer (ViT) is a transformer encoder model (BERT - like) pretrained on a large collection of images in a supervised fashion, namely ImageNet - 21k, at a resolution of 224x224 pixels.

Images are presented to the model as a sequence of fixed - size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.

Note that this model does not provide any fine - tuned heads, as these were zero'd by Google researchers. However, the model does include the pre - trained pooler, which can be used for downstream tasks (such as image classification).

By pre - training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre - trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.

📊 Training Metrics

📊 Evaluation Metrics

📄 License

This project is licensed under the Apache - 2.0 license.