README.md

Model Card

• Model Name: Food Type Image Detection Vision Transformer
• Original Model: Vision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224.
  • It was introduced in the paper An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy et al. and first released in this repository.
  • Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded.
  • Does not provide any fine-tuned heads, as these were zero'd by Google researchers.
• Model Type: Image Classification
• Model Architecture: Vision Transformer (ViT)
• Fine-tuning:
  • Fine-tuned on Food Image Classification Dataset by using 12 varieties of these 35 varieties
  • Optimizer: AdamW
  • Epochs: 20
• Model Performance: Achieved an accuracy of 96.23% on all of the kinds of Food Image Classification Dataset