Food Classifier [Food 101]

Visit Website

LIVE DEMO

Technologies used

• Pytorch
• Pytorch Vision
• Based on the Food101 Dataset.
• Used transfer learning with the EfficientNetB2 model.
• Deployed using HuggingFace Spaces.
• Used here with Gradio API for the demo.

Brief Summary of the Project

• This is a food classifier that can classify 101 different types of food based on the EffNEtB2 model.
• The model was trained on the Food101 dataset.
• The model was trained for 10 epochs with a batch size of 32.
• The model was then fine-tuned for 5 epochs with a batch size of 16.
• The models interface was made using the Gradio API.
• The model was deployed using the HuggingFace Spaces.