Pasta-Pizza-Ravioli Image Classifier

Introduction

The Pasta-Pizza-Ravioli model is an image classifier designed to distinguish between images of pasta, pizza, and ravioli. This model is part of the HuggingPics project and is built using PyTorch and Hugging Face Transformers.

Architecture

The model leverages the Vision Transformer (ViT) architecture, which is a state-of-the-art approach for image classification tasks. It is specifically tailored to perform well in distinguishing between the three classes: pasta, pizza, and ravioli.

Training

The model was trained using the HuggingPics framework, which allows for the creation of custom image classifiers. The training process focused on achieving high accuracy, with the final model reaching an accuracy of 93.75% on the evaluation dataset.

Guide: Running Locally

To run the model locally, follow these steps:

1. Clone the GitHub repository:

   git clone https://github.com/nateraw/huggingpics
   cd huggingpics
   

2. Open the Colab notebook HuggingPics to interact with the model.
3. Ensure you have the necessary dependencies installed:

   pip install torch transformers
   

4. Run the notebook to classify your images.

For optimal performance, consider using cloud GPUs such as those available on Google Colab or AWS.

License

The model and associated code are licensed under the MIT License, allowing for free use, modification, and distribution of the software, provided that all copies or substantial portions of the software include the original license notice.